|
一种超图和自监督的协同训练算法
|
Abstract:
为了针对会话推荐中节点数量与图规模不断扩增而产生的节点稀疏问题,提出一种超图与自监督协同训练算法——DHCN-COTREC (Dual-Channel Convolutional for Hypergraphs and Collaborative Training Recommendation)。首先,构建两个不同的图编码器,将数据进行编码用于自监督学习,产生正负样本信息;其次,引入协同训练算法,并加入发散约束进行对比学习,从而最大化两个编码器之间的互信息;最后,根据序列中最后一个项目与正样本之间的余弦距离,向用户推荐TOP-K个项目。本文在Tmall与Diginetica真实数据集上进行实验,结果表明,DHCN-COTREC算法的准确度和平均倒数排名比目前最优的DHCN算法分别提高了26%和1.92%。证实了DHCN-COTREC算法的有效性。
In order to address the problem of sparse nodes in recommendation systems caused by the in-creasing number of nodes and graph size in session-based recommendation, a cotraining algorithm called DHCN-COTREC using hypergraphs and self-supervised learning is proposed. Firstly, two different graph encoders are constructed to encode the data for self-supervised learning, generating positive and negative sample information. Secondly, a cotraining algorithm is introduced, and divergent constraints are added for contrastive learning to maximize the mutual information between the two encoders. Finally, TOP-K items are recommended to users based on the cosine distance between the last item in the sequence and positive samples. The experiment was conducted on Tmall and Diginetica real datasets, and the results showed that the accuracy and average recip-rocal rank of DHCN-COTREC algorithm were improved by 26% and 1.92% respectively compared with the current optimal DHCN algorithm, which confirms the effectiveness of the DHCN-COTREC algorithm.
[1] | Patra, B.K., Launonen, R., Ollikainen, V., et al. (2014) Exploiting Bhattacharyya Similarity Measure to Diminish User Cold-Start Problem in Sparse Data. Discovery Science: 17th International Conference, DS 2014, Bled, 8-10 October 2014, 252-263. https://doi.org/10.1007/978-3-319-11812-3_22 |
[2] | Thakkar, P., Varma, K., Ukani, V., et al. (2019) Combining User-Based and Item-Based Collaborative Filtering Using Machine Learning. In: Satapathy, S. and Joshi, A., (Eds.), Information and Communication Technology for Intelligent Systems, Springer, Singapore, 173-180. https://doi.org/10.1007/978-981-13-1747-7_17 |
[3] | Hidasi, B., Karatzoglou, A., Baltrunas, L., et al. (2015) Ses-sion-Based Recommendations with Recurrent Neural Networks. arXiv: 1511.06939. |
[4] | Wu, S., Tang, Y., Zhu, Y., et al. (2019) Session-Based Recommendation with Graph Neural Networks. Proceedings of the Thirty-Third AAAI Con-ference on Artificial Intelligence, Honolulu, 27 January 2019 - 1 February 2019, 346-353.
https://doi.org/10.1609/aaai.v33i01.3301346 |
[5] | Feng, Y., You, H., Zhang, Z., et al. (2019) Hypergraph Neural Networks. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, Honolulu, 27 January 2019 - 1 February 2019, 3558-3565.
https://doi.org/10.1609/aaai.v33i01.33013558 |
[6] | Yadati, N., Nimishakavi, M., Yadav, P., et al. (2019) Hypergcn: A New Method for Training Graph Convolutional Networks on Hypergraphs. Advances in Neural Information Pro-cessing Systems, 32, 1511-1522.
https://proceedings.neurips.cc/paper_files/paper/2019/hash/1efa39bcaec6f3900149160693694536-Abstract.html |
[7] | Jiang, J., Wei, Y., Feng, Y., et al. (2019) Dynamic Hypergraph Neural Networks. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Macao, 10-16 August 2019, 2635-2641.
https://doi.org/10.24963/ijcai.2019/366 |
[8] | Bandyopadhyay, S., Das, K. and Murty, M.N. (2020) Line Hyper-graph Convolution Network: Applying Graph Convolution for Hypergraphs. arXiv:2002.03392. |
[9] | Bu, J., Tan, S., Chen, C., et al. (2010) Music Recommendation by Unified Hypergraph: Combining Social Media Information and Music Content. Proceedings of the 18th ACM International Conference on Multimedia, Florence, 25-29 October 2010, 391-400. https://doi.org/10.1145/1873951.1874005 |
[10] | Li, L. and Li, T. (2013) News Recommendation via Hypergraph Learning: Encapsulation of User Behavior and News Content. Proceedings of the Sixth ACM International Conference on Web Search and Data Mining, Rome, 4-8 February 2013, 305-314. https://doi.org/10.1145/2433396.2433436 |
[11] | Wang, J., Ding, K., Hong, L., et al. (2020) Next-Item Recommen-dation with Sequential Hypergraphs. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 25-30 July 2020, 1101-1110. https://doi.org/10.1145/3397271.3401133 |
[12] | Xia, X., Yin, H., Yu, J., et al. (2021) Self-Supervised Hypergraph Convolutional Networks for Session-Based Recommendation. Proceedings of the AAAI Conference on Artificial Intelli-gence, 35, 4503-4511.
https://doi.org/10.1609/aaai.v35i5.16578 |
[13] | Wu, F., Souza, A., Zhang, T., et al. (2019) Simplifying Graph Con-volutional Networks. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, 9-15 June 2019, 6861-6871. |
[14] | Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Advances in Neural Information Processing systems, 30, 5998-6008. |
[15] | Sarwar, B., Karypis, G., Konstan, J., et al. (2001) Item-Based Collaborative Filtering Recommendation Algorithms. Proceedings of the 10th International Conference on World Wide Web, Hong Kong, 1-5 May 2001, 285-295.
https://doi.org/10.1145/371920.372071 |
[16] | Rendle, S., Freudenthaler, C. and Schmidt-Thieme, L. (2010) Factor-izing Personalized Markov Chains for Next-Basket Recommendation. Proceedings of the 19th International Conference on World Wide Web, Raleigh, 26-30 April 2010, 811-820. https://doi.org/10.1145/1772690.1772773 |
[17] | Li, J., Ren, P., Chen, Z., et al. (2017) Neural Attentive Session-Based Recommendation. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, Singapore, 6-10 November 2017, 1419-1428.
https://doi.org/10.1145/3132847.3132926 |
[18] | Liu, Q., Zeng, Y., Mokhosi, R., et al. (2018) STAMP: Short-Term Attention/Memory Priority Model for Session-Based Recommendation. Proceedings of the 24th ACM SIGKDD Interna-tional Conference on Knowledge Discovery & Data Mining, London, 20-23 August 2018, 1831-1839. https://doi.org/10.1145/3219819.3219950 |
[19] | Wang, Z., Wei, W., Cong, G., et al. (2020) Global Context En-hanced Graph Neural Networks for Session-Based Recommendation. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 25-30 July 2020, 169-178. https://doi.org/10.1145/3397271.3401142 |
[20] | Qiu, R., Li, J., Huang, Z., et al. (2019) Rethinking the Item Order in Session-Based Recommendation with Graph Neural Networks. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, 3-7 November 2019, 579-588. https://doi.org/10.1145/3357384.3358010 |