Abstract
Personalized news recommendations can alleviate the information overload problem. To enable personalized recommendation, one critical step is to learn a comprehensive user representation to model her/his interests. Many existing works learn user representations from the historical clicked news articles, which reflect their existing interests. However, these approaches ignore users’ potential interests and pay less attention to news that may interest the users in the future. To address this problem, we propose a novel Graph neural news Recommendation model with user Existing and Potential interest modeling, named GREP. Different from existing works, GREP introduces three modules to jointly model users’ existing and potential interests: (1) Existing Interest Encoding module mines user historical clicked news and applies the multi-head self-attention mechanism to capture the relatedness among the news; (2) Potential Interest Encoding module leverages the graph neural network to explore the user potential interests on the knowledge graph; and (3) Bi-directional Interaction module dynamically builds a news-entity bipartite graph to further enrich two interest representations. Finally, GREP combines the existing and potential interest representations to represent the user and leverages a prediction layer to estimate the clicking probability of the candidate news. Experiments on two real-world large-scale datasets demonstrate the state-of-the-art performance of GREP.
- [1] . 2019. Neural news recommendation with long- and short-term user representations. In Proceedings of the ACL (1). Association for Computational Linguistics, 336–345.Google ScholarCross Ref
- [2] . 2016. Layer normalization. CoRR abs/1607.06450.Google Scholar
- [3] . 2015. Content driven user profiling for comment-worthy recommendations of news and blog articles. In Proceedings of the RecSys. ACM, 195–202.Google ScholarDigital Library
- [4] . 2016. Wide & deep learning for recommender systems. In Proceedings of the DLRS@RecSys. ACM, 7–10.Google ScholarDigital Library
- [5] . 2012. From chatter to headlines: Harnessing the real-time web for personalized news recommendation. In Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 153–162.Google ScholarDigital Library
- [6] . 2020. Graph enhanced representation learning for news recommendation. In Proceedings of the WWW. ACM / IW3C2, 2863–2869.Google ScholarDigital Library
- [7] . 2017. The adressa dataset for news recommendation. In Proceedings of the International Conference on Web Intelligence. 1042–1048.Google ScholarDigital Library
- [8] . 2017. DeepFM: A factorization-machine based neural network for CTR prediction. In Proceedings of the IJCAI. ijcai.org, 1725–1731.Google ScholarCross Ref
- [9] . 2014. Who likes it more?: Mining worth-recommending items from long tails by modeling relative preference. In Proceedings of the 7th ACM International Conference on Web Search and Data Mining. , , , and (Eds.), ACM, 253–262.
DOI: Google ScholarDigital Library - [10] . 2020. Graph neural news recommendation with long-term and short-term interest modeling. Information Processing and Management 57, 2 (2020), 102142.Google ScholarDigital Library
- [11] . 2020. Graph neural news recommendation with unsupervised preference disentanglement. In Proceedings of the ACL. Association for Computational Linguistics, 4255–4264.Google ScholarCross Ref
- [12] . 2010. Ontology-based news recommendation. In Proceedings of the 2010 EDBT/ICDT Workshops. 1–6.Google ScholarDigital Library
- [13] . 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the ICLR (Poster). OpenReview.net.Google Scholar
- [14] . 2010. A contextual-bandit approach to personalized news article recommendation. In Proceedings of the 19th International Conference on World Wide Web. 661–670.Google ScholarDigital Library
- [15] . 2018. Deeper insights into graph convolutional networks for semi-supervised learning. In Proceedings of the AAAI. AAAI Press, 3538–3545.Google ScholarCross Ref
- [16] . 2018. Towards better representation learning for personalized news recommendation: A multi-channel deep fusion approach. In Proceedings of the IJCAI. ijcai.org, 3805–3811.Google ScholarCross Ref
- [17] . 2021. A survey on reinforcement learning for recommender systems. CoRR abs/2109.10665.Google Scholar
- [18] . 2020. KRED: Knowledge-aware document representation for news recommendations. In Proceedings of the RecSys. ACM, 200–209.Google ScholarDigital Library
- [19] . 2020. KRED: Knowledge-aware document representation for news recommendations. In Proceedings of the RecSys 2020: 14th ACM Conference on Recommender Systems, Virtual Event, Brazil, September 22-26, 2020, , , , , , , and (Eds.), ACM, 200–209.
