Handling information loss of graph convolutional networks in collaborative filtering
Collaborative filtering (CF) methods based on graph convolutional network (GCN) and autoencoder (AE) achieve outstanding performance. But the GCN-based CF methods suffer from information loss problems, which are caused by information lossy initialization and using low-order Chebyshev Polynomial to f...
Gespeichert in:
| Veröffentlicht in: | Information systems (Oxford) Jg. 109; S. 102051 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier Ltd
01.11.2022
|
| Schlagworte: | |
| ISSN: | 0306-4379, 1873-6076 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Collaborative filtering (CF) methods based on graph convolutional network (GCN) and autoencoder (AE) achieve outstanding performance. But the GCN-based CF methods suffer from information loss problems, which are caused by information lossy initialization and using low-order Chebyshev Polynomial to fit the graph convolution kernel. And the AE-based CF methods obtain the prediction results by reconstructing the user-item interaction matrix, which does not conduct deep excavation of the behavior patterns, resulting in the limited-expression ability.
To solve the above problems, we propose Variational AutoEncoder-Enhanced Graph Convolutional Network (VE-GCN) for CF. Specifically, we use a variational autoencoder (VAE) to compress the interactive behavior patterns as the prior information of GCN to achieve sufficient learning, thus alleviating the information lossy initialization problem. And then the generalized graph Laplacian convolution kernel is proposed in GCN to handle the high-frequency information loss problem caused by Chebyshev Polynomial fitting in the GCN-based CF. To the best of our knowledge, VE-GCN is a feasible method to handle the information loss problems mentioned above in GCN-based CF for the first time. Meanwhile, the structure of GCN is optimized by removing redundant feature transformation and nonlinear activation function, and using DenseGCN to complete multi-level information interaction. Experiments on four real-world datasets show that the VE-GCN achieves state-of-the-art performance.
•The information loss in Graph Convolutional Network-based Collaborative Filtering.•The enhanced Graph Convolutional Network.•The optimized Laplacian convolution kernel.•The optimized information propagation framework of Graph Convolutional Network. |
|---|---|
| AbstractList | Collaborative filtering (CF) methods based on graph convolutional network (GCN) and autoencoder (AE) achieve outstanding performance. But the GCN-based CF methods suffer from information loss problems, which are caused by information lossy initialization and using low-order Chebyshev Polynomial to fit the graph convolution kernel. And the AE-based CF methods obtain the prediction results by reconstructing the user-item interaction matrix, which does not conduct deep excavation of the behavior patterns, resulting in the limited-expression ability.
To solve the above problems, we propose Variational AutoEncoder-Enhanced Graph Convolutional Network (VE-GCN) for CF. Specifically, we use a variational autoencoder (VAE) to compress the interactive behavior patterns as the prior information of GCN to achieve sufficient learning, thus alleviating the information lossy initialization problem. And then the generalized graph Laplacian convolution kernel is proposed in GCN to handle the high-frequency information loss problem caused by Chebyshev Polynomial fitting in the GCN-based CF. To the best of our knowledge, VE-GCN is a feasible method to handle the information loss problems mentioned above in GCN-based CF for the first time. Meanwhile, the structure of GCN is optimized by removing redundant feature transformation and nonlinear activation function, and using DenseGCN to complete multi-level information interaction. Experiments on four real-world datasets show that the VE-GCN achieves state-of-the-art performance.
