HNS: Hierarchical negative sampling for network representation learning
Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used m...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Chen, Junyang [verfasserIn] Gong, Zhiguo [verfasserIn] Wang, Wei [verfasserIn] Liu, Weiwen [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2020 |
|---|
| Schlagwörter: |
Hierarchical negative sampling |
|---|
| Übergeordnetes Werk: |
Enthalten in: Information sciences - New York, NY : Elsevier Science Inc., 1968, 542, Seite 343-356 |
|---|---|
| Übergeordnetes Werk: |
volume:542 ; pages:343-356 |
| DOI / URN: |
10.1016/j.ins.2020.07.015 |
|---|
| Katalog-ID: |
ELV004679466 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV004679466 | ||
| 003 | DE-627 | ||
| 005 | 20230524132215.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230503s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.ins.2020.07.015 |2 doi | |
| 035 | |a (DE-627)ELV004679466 | ||
| 035 | |a (ELSEVIER)S0020-0255(20)30677-0 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 070 |a 004 |q DE-600 |
| 084 | |a LING |q DE-30 |2 fid | ||
| 084 | |a 54.00 |2 bkl | ||
| 084 | |a 53.71 |2 bkl | ||
| 100 | 1 | |a Chen, Junyang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a HNS: Hierarchical negative sampling for network representation learning |
| 264 | 1 | |c 2020 | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. | ||
| 650 | 4 | |a Hierarchical negative sampling | |
| 650 | 4 | |a Network representation learning | |
| 650 | 4 | |a Network embeddings | |
| 700 | 1 | |a Gong, Zhiguo |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Wei |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Weiwen |e verfasserin |0 (orcid)0000-0002-9148-3997 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Information sciences |d New York, NY : Elsevier Science Inc., 1968 |g 542, Seite 343-356 |h Online-Ressource |w (DE-627)271175850 |w (DE-600)1478990-5 |w (DE-576)078412293 |x 0020-0255 |7 nnns |
| 773 | 1 | 8 | |g volume:542 |g pages:343-356 |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a FID-LING | ||
| 912 | |a SSG-OPC-BBI | ||
| 912 | |a GBV_ILN_20 | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_23 | ||
| 912 | |a GBV_ILN_24 | ||
| 912 | |a GBV_ILN_31 | ||
| 912 | |a GBV_ILN_32 | ||
| 912 | |a GBV_ILN_40 | ||
| 912 | |a GBV_ILN_60 | ||
| 912 | |a GBV_ILN_62 | ||
| 912 | |a GBV_ILN_63 | ||
| 912 | |a GBV_ILN_65 | ||
| 912 | |a GBV_ILN_69 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_73 | ||
| 912 | |a GBV_ILN_74 | ||
| 912 | |a GBV_ILN_90 | ||
| 912 | |a GBV_ILN_95 | ||
| 912 | |a GBV_ILN_100 | ||
| 912 | |a GBV_ILN_101 | ||
| 912 | |a GBV_ILN_105 | ||
| 912 | |a GBV_ILN_110 | ||
| 912 | |a GBV_ILN_150 | ||
| 912 | |a GBV_ILN_151 | ||
| 912 | |a GBV_ILN_224 | ||
| 912 | |a GBV_ILN_370 | ||
| 912 | |a GBV_ILN_602 | ||
| 912 | |a GBV_ILN_702 | ||
| 912 | |a GBV_ILN_2003 | ||
| 912 | |a GBV_ILN_2004 | ||
| 912 | |a GBV_ILN_2005 | ||
| 912 | |a GBV_ILN_2011 | ||
| 912 | |a GBV_ILN_2014 | ||
| 912 | |a GBV_ILN_2015 | ||
| 912 | |a GBV_ILN_2020 | ||
| 912 | |a GBV_ILN_2021 | ||
| 912 | |a GBV_ILN_2025 | ||
| 912 | |a GBV_ILN_2027 | ||
| 912 | |a GBV_ILN_2034 | ||
| 912 | |a GBV_ILN_2038 | ||
| 912 | |a GBV_ILN_2044 | ||
| 912 | |a GBV_ILN_2048 | ||
| 912 | |a GBV_ILN_2049 | ||
| 912 | |a GBV_ILN_2050 | ||
| 912 | |a GBV_ILN_2056 | ||
| 912 | |a GBV_ILN_2059 | ||
| 912 | |a GBV_ILN_2061 | ||
| 912 | |a GBV_ILN_2064 | ||
| 912 | |a GBV_ILN_2065 | ||
| 912 | |a GBV_ILN_2068 | ||
| 912 | |a GBV_ILN_2111 | ||
| 912 | |a GBV_ILN_2112 | ||
| 912 | |a GBV_ILN_2113 | ||
| 912 | |a GBV_ILN_2118 | ||
| 912 | |a GBV_ILN_2122 | ||
| 912 | |a GBV_ILN_2129 | ||
| 912 | |a GBV_ILN_2143 | ||
| 912 | |a GBV_ILN_2147 | ||
| 912 | |a GBV_ILN_2148 | ||
| 912 | |a GBV_ILN_2152 | ||
| 912 | |a GBV_ILN_2153 | ||
| 912 | |a GBV_ILN_2190 | ||
| 912 | |a GBV_ILN_2336 | ||
| 912 | |a GBV_ILN_2507 | ||
| 912 | |a GBV_ILN_2522 | ||
| 912 | |a GBV_ILN_4035 | ||
