{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T11:56:23Z","timestamp":1772452583414,"version":"3.50.1"},"reference-count":50,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T00:00:00Z","timestamp":1668038400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Web Intelligence"],"published-print":{"date-parts":[[2023,6,20]]},"abstract":"<jats:p>Graph Neural Networks (GNNs) have been successfully used to learn user and item representations for Collaborative Filtering (CF) based recommendations (GNN-CF). Besides the main recommendation task in a GNN-CF model, contrastive learning is taken as an auxiliary task to learn better representations. Both the main task and the auxiliary task face the noise problem and the distilling hard negative problem. However, existing GNN-CF models only focus on one of them and ignore the other. Aiming to solve the two problems in a unified framework, we propose a Multi-Mixing strategy for GNN-based CF (M2GCF). In the main task, M2GCF perturbs embeddings of users, items and negative items with sample-noise by a mixing strategy. In the auxiliary task, M2GCF utilizes a contrastive learning mechanism with a two-step mixing strategy to construct hard negatives. Extensive experiments on three benchmark datasets demonstrate the effectiveness of the proposed model. Further experimental analysis shows that M2GCF is robust against interaction noise and is accurate for long-tail item recommendations.<\/jats:p>","DOI":"10.3233\/web-220054","type":"journal-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T11:40:59Z","timestamp":1668166859000},"page":"149-166","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["M2GCF: A multi-mixing strategy for graph neural network based collaborative filtering"],"prefix":"10.1177","volume":"21","author":[{"given":"Jianan","family":"Xu","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, China"},{"name":"Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing, China"}]},{"given":"Jiajin","family":"Huang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, China"},{"name":"Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing, China"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Beijing University of Technology, China"},{"name":"Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing, China"}]},{"given":"Ning","family":"Zhong","sequence":"additional","affiliation":[{"name":"Maebashi Institute of Technology, Maebashi, Japan"}]}],"member":"179","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"key":"ref001","doi-asserted-by":"publisher","DOI":"10.3233\/WEB-190415"},{"key":"ref002","unstructured":"J.\u00a0Chen, H.\u00a0Dong, X.\u00a0Wang, F.\u00a0Feng, M.\u00a0Wang and X.\u00a0He, Bias and debias in recommender system: A survey and future directions, 2021, arXiv preprint arXiv:2010.03240."},{"key":"ref003","doi-asserted-by":"crossref","unstructured":"X.\u00a0Chen and K.\u00a0He, Exploring simple Siamese representation learning, in: Proceedings of the 2021 International Conference on Computer Vision and Pattern Recognition, 2021, pp.\u00a015750\u201315758.","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref004","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Deng, L.\u00a0Huang, C.\u00a0Wang, J.\u00a0Lai and P.S.\u00a0Yu, DeepCF: A unified framework of representation learning and matching function learning in recommender system, in: Proceedings of the 33th International Conference on Artificial Intelligence, 2019, pp.\u00a061\u201368.","DOI":"10.1609\/aaai.v33i01.330161"},{"key":"ref005","unstructured":"W.