•The information loss in Graph Convolutional Network-based Collaborative Filtering.•The enhanced Graph Convolutional Network.•The optimized Laplacian convolution kernel.•The optimized information propagation framework of Graph Convolutional Network. |
| ArticleNumber | 102051 |
| Author | Yin, Jian Hu, YouPeng Li, XunKai Wu, YiXuan Xiong, Xin |
| Author_xml | – sequence: 1 givenname: Xin orcidid: 0000-0002-3072-7302 surname: Xiong fullname: Xiong, Xin email: xiongxin@smail.nju.edu.cn organization: Nanjing University, School of Artificial Intelligence, No.163 Xianlin Avenue, Qixia District, Nanjing City, Jiangsu Province, China – sequence: 2 givenname: XunKai orcidid: 0000-0002-1230-7603 surname: Li fullname: Li, XunKai email: lxk_yb@163.com organization: Shandong University, School of Mechanical, Electrical and Information Engineering, No.180 Wenhua West Road, Weihai City, Shandong Province, China – sequence: 3 givenname: YouPeng orcidid: 0000-0003-2097-5879 surname: Hu fullname: Hu, YouPeng email: yoooooohu@gmail.com organization: Shandong University, School of Mechanical, Electrical and Information Engineering, No.180 Wenhua West Road, Weihai City, Shandong Province, China – sequence: 4 givenname: YiXuan orcidid: 0000-0001-8364-3228 surname: Wu fullname: Wu, YiXuan email: beixuan_wh@163.com organization: Zhejiang University, Polytechnic Institute, No. 269 Shixiang Road, Hangzhou City, Zhejiang Province, China – sequence: 5 givenname: Jian orcidid: 0000-0002-4820-0226 surname: Yin fullname: Yin, Jian email: yinjian@sdu.edu.cn organization: Shandong University, School of Mechanical, Electrical and Information Engineering, No.180 Wenhua West Road, Weihai City, Shandong Province, China |
| BookMark | eNp9kEFPAyEUhImpiW317pE_sPUBXXbxZhq1Jk281DNhWahUCg2sNf57qfVkoqeXyeSbvJkJGoUYDELXBGYECL_ZzlyeUaC0SAo1OUNj0jas4tDwERoDA17NWSMu0CTnLQDQWogxWi9V6L0LG-yCjWmnBhcD9jFnHC3eJLV_xTqGQ_TvR0d5HMzwEdNbLkBxvFddTIU6GGydH0wqWZfo3CqfzdXPnaKXh_v1Ylmtnh-fFnerSlMxH6padX2vLDFWtExbPeeWtF3b1YyC6kzTEKY5EQa6vlZNTYSlQtdt37WgueWMTRE_5epUHk7GSu2G7wZDUs5LAvK4jdxKl-VxG3napoDwC9wnt1Pp8z_k9oSYUujgTJJZOxO06V0yepB9dH_DX_v0f7I |
| CitedBy_id | crossref_primary_10_1007_s00521_023_08958_3 crossref_primary_10_1016_j_neucom_2025_129546 crossref_primary_10_1016_j_is_2023_102335 crossref_primary_10_1155_2022_7787633 crossref_primary_10_1016_j_is_2023_102322 crossref_primary_10_1109_ACCESS_2024_3365549 crossref_primary_10_1016_j_is_2024_102488 |
| Cites_doi | 10.7551/mitpress/1113.003.0010 10.1145/3038912.3052569 10.1145/3178876.3186150 10.1145/3397271.3401063 10.1609/aaai.v33i01.330161 10.1038/44565 10.1609/aaai.v34i01.5330 10.1145/3394486.3403170 10.1145/371920.372071 10.24963/ijcai.2019/630 10.1145/3394486.3403140 10.1109/MC.2009.263 10.1145/3331184.3331267 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier Ltd |
| Copyright_xml | – notice: 2022 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.is.2022.102051 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1873-6076 |
| ExternalDocumentID | 10_1016_j_is_2022_102051 S0306437922000448 |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61971268 funderid: http://dx.doi.org/10.13039/501100001809 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 13V 1B1 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 63O 7-5 71M 77K 8P~ 9JN 9JO AAAKF AAAKG AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXUO AAYFN ABBOA ABFNM ABKBG ABMAC ABMVD ABTAH ABUCO ABXDB ABYKQ ACDAQ ACGFS ACHRH ACNNM ACNTT ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD AEBSH AEKER AENEX AFFNX AFKWA AFTJW AGHFR AGJBL AGUBO AGUMN AGYEJ AHHHB AHZHX AI. AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALEQD ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC BNSAS CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HAMUX HF~ HLZ HVGLF HZ~ H~9 IHE J1W KOM LG9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SSB SSD SSL SSV SSZ T5K TN5 UHS VH1 WUQ XSW ZCG ZY4 ~G- 77I 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABJNI ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c294t-5abddaf1ef983cfc46f18b8b5320abe7713c619e0bd5a7519f29c58db80c6f633 |