| 912 | |a GBV_ILN_4037 | ||
| 912 | |a GBV_ILN_4112 | ||
| 912 | |a GBV_ILN_4125 | ||
| 912 | |a GBV_ILN_4126 | ||
| 912 | |a GBV_ILN_4242 | ||
| 912 | |a GBV_ILN_4251 | ||
| 912 | |a GBV_ILN_4305 | ||
| 912 | |a GBV_ILN_4313 | ||
| 912 | |a GBV_ILN_4323 | ||
| 912 | |a GBV_ILN_4324 | ||
| 912 | |a GBV_ILN_4325 | ||
| 912 | |a GBV_ILN_4326 | ||
| 912 | |a GBV_ILN_4333 | ||
| 912 | |a GBV_ILN_4334 | ||
| 912 | |a GBV_ILN_4335 | ||
| 912 | |a GBV_ILN_4338 | ||
| 912 | |a GBV_ILN_4393 | ||
| 936 | b | k | |a 54.00 |j Informatik: Allgemeines |
| 936 | b | k | |a 53.71 |j Theoretische Nachrichtentechnik |
| 951 | |a AR | ||
| 952 | |d 542 |h 343-356 | ||
| author_variant |
j c jc z g zg w w ww w l wl |
|---|---|
| matchkey_str |
article:00200255:2020----::nheaciangtvsmlnfrewrrp |
| hierarchy_sort_str |
2020 |
| bklnumber |
54.00 53.71 |
| publishDate |
2020 |
| allfields |
10.1016/j.ins.2020.07.015 doi (DE-627)ELV004679466 (ELSEVIER)S0020-0255(20)30677-0 DE-627 ger DE-627 rda eng 070 004 DE-600 LING DE-30 fid 54.00 bkl 53.71 bkl Chen, Junyang verfasserin aut HNS: Hierarchical negative sampling for network representation learning 2020 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. Hierarchical negative sampling Network representation learning Network embeddings Gong, Zhiguo verfasserin aut Wang, Wei verfasserin aut Liu, Weiwen verfasserin (orcid)0000-0002-9148-3997 aut Enthalten in Information sciences New York, NY : Elsevier Science Inc., 1968 542, Seite 343-356 Online-Ressource (DE-627)271175850 (DE-600)1478990-5 (DE-576)078412293 0020-0255 nnns volume:542 pages:343-356 GBV_USEFLAG_U SYSFLAG_U GBV_ELV FID-LING SSG-OPC-BBI GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.00 Informatik: Allgemeines 53.71 Theoretische Nachrichtentechnik AR 542 343-356 |
| spelling |
10.1016/j.ins.2020.07.015 doi (DE-627)ELV004679466 (ELSEVIER)S0020-0255(20)30677-0 DE-627 ger DE-627 rda eng 070 004 DE-600 LING DE-30 fid 54.00 bkl 53.71 bkl Chen, Junyang verfasserin aut HNS: Hierarchical negative sampling for network representation learning 2020 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. Hierarchical negative sampling Network representation learning Network embeddings Gong, Zhiguo verfasserin aut Wang, Wei verfasserin aut Liu, Weiwen verfasserin (orcid)0000-0002-9148-3997 aut Enthalten in Information sciences New York, NY : Elsevier Science Inc., 1968 542, Seite 343-356 Online-Ressource (DE-627)271175850 (DE-600)1478990-5 (DE-576)078412293 0020-0255 nnns volume:542 pages:343-356 GBV_USEFLAG_U SYSFLAG_U GBV_ELV FID-LING SSG-OPC-BBI GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.00 Informatik: Allgemeines 53.71 Theoretische Nachrichtentechnik AR 542 343-356 |
| allfields_unstemmed |
10.1016/j.ins.2020.07.015 doi (DE-627)ELV004679466 (ELSEVIER)S0020-0255(20)30677-0 DE-627 ger DE-627 rda eng 070 004 DE-600 LING DE-30 fid 54.00 bkl 53.71 bkl Chen, Junyang verfasserin aut HNS: Hierarchical negative sampling for network representation learning 2020 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. Hierarchical negative sampling Network representation learning Network embeddings Gong, Zhiguo verfasserin aut Wang, Wei verfasserin aut Liu, Weiwen verfasserin (orcid)0000-0002-9148-3997 aut Enthalten in Information sciences New York, NY : Elsevier Science Inc., 1968 542, Seite 343-356 Online-Ressource (DE-627)271175850 (DE-600)1478990-5 (DE-576)078412293 0020-0255 nnns volume:542 pages:343-356 GBV_USEFLAG_U SYSFLAG_U GBV_ELV FID-LING SSG-OPC-BBI GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.00 Informatik: Allgemeines 53.71 Theoretische Nachrichtentechnik AR 542 343-356 |
| allfieldsGer |