\u00a0Feng, J.\u00a0Zhang, Y.\u00a0Dong, Y.\u00a0Han, H.\u00a0Luan, Q.\u00a0Xu, Q.\u00a0Yang, E.\u00a0Kharlamov and J.\u00a0Tang, Graph random neural networks for semi-supervised learning on graphs, in: Proceedings of the 2020 International Conference on Neural Information Processing Systems, 2020, pp.\u00a022092\u201322103."},{"key":"ref006","unstructured":"C.\u00a0Gao, Y.\u00a0Zheng, N.\u00a0Li, Y.\u00a0Li, Y.\u00a0Qin, J.\u00a0Piao, Y.\u00a0Quan, J.\u00a0Chang, D.\u00a0Jin, X.\u00a0He and Y.\u00a0Li, Graph neural networks for recommender systems: Challenges, methods, and directions, 2021, arXiv preprint arXiv:2109.12843."},{"key":"ref007","doi-asserted-by":"publisher","DOI":"10.3233\/WEB-210448"},{"key":"ref008","unstructured":"S.\u00a0Gidaris, P.\u00a0Singh and N.\u00a0Komodakis, Unsupervised representation learning by predicting image rotations, in: Proceedings of the 6th International Conference on Learning Representations."},{"key":"ref009","unstructured":"X.\u00a0Glorot and Y.\u00a0Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, 2010, pp.\u00a0249\u2013256."},{"key":"ref010","unstructured":"J.\u00a0Grill, F.\u00a0Strub, F.\u00a0Altch\u00e9, C.\u00a0Tallec, P.H.\u00a0Richemond, E.\u00a0Buchatskaya, C.\u00a0Doersch, B.\u00c1.\u00a0Pires, Z.\u00a0Guo, M.G.\u00a0Azar, B.\u00a0Piot, K.\u00a0Kavukcuoglu, R.\u00a0Munos and M.\u00a0Valko, Bootstrap your own latent: A new approach to self-supervised learning, in: Proceedings of the 2020 International Conference on Neural Information Processing Systems, 2020, pp.\u00a021271\u201321284."},{"key":"ref011","unstructured":"W.L.\u00a0Hamilton, Z.\u00a0Ying and J.\u00a0Leskovec, Inductive representation learning on large graphs, in: Proceedings of the 2017 International Conference on Neural Information Processing Systems, 2017, pp.\u00a01024\u20131034."},{"key":"ref012","doi-asserted-by":"crossref","unstructured":"K.\u00a0He, H.\u00a0Fan, Y.\u00a0Wu, S.\u00a0Xie and R.B.\u00a0Girshick, Momentum contrast for unsupervised visual representation learning, in: Proceedings of the 2020 International Conference on Computer Vision and Pattern Recognition, 2020, pp.\u00a09726\u20139735.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref013","doi-asserted-by":"crossref","unstructured":"X.\u00a0He, K.\u00a0Deng, X.\u00a0Wang, Y.\u00a0Li, Y.\u00a0Zhang and M.\u00a0Wang, LightGCN: Simplifying and powering graph convolution network for recommendation, in: Proceedings of the 43th International Conference on Research and Development in Information Retrieval, 2020, pp.\u00a0639\u2013648.","DOI":"10.1145\/3397271.3401063"},{"key":"ref014","doi-asserted-by":"crossref","unstructured":"X.\u00a0He, Z.\u00a0He, X.\u00a0Du and T.\u00a0Chua, Adversarial personalized ranking for recommendation, in: Proceedings of the 41th International Conference on Research Development in Information Retrieval, 2018, pp.\u00a0355\u2013364.","DOI":"10.1145\/3209978.3209981"},{"key":"ref015","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref016","unstructured":"R.D.\u00a0Hjelm, A.\u00a0Fedorov, S.\u00a0Lavoie-Marchildon, K.\u00a0Grewal, P.\u00a0Bachman, A.\u00a0Trischler and Y.\u00a0Bengio, Learning deep representations by mutual information estimation and maximization, in: Proceedings of the 7th International Conference on Learning Representations, 2019."},{"key":"ref017","doi-asserted-by":"crossref","unstructured":"T.\u00a0Huang, Y.\u00a0Dong, M.\u00a0Ding, Z.\u00a0Yang, W.\u00a0Feng, X.\u00a0Wang and J.