Abstract
User features and item features are important information for recommendation systems, and their interaction significantly improves the accuracy of recommendations. Existing work classifies types of interactions as internal and cross interactions. However, it does not take into consideration the different importance of information in cross interactions, nor captures more complex dependencies between features with higher-order interactions. To solve this problem we propose Collaborative Filtering based on Self-Attention Mechanism and Feature Fusion (CF-SAFF). It explicitly uses internal interactions for user and item feature learning, and assigns different weights to cross interactions based on the Self-Attention mechanism to represent the different importance of interaction nodes, thereby performing preference matching on recommendations. At the same time, the fusion operation of internal interaction information and cross interaction information is used to discover high-order feature combination information, which improves the prediction accuracy and generalization ability of the model. The model has conducted extensive experiments on public standard datasets, and the results show that the model has achieved better results than previous mainstream models in all performance indicators.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Beutel, A., et al.: Latent cross: making use of context in recurrent recommender systems. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 46–54 (2018)
Bian, W., et al.: CAN: feature co-action network for click-through rate prediction. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (2022)
Chen, Y., Wu, L., Zaki, M.J.: Toward subgraph guided knowledge graph question generation with graph neural networks. arXiv preprint arXiv:2004.06015 (2020)
Cheng, H.T., et al.: Wide & deep learning for recommender systems. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 7–10 (2016)
Di, W.: LightFIG: simplifying and powering feature interactions via graph for recommendation. PeerJ Comput. Sci. 8, e1019 (2022)
Fu, Y., Liu, Y.: CGSPN: cascading gated self-attention and phrase-attention network for sentence modeling. J. Intell. Inf. Syst. 56, 147–168 (2020). https://doi.org/10.1007/s10844-020-00610-z
Guo, H., Tang, R., Ye, Y., Li, Z., He, X.: DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
He, X., Chua, T.S.: Neural factorization machines for sparse predictive analytics. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 355–364 (2017)
Juan, Y., Zhuang, Y., Chin, W.S., Lin, C.J.: Field-aware factorization machines for CTR prediction. In: Proceedings of the 10th ACM Conference on Recommender Systems, pp. 43–50 (2016)
Koren, Y., Bell, R., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009)
Li, J., Wu, M.: Deep attention factorization machine network for distributed recommendation system. In: 2022 International Conference on Machine Learning, Cloud Computing and Intelligent Mining (MLCCIM), pp. 511–517 (2022)
Li, Z., Cui, Z., Wu, S., Zhang, X., Wang, L.: Fi-GNN: modeling feature interactions via graph neural networks for CTR prediction. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 539–548 (2019)
Liu, B., et al.: AutoFIS: automatic feature interaction selection in factorization models for click-through rate prediction. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2636–2645 (2020)
Qiu, S., Wu, Y., Anwar, S., Li, C.: Investigating attention mechanism in 3D point cloud object detection. In: 2021 International Conference on 3D Vision (3DV), pp. 403–412. IEEE (2021)
Rendle, S.: Factorization machines. In: 2010 IEEE International Conference on Data Mining, pp. 995–1000. IEEE (2010)
Song, W., et al.: AutoInt: automatic feature interaction learning via self-attentive neural networks. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 1161–1170 (2019)
Su, Y., Erfani, S.M., Zhang, R.: MMF: attribute interpretable collaborative filtering. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2019)
Su, Y., Zhang, R., Erfani, S., Xu, Z.: Detecting beneficial feature interactions for recommender systems. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 4357–4365 (2021)
Su, Y., Zhang, R., Erfani, S.M., Gan, J.: Neural graph matching based collaborative filtering. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 849–858 (2021)
Sun, G., Wang, Z., Zhao, J.: Automatic text summarization using deep reinforcement learning and beyond. Inf. Technol. Control 50, 458–469 (2021)
Wang, X., Zhang, R., Sun, Y., Qi, J.: Combating selection biases in recommender systems with a few unbiased ratings. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp. 427–435 (2021)
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2020)
Yin, Y., Huang, C., Sun, J., Huang, F.: Multi-head self-attention recommendation model based on feature interaction enhancement. In: ICC 2022 - IEEE International Conference on Communications, pp. 1740–1745 (2022)
Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W.L., Leskovec, J.: Graph convolutional neural networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 974–983 (2018)
Acknowledgements
This work is supported by “Tianjin Project + Team” Key Training Project under Grant No. XC202022.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kong, W., Wang, X., Xiao, Y. (2023). CF-SAFF: Collaborative Filtering Based on Self-attention Mechanism and Feature Fusion. In: Strauss, C., Amagasa, T., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2023. Lecture Notes in Computer Science, vol 14147. Springer, Cham. https://doi.org/10.1007/978-3-031-39821-6_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-39821-6_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39820-9
Online ISBN: 978-3-031-39821-6
eBook Packages: Computer ScienceComputer Science (R0)