10.1016/j.ins.2020.07.015 doi (DE-627)ELV004679466 (ELSEVIER)S0020-0255(20)30677-0 DE-627 ger DE-627 rda eng 070 004 DE-600 LING DE-30 fid 54.00 bkl 53.71 bkl Chen, Junyang verfasserin aut HNS: Hierarchical negative sampling for network representation learning 2020 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. Hierarchical negative sampling Network representation learning Network embeddings Gong, Zhiguo verfasserin aut Wang, Wei verfasserin aut Liu, Weiwen verfasserin (orcid)0000-0002-9148-3997 aut Enthalten in Information sciences New York, NY : Elsevier Science Inc., 1968 542, Seite 343-356 Online-Ressource (DE-627)271175850 (DE-600)1478990-5 (DE-576)078412293 0020-0255 nnns volume:542 pages:343-356 GBV_USEFLAG_U SYSFLAG_U GBV_ELV FID-LING SSG-OPC-BBI GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.00 Informatik: Allgemeines 53.71 Theoretische Nachrichtentechnik AR 542 343-356 |
| allfieldsSound |
10.1016/j.ins.2020.07.015 doi (DE-627)ELV004679466 (ELSEVIER)S0020-0255(20)30677-0 DE-627 ger DE-627 rda eng 070 004 DE-600 LING DE-30 fid 54.00 bkl 53.71 bkl Chen, Junyang verfasserin aut HNS: Hierarchical negative sampling for network representation learning 2020 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. Hierarchical negative sampling Network representation learning Network embeddings Gong, Zhiguo verfasserin aut Wang, Wei verfasserin aut Liu, Weiwen verfasserin (orcid)0000-0002-9148-3997 aut Enthalten in Information sciences New York, NY : Elsevier Science Inc., 1968 542, Seite 343-356 Online-Ressource (DE-627)271175850 (DE-600)1478990-5 (DE-576)078412293 0020-0255 nnns volume:542 pages:343-356 GBV_USEFLAG_U SYSFLAG_U GBV_ELV FID-LING SSG-OPC-BBI GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.00 Informatik: Allgemeines 53.71 Theoretische Nachrichtentechnik AR 542 343-356 |
| language |
English |
| source |
Enthalten in Information sciences 542, Seite 343-356 volume:542 pages:343-356 |
| sourceStr |
Enthalten in Information sciences 542, Seite 343-356 volume:542 pages:343-356 |
| format_phy_str_mv |
Article |
| bklname |
Informatik: Allgemeines Theoretische Nachrichtentechnik |
| institution |
findex.gbv.de |
| topic_facet |
Hierarchical negative sampling Network representation learning Network embeddings |
| dewey-raw |
070 |
| isfreeaccess_bool |
false |
| container_title |
Information sciences |
| authorswithroles_txt_mv |
Chen, Junyang @@aut@@ Gong, Zhiguo @@aut@@ Wang, Wei @@aut@@ Liu, Weiwen @@aut@@ |
| publishDateDaySort_date |
2020-01-01T00:00:00Z |
| hierarchy_top_id |
271175850 |
| dewey-sort |
270 |
| id |
ELV004679466 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV004679466</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230524132215.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230503s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.ins.2020.07.015</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV004679466</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0020-0255(20)30677-0</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">070</subfield><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">LING</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">53.71</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chen, Junyang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">HNS: Hierarchical negative sampling for network representation learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hierarchical negative sampling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Network representation learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Network embeddings</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gong, Zhiguo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Wei</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Weiwen</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-9148-3997</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Information sciences</subfield><subfield code="d">New York, NY : Elsevier Science Inc., 1968</subfield><subfield code="g">542, Seite 343-356</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)271175850</subfield><subfield code="w">(DE-600)1478990-5</subfield><subfield code="w">(DE-576)078412293</subfield><subfield