\u00a0Tang, MixGCF: An improved training method for graph neural network-based recommender systems, in: Proceedings of the 27th International Conference on Knowledge Discovery and Data Mining, 2021, pp.\u00a0665\u2013674.","DOI":"10.1145\/3447548.3467408"},{"key":"ref018","unstructured":"Y.\u00a0Kalantidis, M.B.\u00a0Sariyildiz, N.\u00a0Pion, P.\u00a0Weinzaepfel and D.\u00a0Larlus, Hard negative mixing for contrastive learning, in: Proceedings of the 2020 International Conference on Neural Information Processing Systems, 2020, pp.\u00a021798\u201321809."},{"key":"ref019","unstructured":"D.P.\u00a0Kingma and J.\u00a0Ba, Adam: A method for stochastic optimization, in: Proceedings of the 3th International Conference on Learning Representations, 2015."},{"key":"ref020","unstructured":"T.N.\u00a0Kipf and M.\u00a0Welling, Semi-supervised classification with graph convolutional networks, in: Proceedings of the 5th International Conference on Learning Representations, 2017."},{"key":"ref021","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"ref022","doi-asserted-by":"crossref","unstructured":"W.\u00a0Krichene and S.\u00a0Rendle, On sampled metrics for item recommendation, in: Proceedings of the 26th International Conference on Knowledge Discovery and Data Mining, 2020, pp.\u00a01748\u20131757.","DOI":"10.1145\/3394486.3403226"},{"key":"ref023","unstructured":"K.\u00a0Lee, Y.\u00a0Zhu, K.\u00a0Sohn, C.\u00a0Li, J.\u00a0Shin and H.\u00a0Lee, i-Mix: A domain-agnostic strategy for contrastive representation learning, in: Proceedings of the 9th International Conference on Learning Representations, 2021."},{"key":"ref024","unstructured":"Z.\u00a0Liu, Y.\u00a0Ma, Y.\u00a0Ouyang and Z.\u00a0Xiong, Contrastive learning for recommender system, 2021, arXiv preprint arXiv:2101.01317."},{"key":"ref025","doi-asserted-by":"crossref","unstructured":"K.\u00a0Mao, J.\u00a0Zhu, J.\u00a0Wang, Q.\u00a0Dai, Z.\u00a0Dong, X.\u00a0Xiao and X.\u00a0He, SimpleX: A simple and strong baseline for collaborative filtering, in: Proceedings of the 30th International Conference on Information and Knowledge Management, 2021, pp.\u00a01243\u20131252.","DOI":"10.1145\/3459637.3482297"},{"key":"ref026","doi-asserted-by":"crossref","unstructured":"J.J.\u00a0McAuley, C.\u00a0Targett, Q.\u00a0Shi and A.\u00a0van den Hengel, Image-based recommendations on styles and substitutes, in: Proceedings of the 38th International Conference on Research and Development in Information Retrieval, 2015, pp.\u00a043\u201352.","DOI":"10.1145\/2766462.2767755"},{"key":"ref027","unstructured":"T.\u00a0Mikolov, I.\u00a0Sutskever, K.\u00a0Chen, G.S.\u00a0Corrado and J.\u00a0Dean, Distributed representations of words and phrases and their compositionality, in: Proceedings of the 2013 International Conference on Neural Information Processing Systems, 2013, pp.\u00a03111\u20133119."},{"key":"ref028","unstructured":"S.\u00a0Rendle, C.\u00a0Freudenthaler, Z.\u00a0Gantner and L.\u00a0Schmidt-Thieme, BPR: Bayesian personalized ranking from implicit feedback, in: Proceedings of the 25th International Conference on Uncertainty in Artificial Intelligence, 2009, pp.\u00a0452\u2013461."},{"key":"ref029","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Shen, Z.\u00a0Liu, Z.\u00a0Liu, M.\u00a0Savvides and T.\u00a0Darrell, Un-Mix: Rethinking image mixture for unsupervised visual representation learning, in: Proceedings of the 36th International Conference on Artificial Intelligence, 2022.","DOI":"10.1609\/aaai.v36i2.20119"},{"key":"ref030","doi-asserted-by":"crossref","unstructured":"X.\u00a0Tang, H.\u00a0Yao, Y.\u00a0Sun, Y.\u00a0Wang, J.\u00a0Tang, C.C.\u00a0Aggarwal, P.