Abstract
The event that predicts the next item that the people will buy in the next basket is defined as the next basket recommendation task. Though this task has been widely studied, previous works still have the following two challenges: 1) Previous methods usually make predictions via only considering the correlations between items within the basket, while ignoring the similarity relationships between baskets, which may also have the potential capability of improving the basket modeling. 2) Previous studies usually use the Recurrent Neural Network (RNN), especially attention-based RNN and fixed attention mechanisms, to model the relationships between items, which fail to capture the local network structures and their high-order sequential relationships. To overcome the above challenges, in this work, we propose a Hyperedge-based Graph Attention Network for Next Basket Recommendation, namely HGAT-BR, as our solution. To be more specific, to incorporate the similarity relationship between two baskets, we treat baskets as sets of items, and further model them as hyperedges in a hypergraph. Then, the basket representation learning can be converted to the hyperedge embedding task, where a hyperedge-based graph attention network is proposed. To further consider the correlation information among items, we treat items within a basket as nodes in a vanilla graph and learn node representations via another graph neural network. Then, we concatenate these two types of representations to make predictions. Note that, we train the basket and note representation learning simultaneously in an end-to-end manner. We conduct extensive experiments on two real-world datasets, and the experimental results demonstrate the superiority of our proposed method compared with several state-of-the-art next basket recommendation methods.
Similar content being viewed by others
Notes
In our task, a basket is defined as a collection of items purchased by the same user in a very short period of time.
References
Gasparetti F, Sansonetti G, Micarelli A (2021) Community detection in social recommender systems: a survey. Appl Intell 51:3975–3995
Bobadilla J, Ortega F, Hernando A, Gutiérrez A (2013) Recommender systems survey. Knowl-Based Syst 46:109–132
Lü L, Medo M, Yeung C H, Zhang Y-C, Zhang Z-K, Zhou T (2012) Recommender systems. Phys Rep 519(1):1–49
ao F LA C, Pádua F LC, Lacerda A, Machado A C, Dalip D H (2019) Multimodal data fusion framework based on autoencoders for top-n recommender systems. Appl Intell 49:3267– 3282
Nisha C C, Mohan A (2019) A social recommender system using deep architecture and network embedding. Appl Intell 49:1937–1953
Zhao J, Yang S, Huo H, Sun Q, Geng X (2035) Tbtf: an effective time-varying bias tensor factorization algorithm for recommender system
Nedunchezhian P, Mahalingam M (2021) Sybilsort algorithm - a friend request decision tracking recommender system in online social networks. Appl Intell
Mao M, Lu J, Han J, Zhang G (2019) Multiobjective e-commerce recommendations based on hypergraph ranking. Inf Sci 471:269–287
(2014) Strategies for avoiding preference profiling in agent-based e-commerce environments. Appl Intell 40:127–142
Pan Y, Wu D, Luo C, Dolgui A (2019) User activity measurement in rating-based online-to-offline (o2o) service recommendation. Inf Sci 479:180–196
Resnick P, Varian H R (1997) Recommender systems, vol 40. Association for Computing Machinery, New York, pp 56–58
Rendle S, Freudenthaler C, Schmidt-Thieme L (2010) Factorizing personalized markov chains for next-basket recommendation. In: Proceedings of the 19th International Conference on World Wide Web, WWW ’10. Association for Computing Machinery, New York, pp 811–820
Wang P, Guo J, Lan Y, Xu J, Wan S, Cheng X (2015) Learning hierarchical representation model for nextbasket recommendation. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’15. Association for Computing Machinery, New York, pp 403–412
Yu F, Liu Q, Wu S, Wang L, Tan T (2016) A dynamic recurrent model for next basket recommendation. In: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’16. Association for Computing Machinery, New York, pp 729–732
Hu H, He X, Gao J, Zhang Z-L (2020) Modeling personalized item frequency information for next-basket recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, New York, pp 1071–1080
Shani G, Heckerman D, Brafman R I (2005) An mdp-based recommender system. J Mach Learn Res 6:1265–1295
Le D-T, Lauw H W, Fang Y (2019) Correlation-sensitive next-basket recommendation. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI-19. International Joint Conferences on Artificial Intelligence Organization, pp 2808–2814
Che B, Zhao P, Fang J, Zhao L, Sheng V S, Cui Z (2019) Inter-basket and intra-basket adaptive attention network for next basket recommendation. IEEE Access 7:80644–80650
Mantha A, Arora Y, Gupta S, Kanumala P, Liu Z, Guo S, Achan K (2020) A large-scale deep architecture for personalized grocery basket recommendations. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 3807–3811
Liu Z, Li X, Fan Z, Guo S, Achan K, Yu P S (2020) Basket recommendation with multi-intent translation graph neural network. In: 2020 IEEE International Conference on Big Data (Big Data), pp 728–737
Leng Y, Yu L, Xiong J, Xu G (2020) Recurrent convolution basket map for diversity next-basket recommendation, pp 638–653
Wang P, Zhang Y, Niu S, Guo J (2019) Modeling temporal dynamics of users’ purchase behaviors for next basket prediction. J Comput Sci Technol 34(6):1230. https://doi.org/10.1007/s11390-019-1972-2
Guidotti R, Rossetti G, Pappalardo L, Giannotti F, Pedreschi D (2017) Market basket prediction using user-centric temporal annotated recurring sequences. In: 2017 IEEE International Conference on Data Mining (ICDM), pp 895–900