code="x">0020-0255</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:542</subfield><subfield code="g">pages:343-356</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-LING</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-BBI</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2038</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2065</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2113</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.00</subfield><subfield code="j">Informatik: Allgemeines</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">53.71</subfield><subfield code="j">Theoretische Nachrichtentechnik</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">542</subfield><subfield code="h">343-356</subfield></datafield></record></collection>
|
| author |
Chen, Junyang |
| spellingShingle |
Chen, Junyang ddc 070 fid LING bkl 54.00 bkl 53.71 misc Hierarchical negative sampling misc Network representation learning misc Network embeddings HNS: Hierarchical negative sampling for network representation learning |
| authorStr |
Chen, Junyang |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)271175850 |
| format |
electronic Article |
| dewey-ones |
070 - News media, journalism & publishing 004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| issn |
0020-0255 |
| topic_title |
070 004 DE-600 LING DE-30 fid 54.00 bkl 53.71 bkl HNS: Hierarchical negative sampling for network representation learning Hierarchical negative sampling Network representation learning Network embeddings |
| topic |
ddc 070 fid LING bkl 54.00 bkl 53.71 misc Hierarchical negative sampling misc Network representation learning misc Network embeddings |
| topic_unstemmed |
ddc 070 fid LING bkl 54.00 bkl 53.71 misc Hierarchical negative sampling misc Network representation learning misc Network embeddings |
| topic_browse |
ddc 070 fid LING bkl 54.00 bkl 53.71 misc Hierarchical negative sampling misc Network representation learning misc Network embeddings |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
cr |
| hierarchy_parent_title |
Information sciences |
| hierarchy_parent_id |
271175850 |
| dewey-tens |
070 - News media, journalism & publishing 000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Information sciences |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)271175850 (DE-600)1478990-5 (DE-576)078412293 |
| title |
HNS: Hierarchical negative sampling for network representation learning |
| ctrlnum |
(DE-627)ELV004679466 (ELSEVIER)S0020-0255(20)30677-0 |
| title_full |
HNS: Hierarchical negative sampling for network representation learning |
| author_sort |
Chen, Junyang |
| journal |
Information sciences |
| journalStr |
Information sciences |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2020 |
| contenttype_str_mv |
zzz |
| container_start_page |
343 |
| author_browse |
Chen, Junyang Gong, Zhiguo Wang, Wei Liu, Weiwen |
| container_volume |
542 |
| class |
070 004 DE-600 LING DE-30 fid 54.00 bkl 53.71 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Chen, Junyang |
| doi_str_mv |
10.1016/j.ins.2020.07.015 |
| normlink |
(ORCID)0000-0002-9148-3997 |
| normlink_prefix_str_mv |
(orcid)0000-0002-9148-3997 |
| dewey-full |
070 004 |
| author2-role |
verfasserin |
| title_sort |
hns: hierarchical negative sampling for network representation learning |
| title_auth |
HNS: Hierarchical negative sampling for network representation learning |
| abstract |
Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. |
| abstractGer |
Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. |
| abstract_unstemmed |
Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks. |
| collection_details |
GBV_USEFLAG_U SYSFLAG_U GBV_ELV FID-LING SSG-OPC-BBI GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 |
| title_short |
HNS: Hierarchical negative sampling for network representation learning |
| remote_bool |
true |
| author2 |
Gong, Zhiguo Wang, Wei Liu, Weiwen |
| author2Str |
