ABSTRACT
Deep learning on graphs and especially graph convolutional networks (GCNs) have shown superior performance in collaborative filtering. Most GCNs have a message-passing architecture that enables nodes aggregate information from neighbours continuously through multiple layers. This also leads to a common issue called over-smoothing: as the number of layers increases, the node embeddings become similar and the performance of tasks such as link prediction degrades severely. In this work, we propose motif-based graph attention network for web service recommendation (MGSR) that alleviates the over-smoothing issue by incorporate network motifs in layer propagation. Extensive experiments show that our model outperforms state-of-the-art approaches.
- Austin R. Benson, David F. Gleich, and Jure Leskovec. 2016. Higher-order organization of complex networks. Science 353, 6295 (July 2016), 163–166. https://doi.org/10.1126/science.aad9029Google ScholarCross Ref
- Xuexin Chen, Ruichu Cai, Yuan Fang, Min Wu, Zijian Li, and Zhifeng Hao. 2022. Motif Graph Neural Network. arXiv:2112.14900 [cs] (Jan. 2022). http://arxiv.org/abs/2112.14900Google Scholar
- Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249–256. https://proceedings.mlr.press/v9/glorot10a.html ISSN: 1938-7228.Google Scholar
- Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, YongDong Zhang, and Meng Wang. 2020. 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(SIGIR ’20). Association for Computing Machinery, New York, NY, USA, 639–648. https://doi.org/10.1145/3397271.3401063Google ScholarDigital Library
- Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural Collaborative Filtering. arXiv:1708.05031 [cs] (Aug. 2017). http://arxiv.org/abs/1708.05031 arXiv:1708.05031.Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations. http://arxiv.org/abs/1609.02907Google Scholar
- Tingting Liang, Liang Chen, Jian Wu, Hai Dong, and Athman Bouguettaya. 2016. Meta-Path Based Service Recommendation in Heterogeneous Information Networks. In Service-Oriented Computing(Lecture Notes in Computer Science), Quan Z. Sheng, Eleni Stroulia, Samir Tata, and Sami Bhiri (Eds.). Springer International Publishing, Cham, 371–386. https://doi.org/10.1007/978-3-319-46295-0_23Google ScholarDigital Library
- Yutao Ma, Xiao Geng, and Jian Wang. 2021. A Deep Neural Network With Multiplex Interactions for Cold-Start Service Recommendation. IEEE Transactions on Engineering Management 68, 1 (Feb. 2021), 105–119. https://doi.org/10.1109/TEM.2019.2961376 Conference Name: IEEE Transactions on Engineering Management.Google ScholarCross Ref
- R. Milo, S. Shen-Orr, S. Itzkovitz, N. Kashtan, D. Chklovskii, and U. Alon. 2002. Network Motifs: Simple Building Blocks of Complex Networks. Science 298, 5594 (Oct. 2002), 824–827. https://doi.org/10.1126/science.298.5594.824Google ScholarCross Ref
- F. Monti, K. Otness, and M. M. Bronstein. 2018. MOTIFNET: A MOTIF-BASED GRAPH CONVOLUTIONAL NETWORK FOR DIRECTED GRAPHS. In 2018 IEEE Data Science Workshop (DSW). 225–228. https://doi.org/10.1109/DSW.2018.8439897Google ScholarCross Ref
- Mo Nguyen, Jian Yu, Tung Nguyen, and Yanbo Han. 2021. Attentional matrix factorization with context and co-invocation for service recommendation. Expert Systems with Applications 186 (Dec. 2021), 115698. https://doi.org/10.1016/j.eswa.2021.115698Google ScholarDigital Library
- Mo Nguyen, Jian Yu, Tung Nguyen, and Sira Yongchareon. 2022. High-order autoencoder with data augmentation for collaborative filtering. Knowledge-Based Systems 240 (March 2022), 107773. https://doi.org/10.1016/j.knosys.2021.107773Google ScholarDigital Library
- Jinghua Piao, Guozhen Zhang, Fengli Xu, Zhilong Chen, and Yong Li. 2021. Predicting Customer Value with Social Relationships via Motif-based Graph Attention Networks. In Proceedings of the Web Conference 2021(WWW ’21). Association for Computing Machinery, New York, NY, USA, 3146–3157. https://doi.org/10.1145/3442381.3449849Google ScholarDigital Library
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations. https://openreview.net/forum?id=rJXMpikCZGoogle Scholar
- Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019. Neural Graph Collaborative Filtering. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (July 2019), 165–174. https://doi.org/10.1145/3331184.3331267 arXiv:1905.08108.Google ScholarDigital Library
- Fenfang Xie, Liang Chen, Dongding Lin, Zibin Zheng, and Xiaola Lin. 2019. Personalized Service Recommendation With Mashup Group Preference in Heterogeneous Information Network. IEEE Access 7(2019), 16155–16167. https://doi.org/10.1109/ACCESS.2019.2894822 Conference Name: IEEE Access.Google ScholarCross Ref
- Fang Xie, Jian Wang, Ruibin Xiong, Neng Zhang, Yutao Ma, and Keqing He. 2019. An integrated service recommendation approach for service-based system development. Expert Systems with Applications 123 (June 2019), 178–194. https://doi.org/10.1016/j.eswa.2019.01.025Google ScholarDigital Library
- Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, and Stefanie Jegelka. 2018. Representation Learning on Graphs with Jumping Knowledge Networks. arXiv:1806.03536 [cs, stat] (June 2018). http://arxiv.org/abs/1806.03536 arXiv:1806.03536.Google Scholar
- Lina Yao, Xianzhi Wang, Quan Z. Sheng, Boualem Benatallah, and Chaoran Huang. 2021. Mashup Recommendation by Regularizing Matrix Factorization with API Co-Invocations. IEEE Transactions on Services Computing 14, 2 (March 2021), 502–515. https://doi.org/10.1109/TSC.2018.2803171 Conference Name: IEEE Transactions on Services Computing.Google ScholarCross Ref
- Wenhui Yu, Zixin Zhang, and Zheng Qin. 2022. Low-Pass Graph Convolutional Network for Recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
Index Terms
- Motif-based Graph Attention Network for Web Service Recommendation
Recommendations
Motif-based graph attentional neural network for web service recommendation
AbstractDeep Neural Networks (DNN) based collaborative filtering has been successful in recommending services by effectively generalizing graph-structured data. However, most existing approaches focus on first-order interactions. Although recent ...
Graphical abstractDisplay Omitted
Highlights- We report a Motif-based Graph Attention Network for service recommendation (MGSR).
- The model aggregates high-order information of motif-based neighbors.
- The model identifies all the seven up-to-four-node motifs in bipartite graphs.
Hybrid graph convolutional networks with multi-head attention for location recommendation
AbstractRecommending yet-unvisited points of interest (POIs) which may be of interest to users is one of the fundamental applications in location-based social networks. It mainly replies on the understanding of users, POIs, and their interactions. ...
Bundle Recommendation with Graph Convolutional Networks
SIGIR '20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information RetrievalBundle recommendation aims to recommend a bundle of items for a user to consume as a whole. Existing solutions integrate user-item interaction modeling into bundle recommendation by sharing model parameters or learning in a multi-task manner, which ...
Comments