| ISICitedReferencesCount | 11 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000798811300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0306-4379 |
| IngestDate | Tue Nov 18 21:12:24 EST 2025 Sat Nov 29 07:25:35 EST 2025 Fri Feb 23 02:40:56 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Variational autoencoder Graph convolutional network Collaborative filtering Recommender system |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c294t-5abddaf1ef983cfc46f18b8b5320abe7713c619e0bd5a7519f29c58db80c6f633 |
| ORCID | 0000-0002-1230-7603 0000-0002-4820-0226 0000-0002-3072-7302 0000-0001-8364-3228 0000-0003-2097-5879 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_is_2022_102051 crossref_primary_10_1016_j_is_2022_102051 elsevier_sciencedirect_doi_10_1016_j_is_2022_102051 |
| PublicationCentury | 2000 |
| PublicationDate | November 2022 2022-11-00 |
| PublicationDateYYYYMMDD | 2022-11-01 |
| PublicationDate_xml | – month: 11 year: 2022 text: November 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | Information systems (Oxford) |
| PublicationYear | 2022 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Kipf, Welling (b7) 2016 Kingma, Ba (b40) 2014 Pham, Cao, Klamma, Jarke (b2) 2011; 17 Kingma, Welling (b22) 2013 Li, Muller, Thabet, Ghanem (b33) 2019 Wu, Souza, Zhang, Fifty, Yu, Weinberger (b25) 2019 Berg, Kipf, Welling (b23) 2017 Koren, Bell, Volinsky (b3) 2009; 42 Fenyu Hu, Yanqiao Zhu, Shu Wu, Liang Wang, Tieniu Tan, Hierarchical graph convolutional networks for semi-supervised node classification, in: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, pp. 4532–4539. Herbrich (b38) 2000 Badrul Sarwar, George Karypis, Joseph Konstan, John Riedl, Item-based collaborative filtering recommendation algorithms, in: Proceedings of the 10th International Conference on World Wide Web, 2001, pp. 285–295. Zhang, Shi, Zhao, King (b24) 2019 Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, Lars BPR Schmidt-Thieme, Bayesian personalized ranking from implicit feedback, in: Proc. of Uncertainty in Artificial Intelligence, 2014, pp. 452–461. Yun, Jing, Gang (b4) 2019; 36 Scholz (b31) 2006 Ganqu Cui, Jie Zhou, Cheng Yang, Zhiyuan Liu, Adaptive graph encoder for attributed graph embedding, in: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2020, pp. 976–985. Tianwen Chen, RaymondChi-Wing Wong, Handling information loss of graph neural networks for session-based recommendation, in: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 1172–1180. Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, Meng Wang, Lightgcn: Simplifying and powering graph convolution network for recommendation, in: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020, pp. 639–648. Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, Tat-Seng Chua, Neural collaborative filtering, in: Proceedings of the 26th International Conference on World Wide Web, 2017, pp. 173–182. Powers (b37) 2011 Lee, Seung (b6) 1999; 401 Yu, Qin (b26) 2020 He, Du, Wang, Tian, Tang, Chua (b14) 2018 Rong, Huang, Xu, Huang (b16) 2020 Xia, Li, Gu, Lu, Zhang, Gu (b19) 2021 Xavier Glorot, Yoshua Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010, pp. 249–256. Lei Chen, Le Wu, Richang Hong, Kun Zhang, Meng Wang, Revisiting graph based collaborative filtering: A linear residual graph convolutional network approach, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 2020, pp. 27–34. Peng, Mine (b21) 2020 Jenatton, Roux, Bordes, Obozinski (b5) 2012 Vahdat, Kautz (b29) 2020; 33 Veličković, Cucurull, Casanova, Romero, Lio, Bengio (b9) 2017 Defferrard, Bresson, Vandergheynst (b35) 2016 X. Glorot, A. Bordes, Y. Bengio, Deep sparse rectifier neural networks, in: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), 2011, pp. 315–323. Higgins, Matthey, Pal, Burgess, Glorot, Botvinick, Mohamed, Lerchner (b27) 2017 Dawen Liang, Rahul G Krishnan, Matthew D Hoffman, Tony Jebara, Variational autoencoders for collaborative filtering, in: Proceedings of the 2018 World Wide Web Conference, 2018, pp. 689–698. Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, Tat-Seng Chua, Neural graph collaborative filtering, in: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019, pp. 165–174. Bo, Wang, Shi, Shen (b18) 2021 Zhi-Hong Deng, Ling Huang, Chang-Dong Wang, Jian-Huang Lai, S Yu Philip, Deepcf: A unified framework of representation learning and matching function learning in recommender system, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 61–68. Hamilton, Ying, Leskovec (b8) 2017 Chen, Li, Grosse, Duvenaud (b28) 2018 Yu (10.1016/j.is.2022.102051_b26) 2020 Jenatton (10.1016/j.is.2022.102051_b5) 2012 Vahdat (10.1016/j.is.2022.102051_b29) 2020; 33 Herbrich (10.1016/j.is.2022.102051_b38) 2000 Scholz (10.1016/j.is.2022.102051_b31) 2006 Higgins (10.1016/j.is.2022.102051_b27) 2017 Peng (10.1016/j.is.2022.102051_b21) 2020 Bo (10.1016/j.is.2022.102051_b18) 2021 Li (10.1016/j.is.2022.102051_b33) 2019 Zhang (10.1016/j.is.2022.102051_b24) 2019 Berg (10.1016/j.is.2022.102051_b23) 2017 Wu (10.1016/j.is.2022.102051_b25) 2019 Powers (10.1016/j.is.2022.102051_b37) 2011 Yun (10.1016/j.is.2022.102051_b4) 2019; 36 Veličković (10.1016/j.is.2022.102051_b9) 2017 10.1016/j.is.2022.102051_b20 Kipf (10.1016/j.is.2022.102051_b7) 2016 Lee (10.1016/j.is.2022.102051_b6) 1999; 401 Xia (10.1016/j.is.2022.102051_b19) 2021 Hamilton (10.1016/j.is.2022.102051_b8) 2017 Kingma (10.1016/j.is.2022.102051_b22) 2013 10.1016/j.is.2022.102051_b1 Pham (10.1016/j.is.2022.102051_b2) 2011; 17 Defferrard (10.1016/j.is.2022.102051_b35) 2016 10.1016/j.is.2022.102051_b36 10.1016/j.is.2022.102051_b13 10.1016/j.is.2022.102051_b12 10.1016/j.is.2022.102051_b34 10.1016/j.is.2022.102051_b11 He (10.1016/j.is.2022.102051_b14) 2018 10.1016/j.is.2022.102051_b17 10.1016/j.is.2022.102051_b39 Chen (10.1016/j.is.2022.102051_b28) 2018 10.1016/j.is.2022.102051_b15 Koren (10.1016/j.is.2022.102051_b3) 2009; 42 Kingma (10.1016/j.is.2022.102051_b40) 2014 10.1016/j.is.2022.102051_b10 10.1016/j.is.2022.102051_b32 10.1016/j.is.2022.102051_b30 Rong (10.1016/j.is.2022.102051_b16) 2020 |
| References_xml | – start-page: 9266 year: 2019 end-page: 9275 ident: b33 article-title: Deepgcns: Can GCNs go as deep as CNNs? publication-title: 2019 IEEE/CVF International Conference on Computer Vision (ICCV) – reference: Tianwen Chen, RaymondChi-Wing Wong, Handling information loss of graph neural networks for session-based recommendation, in: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 1172–1180. – year: 2017 ident: b23 article-title: Graph convolutional matrix completion – year: 2006 ident: b31 article-title: Maximum likelihood estimation publication-title: Wiley StatsRef: Statist. Ref. Online – year: 2016 ident: b7 article-title: Semi-supervised classification with graph convolutional networks – volume: 401 start-page: 788 year: 1999 end-page: 791 ident: b6 article-title: Learning the parts of objects by non-negative matrix factorization publication-title: Nature – volume: 36 start-page: 245 year: 2019 end-page: 250 ident: b4 article-title: Recommendation algorithm based on funksvd matrix decomposition and similarity matrix publication-title: Jisuanji Yingyong Yuruanjian – start-page: 115 year: 2000 end-page: 132 ident: b38 article-title: Large margin rank boundaries for ordinal regression publication-title: Adv. Large Margin