\u00a0Mitra and S.\u00a0Wang, Investigating and mitigating degree-related biases in graph convoltuional networks, in: Proceedings of the 29th International Conference on Information and Knowledge Management, 2020, pp.\u00a01435\u20131444.","DOI":"10.1145\/3340531.3411872"},{"key":"ref031","unstructured":"R.\u00a0van den Berg, T.N.\u00a0Kipf and M.\u00a0Welling, Graph convolutional matrix completion, in: Proceedings of the 23th International Conference on Knowledge Discovery and Data Mining, 2018."},{"key":"ref032","unstructured":"V.\u00a0Verma, T.\u00a0Luong, K.\u00a0Kawaguchi, H.\u00a0Pham and Q.V.\u00a0Le, Towards domain-agnostic contrastive learning, in: Proceedings of the 38th International Conference on Machine Learning, 2021, pp.\u00a010530\u201310541."},{"key":"ref033","doi-asserted-by":"crossref","unstructured":"D.\u00a0Walawalkar, Z.\u00a0Shen, Z.\u00a0Liu and M.\u00a0Savvides, Attentive Cutmix: An enhanced data augmentation approach for deep learning based image classification, in: Proceedings of the 2020 International Conference on Acoustics, Speech and Signal Processing, 2020, pp.\u00a03642\u20133646.","DOI":"10.1109\/ICASSP40776.2020.9053994"},{"key":"ref034","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783273"},{"key":"ref035","doi-asserted-by":"crossref","unstructured":"J.\u00a0Wang, L.\u00a0Yu, W.\u00a0Zhang, Y.\u00a0Gong, Y.\u00a0Xu, B.\u00a0Wang, P.\u00a0Zhang and D.\u00a0Zhang, IRGAN: A minimax game for unifying generative and discriminative information retrieval models, in: Proceedings of the 40th International Conference on Research and Development in Information Retrieval, 2017, pp.\u00a0515\u2013524.","DOI":"10.1145\/3077136.3080786"},{"key":"ref036","doi-asserted-by":"crossref","unstructured":"S.\u00a0Wang, L.\u00a0Hu, Y.\u00a0Wang, X.\u00a0He, Q.Z.\u00a0Sheng, M.A.\u00a0Orgun, L.\u00a0Cao, F.\u00a0Ricci and P.S.\u00a0Yu, Graph learning based recommender systems: A review, in: Proceedings of the 30th International Joint Conference on Artificial Intelligence, 2021, pp.\u00a04644\u20134652.","DOI":"10.24963\/ijcai.2021\/630"},{"key":"ref037","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441800"},{"key":"ref038","doi-asserted-by":"crossref","unstructured":"X.\u00a0Wang, X.\u00a0He, M.\u00a0Wang, F.\u00a0Feng and T.\u00a0Chua, Neural graph collaborative filtering, in: Proceedings of the 42th International Conference on Research and Development in Information Retrieval, 2019, pp.\u00a0165\u2013174.","DOI":"10.1145\/3331184.3331267"},{"key":"ref039","doi-asserted-by":"crossref","unstructured":"J.\u00a0Wu, X.\u00a0Wang, F.\u00a0Feng, X.\u00a0He, L.\u00a0Chen, J.\u00a0Lian and X.\u00a0Xie, Self-supervised graph learning for recommendation, in: Proceedings of the 44th International Conference on Research and Development in Information Retrieval, 2021, pp.\u00a0726\u2013735.","DOI":"10.1145\/3404835.3462862"},{"key":"ref040","unstructured":"X.\u00a0Xie, F.\u00a0Sun, Z.\u00a0Liu, J.\u00a0Gao, B.\u00a0Ding and B.\u00a0Cui, Contrastive pre-training for sequential recommendation, 2021, arXiv preprint arXiv:2010.14395."},{"key":"ref041","doi-asserted-by":"crossref","unstructured":"H.\u00a0Xue, X.\u00a0Dai, J.\u00a0Zhang, S.\u00a0Huang and J.\u00a0Chen, Deep matrix factorization models for recommender systems, in: Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017, pp.\u00a03203\u20133209.","DOI":"10.24963\/ijcai.2017\/447"},{"key":"ref042","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Yang, M.\u00a0Ding, C.\u00a0Zhou, H.\u00a0Yang, J.\u00a0Zhou and J.