Abstract
Multi-behavior session-based recommendation aims to predict the next item, such as a location-based service (LBS) or a product, to be interacted by a specific behavior type (e.g., buy or click) in a session involving multiple types of behaviors. State-of-the-art methods generally model multi-behavior dependencies in item-level, but ignore the potential of discovering useful patterns of multi-behavior transition through feature-level representation learning. Besides, sequential and non-sequential patterns should be properly fused in session modeling to capture dynamic interests within the session. To this end, this paper proposes a Graph Neural Network based Hybrid Model GNNH, which enables feature-level deeper representations of multi-behavior interaction sequences for session-based recommendation. Specifically, we first construct multi-relational item graph (MRIG) and feature graph (MRFG) based on session sequences. On top of the MRIG and MRFG, our model takes advantage of GNN to capture item and feature representations, such that global item-to-item and feature-to-feature relations are fully preserved. Afterwards, each multi-behavior session is modeled by a seamless fusion of interacted item and feature representations, where self-attention and mean-pooling are used to obtain sequential and non-sequential patterns simultaneously. Experiments on two real datasets show that the GNNH model significantly outperforms the state-of-the-art methods.
Similar content being viewed by others
References
Auer P (2002) Using confidence bounds for exploitation-exploration trade-offs. JMLR, pp 397–422
Chen L, Shang S, Jensen CS, Xu J, Kalnis P, Yao B, Shao L (2020) Top-k term publish/subscribe for geo-textual data streams. VLDB, pp 1101–1128
Chen L, Shang S, Yang C, Li J (2020) Spatial keyword search: a survey. GeoInformatica, pp 85–106
Chen L, Shang S, Zhang Z, Cao X, Jensen CS, Kalnis P (2018) Location-aware top-k term publish/subscribe. In: ICDE, pp 749–760
Chen X, Xu J, Zhou R, Zhao P, Liu C, Fang J, Zhao L (2020) S2r-tree: a pivot-based indexing structure for semantic-aware spatial keyword search. GeoInformatica, pp 3–25
Cheng C, Yang H, King I, Lyu MR (2012) Fused matrix factorization with geographical and social influence in location-based social networks. In: AAAI
Gao C, He X, Gan D, Chen X, Feng F, Li Y, Chua T (2019) Neural multi-task recommendation from multi-behavior data. In: ICDE, pp 1554–1557
Gao R, Li J, Li X, Song C, Chang J, Liu D, Wang C (2018) STSCR: Exploring spatial-temporal sequential influence and social information for location recommendation. Neurocomputing, pp 118–133
Han P, Li Z, Liu Y, Zhao P, Li J, Wang H, Shang S (2020) Contextualized point-of-interest recommendation. In: IJCAI, pp 2484–2490
Han P, Shang S, Sun A, Zhao P, Zheng K, Kalnis P (2019) Auc-mf: point of interest recommendation with auc maximization. In: ICDE, IEEE, pp 1558–1561
Han P, Shang S, Sun A, Zhao P, Zheng K, Zhang X (2021) Point-of-interest recommendation with global and local context. IEEE Transactions on Knowledge and Data Engineering
Han P, Yang P, Zhao P, Shang S, Liu Y, Zhou J, Gao X, Kalnis P (2019) Gcn-mf: disease-gene association identification by graph convolutional networks and matrix factorization. In: SIGKDD, pp 705–713
He X, Zhang H, Kan M, Chua T (2016) Fast matrix factorization for online recommendation with implicit feedback. In: SIGIR, pp 549–558
Hidasi B, Karatzoglou A, Baltrunas L, Tikk D (2016) Session-based recommendations with recurrent neural networks. In: ICLR
Jin B, Gao C, He X, Jin D, Li Y (2020) Multi-behavior recommendation with graph convolutional networks. In: SIGIR, pp 659–668
Kang W, McAuley JJ (2018) Self-attentive sequential recommendation. In: ICDM, pp 197–206
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: ICLR
Kotzias D, Lichman M, Smyth P (2019) Predicting consumption patterns with repeated and novel events. TKDE, pp 371–384
Li J, Ren P, Chen Z, Ren Z, Lian T, Ma J (2017) Neural attentive session-based recommendation. In: CIKM, pp 1419–1428
Li L, Chu W, Langford J, Schapire RE (2010) A contextual-bandit approach to personalized news article recommendation. In: WWW, pp 661–670
Li L, Lu Y, Zhou D (2017) Provable optimal algorithms for generalized linear contextual bandits. coRR