Classif. – reference: Badrul Sarwar, George Karypis, Joseph Konstan, John Riedl, Item-based collaborative filtering recommendation algorithms, in: Proceedings of the 10th International Conference on World Wide Web, 2001, pp. 285–295. – volume: 42 start-page: 30 year: 2009 end-page: 37 ident: b3 article-title: Matrix factorization techniques for recommender systems publication-title: Computer – reference: Lei Chen, Le Wu, Richang Hong, Kun Zhang, Meng Wang, Revisiting graph based collaborative filtering: A linear residual graph convolutional network approach, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 2020, pp. 27–34. – year: 2017 ident: b8 article-title: Inductive representation learning on large graphs – reference: Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, Meng Wang, Lightgcn: Simplifying and powering graph convolution network for recommendation, in: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020, pp. 639–648. – year: 2020 ident: b21 article-title: A robust hierarchical graph convolutional network model for collaborative filtering – year: 2021 ident: b18 article-title: Beyond low-frequency information in graph convolutional networks – reference: Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, Lars BPR Schmidt-Thieme, Bayesian personalized ranking from implicit feedback, in: Proc. of Uncertainty in Artificial Intelligence, 2014, pp. 452–461. – year: 2017 ident: b9 article-title: Graph attention networks – year: 2019 ident: b24 article-title: STAR-GCN: Stacked and reconstructed graph convolutional networks for recommender systems – year: 2018 ident: b14 article-title: Outer product-based neural collaborative filtering – year: 2020 ident: b16 article-title: DropEdge: TOwards deep graph convolutional networks on node classification publication-title: ICLR 2020 : Eighth International Conference on Learning Representations – reference: Fenyu Hu, Yanqiao Zhu, Shu Wu, Liang Wang, Tieniu Tan, Hierarchical graph convolutional networks for semi-supervised node classification, in: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019, pp. 4532–4539. – year: 2018 ident: b28 article-title: Isolating sources of disentanglement in variational autoencoders publication-title: ICLR (Workshop) – reference: X. Glorot, A. Bordes, Y. Bengio, Deep sparse rectifier neural networks, in: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), 2011, pp. 315–323. – reference: Dawen Liang, Rahul G Krishnan, Matthew D Hoffman, Tony Jebara, Variational autoencoders for collaborative filtering, in: Proceedings of the 2018 World Wide Web Conference, 2018, pp. 689–698. – reference: Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, Tat-Seng Chua, Neural collaborative filtering, in: Proceedings of the 26th International Conference on World Wide Web, 2017, pp. 173–182. – reference: Ganqu Cui, Jie Zhou, Cheng Yang, Zhiyuan Liu, Adaptive graph encoder for attributed graph embedding, in: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2020, pp. 976–985. – reference: Zhi-Hong Deng, Ling Huang, Chang-Dong Wang, Jian-Huang Lai, S Yu Philip, Deepcf: A unified framework of representation learning and matching function learning in recommender system, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 61–68. – reference: Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, Tat-Seng Chua, Neural graph collaborative filtering, in: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019, pp. 165–174. – start-page: 6861 year: 2019 end-page: 6871 ident: b25 article-title: Simplifying graph convolutional networks publication-title: International Conference on Machine Learning – volume: 33 start-page: 19667 year: 2020 end-page: 19679 ident: b29 article-title: NVAE: A Deep hierarchical variational autoencoder publication-title: Advances in Neural Information Processing Systems – year: 2016 ident: b35 article-title: Convolutional neural networks on graphs with fast localized spectral filtering – year: 2014 ident: b40 article-title: Adam: A method for stochastic optimization – start-page: 2170 year: 2021 end-page: 2179 ident: b19 article-title: Incremental graph convolutional network for collaborative filtering publication-title: Proceedings of the 30th ACM International Conference on Information & Knowledge Management – year: 2013 ident: b22 article-title: Auto-encoding variational bayes – year: 2017 ident: b27 article-title: Beta-VAE: Learning basic visual concepts with a constrained variational framework publication-title: ICLR 2017 : International Conference on Learning Representations 2017 – start-page: 10936 year: 2020 end-page: 10945 ident: b26 article-title: Graph convolutional network for recommendation with low-pass collaborative filters publication-title: ICML 2020: 37th International Conference on Machine Learning, Vol. 1 – volume: 17 start-page: 583 year: 2011 end-page: 604 ident: b2 article-title: A clustering approach for collaborative filtering recommendation using social network analysis publication-title: J. UCS – start-page: 37 year: 2011 end-page: 63 ident: b37 article-title: Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation – reference: Xavier Glorot, Yoshua Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010, pp. 249–256. – start-page: 3167 year: 2012 end-page: 3175 ident: b5 article-title: A latent factor model for highly multi-relational data publication-title: Advances in Neural Information Processing Systems 25, Vol. 25 – year: 2020 ident: 10.1016/j.is.2022.102051_b16 article-title: DropEdge: TOwards deep graph convolutional networks on node classification – start-page: 115 year: 2000 ident: 10.1016/j.is.2022.102051_b38 article-title: Large margin rank boundaries for ordinal regression publication-title: Adv. Large Margin Classif. doi: 10.7551/mitpress/1113.003.0010 – ident: 10.1016/j.is.2022.102051_b13 doi: 10.1145/3038912.3052569 – year: 2017 ident: 10.1016/j.is.2022.102051_b23 – ident: 10.1016/j.is.2022.102051_b30 – ident: 10.1016/j.is.2022.102051_b32 doi: 10.1145/3178876.3186150 – year: 2006 ident: 10.1016/j.is.2022.102051_b31 article-title: Maximum likelihood estimation publication-title: Wiley StatsRef: Statist. Ref. Online – year: 2016 ident: 10.1016/j.is.2022.102051_b35 – ident: 10.1016/j.is.2022.102051_b34 – ident: 10.1016/j.is.2022.102051_b11 doi: 10.1145/3397271.3401063 – year: 2018 ident: 10.1016/j.is.2022.102051_b28 article-title: Isolating sources of disentanglement in variational autoencoders – ident: 10.1016/j.is.2022.102051_b39 – start-page: 2170 year: 2021 ident: 10.1016/j.is.2022.102051_b19 article-title: Incremental graph convolutional network for collaborative filtering – start-page: 37 year: 2011 ident: 10.1016/j.is.2022.102051_b37 – volume: 17 start-page: 583 year: 2011 ident: 10.1016/j.is.2022.102051_b2 article-title: A clustering approach for collaborative filtering recommendation using social network analysis publication-title: J. UCS – ident: 10.1016/j.is.2022.102051_b36 doi: 10.1609/aaai.v33i01.330161 – year: 2018 ident: 10.1016/j.is.2022.102051_b14 – volume: 401 start-page: 788 issue: 6755 year: 1999 ident: 10.1016/j.is.2022.102051_b6 article-title: Learning the parts of objects by non-negative matrix factorization publication-title: Nature doi: 10.1038/44565 – ident: 10.1016/j.is.2022.102051_b12 doi: 10.1609/aaai.v34i01.5330 – start-page: 3167 year: 2012 ident: 10.1016/j.is.2022.102051_b5 article-title: A latent factor model for highly multi-relational data – ident: 10.1016/j.is.2022.102051_b20 doi: 10.1145/3394486.3403170 – year: 2017 ident: 10.1016/j.is.2022.102051_b8 – start-page: 10936 year: 2020 ident: 10.1016/j.is.2022.102051_b26 article-title: Graph convolutional