Guidotti R, Rossetti G, Pappalardo L, Giannotti F, Pedreschi D (2019) Personalized market basket prediction with temporal annotated recurring sequences. IEEE Trans Knowl Data Eng 31(11):2151–2163
Zhu J, Ma X, Yue C, Wang C (2019) Interest-forgetting markov model for next-basket recommendation. In: Cheng X, Jing W, Song X, Lu Z (eds) Data Science. Springer Singapore, Singapore, pp 20–31
Bai T, Nie J-Y, Zhao W X, Zhu Y, Du P, Wen J-R (2018) An attribute-aware neural attentive model for next basket recommendation. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR ’18. Association for Computing Machinery, New York, pp 1201–1204
Hu H, He X (2019) Sets2sets: Learning from sequential sets with neural networks. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 1491–1499
Gori M, Monfardini G, Scarselli F (2005) A new model for learning in graph domains. In: Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, vol 2, pp 729–734
Hamilton W L, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17. Curran Associates Inc., Red Hook, pp 1025–1035
Guo Y, Ling Y, Chen H (2020) A time-aware graph neural network for session-based recommendation. IEEE Access 8:167371–167382
Liu Z, Wan M, Guo S, Achan K, Yu P S (2020) Basconv: Aggregating heterogeneous interactions for basket recommendation with graph convolutional neural network. In: Proceedings of the 2020 SIAM International Conference on Data Mining (SDM), pp 64–72
Zhou D, Huang J, Schölkopf B (2007) Learning with hypergraphs: Clustering, classification, and embedding. In: Schölkopf B, Platt J, Hoffman T (eds) Advances in Neural Information Processing Systems, vol 19. MIT Press
Bu J, Tan S, Chen C, Wang C, Wu H, Zhang L, He X (2010) Music recommendation by unified hypergraph: Combining social media information and music content. In: Proceedings of the 18th ACM International Conference on Multimedia, MM ’10. Association for Computing Machinery, New York, pp 391–400
Zheng X, Luo Y, Sun L, Ding X, Zhang J (2018) A novel social network hybrid recommender system based on hypergraph topologic structure. World Wide Web 21(4):985–1013. https://doi.org/10.1007/s11280-017-0494-5
Zhu Y, Guan Z, Tan S, Liu H, Cai D, He X (2016) Heterogeneous hypergraph embedding for document recommendation. Neurocomputing 216. https://doi.org/10.1016/j.neucom.2016.07.030
Karantaidis G, Sarridis I, Kotropoulos C (2021) Adaptive hypergraph learning with multi-stage optimizations for image and tag recommendation. Signal Process Image Commun 97:116367. https://doi.org/10.1016/j.image.2021.116367
Wu S, Tang Y, Zhu Y, Wang L, Xie X, Tan T (July 2019) Session-based recommendation with graph neural networks. In: Hentenryck P V, Zhou Z-H (eds) Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, vol 33. AAAI Press, pp 346–353
Qiu R, Li J, Huang Z, YIn H (2019) Rethinking the item order in session-based recommendation with graph neural networks. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM ’19. Association for Computing Machinery, New York, pp 579–588
Xia X, Yin H, Yu J, Wang Q, Cui L, Zhang X (2021) Self-supervised hypergraph convolutional networks for session-based recommendation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 35, pp 4503–4511
Wang S, Hu L, Wang Y, Sheng Q Z, Orgun M, Cao L (20197) Modeling multi-purpose sessions for next-item recommendations via mixture-channel purpose routing networks. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI-19. International Joint Conferences on Artificial Intelligence Organization, pp 3771–3777
Zhang M, Wu S, Gao M, Jiang X, Xu K, Wang L (2021) Personalized graph neural networks with attention mechanism for session-aware recommendation. IEEE Trans Knowl Data Eng:1–1
He X, Deng K, Wang X, Li Y, Zhang Y, Wang M (2020) Lightgcn: Simplifying and powering graph convolution network for recommendation. Association for Computing Machinery, New York, pp 639–648
Yu L, Sun L, Du B, Liu C, Xiong H, Lv W (2020) Predicting temporal sets with deep neural networks. Association for Computing Machinery, New York, pp 1083–1091
Velickovic P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2018) Graph attention networks. In: International Conference on Learning Representations
Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network
Nair V, Hinton G E (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML’10. Omnipress, Madison, pp 807–814
Ying H, Zhuang F, Zhang F, Liu Y, Xu G, Xie X, Xiong H, Wu J (2018) Sequential recommender system based on hierarchical attention networks. In: Proceedings of the twenty-seventh international joint conference on artificial intelligence, IJCAI-18. International Joint Conferences on Artificial Intelligence Organization, pp 3926–3932
He X, Chen T, Kan M-Y, Chen X (2015) Trirank: Review-aware explainable recommendation by modeling aspects. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, CIKM ’15. Association for Computing Machinery, New York, pp 1661–1670
Qin Y, Wang P, Li C (2021) The world is binary: Contrastive learning for denoising next basket recommendation. Association for Computing Machinery, New York, pp 859– 868
Holzinger A, Malle B, Saranti A, Pfeifer B (2021) Towards multi-modal causability with graph neural networks enabling information fusion for explainable ai. Information Fusion 71:28–37. https://doi.org/10.1016/j.inffus.2021.01.008
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 61602282, No. 11504153) and China Postdoctoral Science Foundation (No. 2016M602181).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Song, T., Guo, F., Jiang, H. et al. HGAT-BR: Hyperedge-based graph attention network for basket recommendation. Appl Intell 53, 1435–1451 (2023). https://doi.org/10.1007/s10489-022-03575-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03575-4