Advertisement

Interaction Graph Neural Network for News Recommendation

  • Yongye Qian
  • Pengpeng ZhaoEmail author
  • Zhixu Li
  • Junhua Fang
  • Lei Zhao
  • Victor S. Sheng
  • Zhiming Cui
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11881)

Abstract

Personalized news recommendation has become a highly challenging problem in recent years. Traditional ID-based methods such as collaborative filtering are not suitable for news recommendation due to the extremely rapid update of candidate news. Various content-based methods have been proposed for news recommendation and achieved the state-of-the-art performance. Recently, knowledge-aware news recommendation further improves the performance through discover latent knowledge level connections among the news. However, we argue that the above content-based methods do not fully utilize the collaborative information latent in user-item interactions into user and news representation learning process. In this paper, we propose a new news recommendation model, Interaction Graph Neural Network (IGNN), which integrates a user-item interactions graph and a knowledge graph into the news recommendation model. Specifically, IGNN obtains the representation of users and items with two graphs. One is the knowledge graph, and another is the user-item interaction graph. It learns the content-based feature from knowledge-level and semantic-level with convolutional neural networks and fuses the high-order collaborative signals extracted from the user-item interaction graph into user and news representation learning process with a graph neural network. Extensive experiments are conducted on the two real-world news data sets, and experimental results show that IGNN significantly outperforms the state-of-the-art approaches for news recommendation.

Keywords

News recommendation Graph Neural Network Knowledge graph 

Notes

Acknowledgements

This research was partially supported by NSFC (No. 61876117, 61876217, 61872258, 61728205), Open Program of Key Lab of IIP of CAS (No. IIP2019-1) and PAPD.