network for recommendation with low-pass collaborative filters – year: 2021 ident: 10.1016/j.is.2022.102051_b18 – start-page: 9266 year: 2019 ident: 10.1016/j.is.2022.102051_b33 article-title: Deepgcns: Can GCNs go as deep as CNNs? – year: 2017 ident: 10.1016/j.is.2022.102051_b9 – ident: 10.1016/j.is.2022.102051_b1 doi: 10.1145/371920.372071 – start-page: 6861 year: 2019 ident: 10.1016/j.is.2022.102051_b25 article-title: Simplifying graph convolutional networks – year: 2014 ident: 10.1016/j.is.2022.102051_b40 – year: 2017 ident: 10.1016/j.is.2022.102051_b27 article-title: Beta-VAE: Learning basic visual concepts with a constrained variational framework – ident: 10.1016/j.is.2022.102051_b17 doi: 10.24963/ijcai.2019/630 – ident: 10.1016/j.is.2022.102051_b15 doi: 10.1145/3394486.3403140 – volume: 42 start-page: 30 issue: 8 year: 2009 ident: 10.1016/j.is.2022.102051_b3 article-title: Matrix factorization techniques for recommender systems publication-title: Computer doi: 10.1109/MC.2009.263 – year: 2019 ident: 10.1016/j.is.2022.102051_b24 – volume: 36 start-page: 245 issue: 12 year: 2019 ident: 10.1016/j.is.2022.102051_b4 article-title: Recommendation algorithm based on funksvd matrix decomposition and similarity matrix publication-title: Jisuanji Yingyong Yuruanjian – volume: 33 start-page: 19667 year: 2020 ident: 10.1016/j.is.2022.102051_b29 article-title: NVAE: A Deep hierarchical variational autoencoder – year: 2020 ident: 10.1016/j.is.2022.102051_b21 – year: 2016 ident: 10.1016/j.is.2022.102051_b7 – ident: 10.1016/j.is.2022.102051_b10 doi: 10.1145/3331184.3331267 – year: 2013 ident: 10.1016/j.is.2022.102051_b22 |
| SSID | ssj0002599 |
| Score | 2.405115 |
| Snippet | Collaborative filtering (CF) methods based on graph convolutional network (GCN) and autoencoder (AE) achieve outstanding performance. But the GCN-based CF... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 102051 |
| SubjectTerms | Collaborative filtering Graph convolutional network Recommender system Variational autoencoder |
| Title | Handling information loss of graph convolutional networks in collaborative filtering |
| URI | https://dx.doi.org/10.1016/j.is.2022.102051 |
| Volume | 109 |
| WOSCitedRecordID | wos000798811300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-6076 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002599 issn: 0306-4379 databaseCode: AIEXJ dateStart: 19950301 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwEB6VLQc4QClUFErlAxeEUrLxJrGPFSrqA1UcFpRbZDuOlFWVrbq7qD-f8SsPShE9cIkiy55Ymc-eGXv8GeD9TAupU6EjJSkGKGggIyETFTFFqcrRpDFLpP3ja355yYqChx3dlb1OIG9bdnvLr_-rqrEMlW2Ozj5A3Z1QLMB3VDo-Ue34_CfFnxreBHdSpTuZ-PEKbaHxCy0_tU01931ADbUuE9wmxg5gYejAG7OXHozbIiS992IdD7RduHUnDwcLC0Xjs32Lpk_7sbkDxaa9EE0PKGsGlptv2n_I2AhX2BQbj16_MIEx7bRbmPAHsuIsMnSHo8k25oPpEr2b2PHN3pnJ3aLCAkUdGeFHfdUxafZvxqxLMQzZa4uyWZVGQukkPILtJE85m8D28dlJcd6ZbYwDudtycr32e9ouGXDciz_7MAO_ZL4Dz3xAQY4dEF7Alm534Xm4rIP4uXsXng6YJ1_CPKCEDFBCDErIsiYWJWSEEhJQgg3ICCWkQ8kr-P7lZP75NPIXbEQq4bN1lApZVaKe6pozqmo1y-opk0yay0JwCONQpQoDbB3LKhU5-vp1wlXKKslildUZpXswaZetfg0krxOmkyoWWG8mMs6rRGc42KWiAj3IfB8-hV9WKs8-by5BuSrvU9Q-fOhaXDvmlb_UpUELpfccnUdYIpzubfXmAV94C096jB_AZH2z0e_gsfq5blY3hx5LvwAfAo7v |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Handling+information+loss+of+graph+convolutional+networks+in+collaborative+filtering&rft.jtitle=Information+systems+%28Oxford%29&rft.au=Xiong%2C+Xin&rft.au=Li%2C+XunKai&rft.au=Hu%2C+YouPeng&rft.au=Wu%2C+YiXuan&rft.date=2022-11-01&rft.issn=0306-4379&rft.volume=109&rft.spage=102051&rft_id=info:doi/10.1016%2Fj.is.2022.102051&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_is_2022_102051 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-4379&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-4379&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-4379&client=summon |