Li Y, Xu J, Zhao P, Fang J, Chen W, Zhao L (2020) Atlrec: an attentional adversarial transfer learning network for cross-domain recommendation. JCST, pp 794–808
Liu A, Wang W, Shang S, Li Q, Zhang X (2018) Efficient task assignment in spatial crowdsourcing with worker and task privacy protection. GeoInformatica, pp 335–362
Liu Q, Zeng Y, Mokhosi R, Zhang H (2018) STAMP: Short-term attention/memory priority model for session-based recommendation. In: SIGKDD, pp 1831–1839
Loni B, Pagano R, Larson MA, Hanjalic A (2016) Bayesian personalized ranking with multi-channel user feedback. In: Recsys, pp 361–364
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Nips, pp 3111–3119
Rendle S, Freudenthaler C, Gantner Z (2009) Schmidt-thieme, L.: BPR: bayesian personalized ranking from implicit feedback. In: UAI, pp 452–461
Rendle S, Freudenthaler C (2010) Schmidt-thieme, L.: Factorizing personalized markov chains for next-basket recommendation. In: WWW, pp 811–820
Sarwar BM, Karypis G, Konstan JA, Riedl J (2001) Item-based collaborative filtering recommendation algorithms. In: WWW, pp 285–295
Shang S, Chen L, Jensen CS, Wen J, Kalnis P (2018) Searching trajectories by regions of interest. In: ICDE, pp 1741–1742
Shang S, Chen L, Wei Z, Jensen CS, Wen J, Kalnis P (2017) Collective travel planning in spatial networks. In: ICDE, pp 59–60
Shang S, Chen L, Wei Z, Jensen CS, Zheng K, Kalnis P (2017) Trajectory similarity join in spatial networks. VLDB, pp 1178–1189
Shang S, Chen L, Wei Z, Jensen CS, Zheng K, Kalnis P (2018) Parallel trajectory similarity joins in spatial networks. VLDB, pp 395–420
Shang S, Chen L, Zheng K, Jensen CS, Wei Z, Kalnis P (2019) Parallel trajectory-to-location join. TKDE, pp 1194–1207
Shang S, Ding R, Zheng K, Jensen CS, Kalnis P, Zhou X (2014) Personalized trajectory matching in spatial networks. VLDB, pp 449–468
Singh AP, Gordon GJ (2008) Relational learning via collective matrix factorization. In: SIGKDD, pp 650–658
Song X, Xu J, Zhou R, Liu C, Zheng K, Zhao P, Falkner N (2020) Collective spatial keyword search on activity trajectories. GeoInformatica, pp 61–84
Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. JMLR, pp 1929–1958
Tan YK, Xu X, Liu Y (2016) Improved recurrent neural networks for session-based recommendations. In: Recsys, pp 17–22
Tang L, Long B, Chen B, Agarwal D (2016) An empirical study on recommendation with multiple types of feedback. In: SIGKDD, pp 283–292
Tuan TX, Phuong TM (2017) 3d convolutional networks for session-based recommendation with content features. In: Recsys, pp 138–146
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: NIPS, pp 5998–6008
Wang S, Cao L, Wang Y (2019) A survey on session-based recommender systems. coRR
Wang S, Hu L, Wang Y, Cao L, Sheng QZ, Orgun MA (2019) Sequential recommender systems: Challenges, progress and prospects. In: IJCAI, pp 6332–6338
Wang W, Zhang W, Liu S, Liu Q, Zhang B, Lin L, Zha H (2020) Beyond clicks: Modeling multi-relational item graph for session-based target behavior prediction. In: WWW, pp 3056–3062
Wu S, Tang Y, Zhu Y, Wang L, Xie X, Tan T (2019) Session-based recommendation with graph neural networks. In: AAAI, pp 346–353
Xu J, Gao Y, Liu C, Zhao L, Ding Z (2015) Efficient route search on hierarchical dynamic road networks. DPD, pp 227–252
Xu J, Zhao J, Zhou R, Liu C, Zhao P, Zhao L (2021) Predicting destinations by a deep learning based approach. TKDE, pp 651–666
Xu S, Zhang R, Cheng W, Xu J (2020) Mtlm: a multi-task learning model for travel time estimation. GeoInformatica
Zhang T, Zhao P, Liu Y, Sheng VS, Xu J, Wang D, Liu G, Zhou X (2019) Feature-level deeper self-attention network for sequential recommendation. In: IJCAI, pp. 4320–4326
Zhang Y, Liu Y, Han P, Miao C, Cui L, Li B, Tang H (2020) Learning personalized itemset mapping for cross-domain recommendation. In: IJCAI, pp 2561–2567
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant Nos. 61872258, 61802273, Major project of natural science research in Universities of Jiangsu Province under grant number 20KJA520005.
Author information
Authors and Affiliations
Corresponding author
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
Yu, B., Zhang, R., Chen, W. et al. Graph neural network based model for multi-behavior session-based recommendation. Geoinformatica 26, 429–447 (2022). https://doi.org/10.1007/s10707-021-00439-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10707-021-00439-w