Gong, Zhiguo Wang, Wei Liu, Weiwen |
| ppnlink |
271175850 |
| mediatype_str_mv |
c |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1016/j.ins.2020.07.015 |
| up_date |
2024-07-06T23:48:02.633Z |
| _version_ |
1803875445779726336 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV004679466</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230524132215.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230503s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.ins.2020.07.015</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV004679466</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0020-0255(20)30677-0</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">070</subfield><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">LING</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">53.71</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Chen, Junyang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">HNS: Hierarchical negative sampling for network representation learning</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Network representation learning (NRL) aims at modeling network graph by encoding vertices and edges into a low-dimensional space. These learned representations can be used for subsequent applications, such as vertex classification and link prediction. Negative Sampling (NS) is the most widely used method for boosting the performance of NRL. However, most of the existing work only randomly draws negative samples based on vertex frequencies, i.e., the vertices with higher frequency are more likely to be drawn, which ignores the situation that the sampled one may not be a true negative sample, thus, lead to undesirable embeddings. In this paper, we propose a new negative sampling method, called Hierarchical Negative Sampling (HNS), which is able to model the latent structures of vertices and learn the relations among them. During sampling, HNS can draw more appropriate negative samples and thereby obtain better performance on network embeddings. Firstly, we theoretically demonstrate the superiority of HNS over NS. And then we use experimental results to show that our proposed method outperforms the state-of-the-art models on vertex classification tasks at different training scales in real-world networks.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Hierarchical negative sampling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Network representation learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Network embeddings</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Gong, Zhiguo</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Wei</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Liu, Weiwen</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-9148-3997</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Information sciences</subfield><subfield code="d">New York, NY : Elsevier Science Inc., 1968</subfield><subfield code="g">542, Seite 343-356</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)271175850</subfield><subfield code="w">(DE-600)1478990-5</subfield><subfield code="w">(DE-576)078412293</subfield><subfield code="x">0020-0255</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:542</subfield><subfield code="g">pages:343-356</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-LING</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-BBI</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2038</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2065</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2113</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.00</subfield><subfield code="j">Informatik: Allgemeines</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">53.71</subfield><subfield code="j">Theoretische Nachrichtentechnik</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">542</subfield><subfield code="h">343-356</subfield></datafield></record></collection>
|
| score |
7.401019 |