References

  1. 1.
    Chong, W., Blei, D.M.: Collaborative topic modeling for recommending scientific articles. In: 17th SIGKDD, San Diego, CA, USA, pp. 448–456. ACM (2011)Google Scholar
  2. 2.
    Tomas, M., Ilya, S., Kai, C., et al.: Distributed representations of words and phrases and their compositionality. In: 27th NIPS, Lake Tahoe, Nevada, United States, pp. 3111–3119 (2013)Google Scholar
  3. 3.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)zbMATHGoogle Scholar
  4. 4.
    Hongwei, W., Fuzheng, Z., Xing, X., et al.: DKN: deep knowledge-aware network for news recommendation. In: WWW 2018, Lyon, France, pp. 1835–1844. ACM (2018)Google Scholar
  5. 5.
    Xiao, Y., Xiang, R., Yizhou, S., et al.: Personalized entity recommendation: a heterogeneous information network approach. In: 7th WSDM, pp. 283–292. ACM, New York, NY, USA (2014)Google Scholar
  6. 6.
    Grad-Gyenge, L., Filzmoser, P., Werthner, H.: Recommendations on a knowledge graph. In: 1st International Workshop on Machine Learning Methods for Recommender Systems, pp. 13–20 (2015)Google Scholar
  7. 7.
    Fuzheng, Z., Nicholas, J., Defu, L., et al.: Collaborative knowledge base embedding for recommender systems. In: 22nd SIGKDD, San Francisco, California, USA, pp. 353–362. ACM (2016)Google Scholar
  8. 8.
    Xiyu, W., Qimai, C., Hai, L.: Collaborative filtering recommendation algorithm based on representation learning of knowledge graph. Comput. Eng. 2(44), 226–232 (2018)Google Scholar
  9. 9.
    van den Berg, R., Kipf, T.N., Welling, M.: Graph convolutional matrix completion. CoRR (2017)Google Scholar
  10. 10.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th ICLR, Toulon, France. OpenReview.net (2017)Google Scholar
  11. 11.
    Rex, Y., Ruining, H., Kaifeng, C., et al.: Graph convolutional neural networks for web-scale recommender systems. In: 24th SIGKDD, London, UK, pp. 974–983. ACM (2018)Google Scholar
  12. 12.
    Lei, Z., Chun-Ta, L., Fei, J., et al.: Spectral collaborative filtering. In: 12th Conference on Recommender Systems, Vancouver, BC, Canada, pp. 311–319. ACM (2018)Google Scholar
  13. 13.
    Antoine, B., Nicolas, U., Alberto, G., et al.: Translating embeddings for modeling multi-relational data. In: 27th NIPS, Lake Tahoe, Nevada, United States, pp. 2787–2795 (2013)Google Scholar
  14. 14.
    Petar, V., Guillem, C., Arantxa, C., et al.: Graph attention networks. In: 6th ICLR, Vancouver, BC, Canada (2018)Google Scholar
  15. 15.
    Steffen, R., Christoph, F., Zeno, G., et al.: BPR: Bayesian personalized ranking from implicit feedback. In: 25th UAI, Montreal, QC, Canada, pp. 452–461. AUAI Press (2018)Google Scholar
  16. 16.
    Jon Atle, G., Lemei, Z., Peng, L., et al.: The Adressa dataset for news recommendation. In: WI 2017, Leipzig, Germany, pp. 1042–1048. ACM (2017)Google Scholar
  17. 17.
    Xiangnan, H., Lizi, L., Hanwang, Z., et al.: Neural collaborative filtering. In: WWW 2017, Perth, Australia, pp. 173–182. ACM (2017)Google Scholar
  18. 18.
    Jheng-Hong, Y., Chih-Ming, C., Chuan-Ju, W., et al.: HOP-rec: high-order proximity for implicit recommendation. In: 12th Conference on Recommender Systems, Vancouver, BC, Canada, pp. 140–144. ACM (2018)Google Scholar
  19. 19.
    Steffen, R.: Factorization machines with libFM. ACM TIST 3(3), 57:1–57:22 (2012)MathSciNetGoogle Scholar
  20. 20.
    Heng-Tze, C., Levent, K., Jeremiah, H., et al.: Wide & deep learning for recommender systems. In: 1st Workshop on Deep Learning for Recommender Systems, Boston, MA, USA, pp. 7–10. ACM (2016)Google Scholar
  21. 21.
    Xiang, W., Xiangnan, H., Liqiang, N., et al.: Item silk road: recommending items from information domains to social users. In: 40th SIGIR, Shinjuku, Tokyo, Japan, pp. 185–194. ACM (2017)Google Scholar
  22. 22.
    Jeong-Woo, S., A-Yeong, K., Seong-Bae, P.: A location-based news article recommendation with explicit localized semantic analysis. In: 36th SIGIR, Dublin, Ireland, pp. 293–302. ACM (2013)Google Scholar
  23. 23.
    Po-Sen, H., Xiaodong, H., Jianfeng, G.: Learning deep structured semantic models for web search using clickthrough data. In: 22nd CIKM, San Francisco, California, USA, pp. 2333–2338. ACM (2013)Google Scholar
  24. 24.
    Kevin, J., Hui, J.: Content based news recommendation via shortest entity distance over knowledge graphs. In: WWW 2019, San Francisco, USA, pp. 690–699. ACM (2019)Google Scholar
  25. 25.
    Chengfeng, X., Pengpeng, Z., Yanchi, L., et al.: Graph contextualized self-attention network for session-based recommendation. In: IJCAI 2019, Macao, China, pp. 3940–3946 (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yongye Qian
    • 1
  • Pengpeng Zhao
    • 1
    • 2
    Email author
  • Zhixu Li
    • 1
  • Junhua Fang
    • 1
  • Lei Zhao
    • 1
  • Victor S. Sheng
    • 3
  • Zhiming Cui
    • 4
  1. 1.Institute of AI, School of Computer Science and TechnologySoochow UniversitySuzhouChina
  2. 2.Key Lab of IIP of CASInstitute of Computing TechnologyBeijingChina
  3. 3.The University of Central ArkansasConwayUSA
  4. 4.School of Electronic and Information EngineeringSuzhou University of Science and TechnologySuzhouChina

Personalised recommendations