DOI: Google ScholarDigital Library - [20] . 2017. Embedding-based news recommendation for millions of users. In Proceedings of the KDD. ACM, 1933–1942.Google ScholarDigital Library
- [21] . 2014. Glove: Global vectors for word representation. In Proceedings of the EMNLP. ACL, 1532–1543.Google ScholarCross Ref
- [22] . 2021. HieRec: Hierarchical user interest modeling for personalized news recommendation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, , , , and (Eds.), Association for Computational Linguistics, 5446–5456.
DOI: Google ScholarCross Ref - [23] . 2019. Question difficulty prediction for multiple choice problems in medical exams. In Proceedings of the CIKM. ACM, 139–148.Google ScholarDigital Library
- [24] . 2020. Automatic distractor generation for multiple choice questions in standard tests. In Proceedings of the COLING. International Committee on Computational Linguistics, 2096–2106.Google ScholarCross Ref
- [25] . 2021. U-BERT: Pre-training user representations for improved recommendation. In Proceedings of the AAAI. AAAI Press, 4320–4327.Google Scholar
- [26] . 2012. Factorization machines with libFM. ACM Transactions on Intelligent Systems and Technology 3, 3 (2012), 57:1–57:22.Google ScholarDigital Library
- [27] . 2020. Masked label prediction: Unified massage passing model for semi-supervised classification. CoRR abs/2009.03509.Google Scholar
- [28] . 2011. Collaborative topic modeling for recommending scientific articles. In Proceedings of the KDD. ACM, 448–456.Google ScholarDigital Library
- [29] . 2020. Fine-grained interest matching for neural news recommendation. In Proceedings of the ACL. Association for Computational Linguistics, 836–845.Google ScholarCross Ref
- [30] . 2018. DKN: Deep knowledge-aware network for news recommendation. In Proceedings of the WWW. ACM, 1835–1844.Google ScholarDigital Library
- [31] . 2019. Neural news recommendation with attentive multi-view learning. In Proceedings of the IJCAI. ijcai.org, 3863–3869.Google ScholarCross Ref
- [32] . 2019. NPA: Neural news recommendation with personalized attention. In Proceedings of the KDD. ACM, 2576–2584.Google ScholarDigital Library
- [33] . 2019. Neural news recommendation with multi-head self-attention. In Proceedings of the EMNLP/IJCNLP (1). Association for Computational Linguistics, 6388–6393.Google ScholarCross Ref
- [34] . 2020. MIND: A large-scale dataset for news recommendation. In Proceedings of the 58th Annual Meeting of the Association for Computational, Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault (Eds.). Association for Computational Linguistics, 3597–3606.
DOI: Google ScholarCross Ref - [35] . 2021. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems 32, 1 (2021), 4–24.Google ScholarCross Ref
- [36] . 2019. Dynamic news recommendation with hierarchical attention network. In Proceedings of the ICDM. IEEE, 1456–1461.Google ScholarCross Ref
- [37] . 2021. Combining explicit entity graph with implicit text information for news recommendation. In Proceedings of the Companion Proceedings of the Web Conference 2021. 412–416.Google ScholarDigital Library
- [38] . 2018. DRN: A deep reinforcement learning framework for news recommendation. In Proceedings of the 2018 World Wide Web Conference. 167–176.Google ScholarDigital Library
- [39] . 2018. A generic top-n recommendation framework for trading-off accuracy, novelty, and coverage. In 34th IEEE International Conference on Data Engineering, ICDE 2018, Paris, France, April 16-19, 2018. IEEE Computer Society, 149–160.
DOI: Google ScholarCross Ref
Index Terms
- Graph Neural News Recommendation with User Existing and Potential Interest Modeling
Recommendations
User-Oriented Interest Representation on Knowledge Graph for Long-Tail Recommendation
Advanced Data Mining and ApplicationsAbstractGraph neural networks have demonstrated impressive performance in the field of recommender systems. However, existing graph neural network recommendation approaches are proficient in capturing users’ mainstream interests and recommending popular ...
SGAT: Scene Graph Attention Network for Video Recommendation
IVSP '23: Proceedings of the 2023 5th International Conference on Image, Video and Signal ProcessingAs a widely studied topic in recommender systems, collaborative filtering (CF) methods help users discover potential items of interest by assuming that behavioral similar users would have similar preferences on items. A recent trend is to develop models ...
MGR: Metric Learning with Graph Neural Networks for Multi-behavior Recommendation
Knowledge Science, Engineering and ManagementAbstractTraditional recommendation methods often suffer from the problems of sparsity and cold start. Therefore, researchers usually leverage Knowledge Graph as a kind of side information to alleviate these issues and improve the accuracy of ...
Comments