\u00a0Tang, Understanding negative sampling in graph representation learning, in: Proceedings of the 26th International Conference on Knowledge Discovery and Data Mining, 2020, pp.\u00a01666\u20131676.","DOI":"10.1145\/3394486.3403218"},{"key":"ref043","doi-asserted-by":"crossref","unstructured":"R.\u00a0Ying, R.\u00a0He, K.\u00a0Chen, P.\u00a0Eksombatchai, W.L.\u00a0Hamilton and J.\u00a0Leskovec, Graph convolutional neural networks for web-scale recommender systems, in: Proceedings of the 24th International Conference on Knowledge Discovery Data Mining, 2018, pp.\u00a0974\u2013983.","DOI":"10.1145\/3219819.3219890"},{"key":"ref044","unstructured":"Y.\u00a0You, T.\u00a0Chen, Y.\u00a0Sui, T.\u00a0Chen, Z.\u00a0Wang and Y.\u00a0Shen, Graph contrastive learning with augmentations, in: Proceedings of the 2020 International Conference on Neural Information Processing Systems, 2020, pp.\u00a05812\u20135823."},{"key":"ref045","doi-asserted-by":"crossref","unstructured":"S.\u00a0Yun, D.\u00a0Han, S.\u00a0Chun, S.J.\u00a0Oh, Y.\u00a0Yoo and J.\u00a0Choe, CutMix: Regularization strategy to train strong classifiers with localizable features, in: Proceedings of the 2019 International Conference on Computer Vision, 2019, pp.\u00a06022\u20136031.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref046","unstructured":"H.\u00a0Zhang, M.\u00a0Ciss\u00e9, Y.N.\u00a0Dauphin and D.\u00a0Lopez-Paz, mixup: Beyond empirical risk minimization, in: Proceedings of the 6th International Conference on Learning Representations, 2018."},{"key":"ref047","unstructured":"L.\u00a0Zhang, Z.\u00a0Deng, K.\u00a0Kawaguchi, A.\u00a0Ghorbani and J.\u00a0Zou, How does mixup help with robustness and generalization? in: Proceedings of the 9th International Conference on Learning Representations, 2021."},{"key":"ref048","doi-asserted-by":"crossref","unstructured":"W.\u00a0Zhang, T.\u00a0Chen, J.\u00a0Wang and Y.\u00a0Yu, Optimizing top-n collaborative filtering via dynamic negative item sampling, in: Proceedings of the 36th International Conference on Research and Development in Information Retrieval, 2013, pp.\u00a0785\u2013788.","DOI":"10.1145\/2484028.2484126"},{"key":"ref049","doi-asserted-by":"crossref","unstructured":"K.\u00a0Zhou, H.\u00a0Wang, W.X.\u00a0Zhao, Y.\u00a0Zhu, S.\u00a0Wang, F.\u00a0Zhang, Z.\u00a0Wang and J.\u00a0Wen, S3-Rec: Self-supervised learning for sequential recommendation with mutual information maximization, in: Proceedings of the 29th International Conference on Information and Knowledge Management, 2020, pp.\u00a01893\u20131902.","DOI":"10.1145\/3340531.3411954"},{"key":"ref050","unstructured":"X.\u00a0Zhou, A.\u00a0Sun, Y.\u00a0Liu, J.\u00a0Zhang and C.\u00a0Miao, SelfCF: A simple framework for self-supervised collaborative filtering, 2021, arXiv preprint arXiv:2010.14395."}],"container-title":["Web Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/WEB-220054","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/WEB-220054","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/WEB-220054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T10:59:48Z","timestamp":1772449188000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/WEB-220054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,10]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,6,20]]}},"alternative-id":["10.3233\/WEB-220054"],"URL":"https:\/\/doi.org\/10.3233\/web-220054","relation":{},"ISSN":["2405-6456","2405-6464"],"issn-type":[{"value":"2405-6456","type":"print"},{"value":"2405-6464","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,10]]}}}