RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems

    CIKM, pp. 417-426, 2018.

    Cited by: 95|Bibtex|Views107|Links
    EI
    Keywords:
    knowledge graph embeddingcollaborative filteringSigned Heterogeneous Information Network EmbeddingCollaborative Knowledge base EmbeddingDeep Knowledge-aware NetworkMore(10+)
    Wei bo:
    We propose RippleNet, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems

    Abstract:

    To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based a...More

    Code:

    Data:

    0
    Introduction
    • The explosive growth of online content and services has provided overwhelming choices for users, such as news, movies, music, restaurants, and books.
    • Recommender systems (RS) intend to address the information explosion by finding a small set of items for.
    • Guo is the corresponding author.
    • Cast Away Back to the Future genre include starred.
    • Adventure include style genre star.
    • Tom Hanks starred collaborate direct directed.
    • The Green Mile Movies the user have watched Robert Zemeckis.
    Highlights
    • The explosive growth of online content and services has provided overwhelming choices for users, such as news, movies, music, restaurants, and books
    • We find that RippleNet provides a new perspective of explainability for the recommended results in terms of the knowledge graph
    • Researchers have proposed using memory networks in other tasks such as sentiment classification [13, 26] and recommendation [5, 8]. Note that these works usually focus on entry-level or sentence-level memories, while our work addresses entity-level connections in the knowledge graph, which is more fine-grained and intuitive when performing multi-hop iterations
    • The results of all methods in click-through rate prediction and top-K recommendation are presented in Table 3 and Figures 5, 6, 7, respectively
    • We propose RippleNet, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems
    • The results demonstrate the significant superiority of RippleNet over strong baselines
    Methods
    • The authors evaluate RippleNet on three real-world scenarios: movie, book, and news recommendations 5.
    • 4.1 Datasets.
    • The authors utilize the following three datasets in the experiments for movie, book, and news recommendation: MovieLens-1M Book-Crossing Bing-News # users # items.
    • MovieLens-1M d = 16, H = 2, λ1 = 10−7, λ2 = 0.01, η = 0.02 Book-Crossing d = 4, H = 3, λ1 = 10−5, λ2 = 0.01, η = 0.001
    Results
    • The results of all methods in CTR prediction and top-K recommendation are presented in Table 3 and Figures 5, 6, 7, respectively.
    • CKE performs comparably poorly than other baselines, which is probably because the authors only have structural knowledge available, without visual and textual input.
    • SHINE performs better in movie and book recommendation than news.
    • This is because the 1-hop triples for news are too complicated when taken as profile input.
    • Precision@K Ripple CKE SHINE DKN PER LibFM Wide&Deep
    Conclusion
    • A user’s interest in film "Back to the Future" might be explained by the path "user −w−−a−t−c−h−e−→d For r est Gump directed by −−−−−−−−−−−→ Rober t Zemeckis −−d−i−r−e−c−t→s Back to the.
    • RippleNet overcomes the limitations of existing embeddingbased and path-based KG-aware recommendation methods by introducing preference propagation, which automatically propagates users’ potential preferences and explores their hierarchical interests in the KG.
    • The authors plan to (1) further investigate the methods of characterizing entity-relation interactions; (2) design non-uniform samplers during preference propagation to better explore users’ potential interests and improve the performance
    Summary
    • Introduction:

      The explosive growth of online content and services has provided overwhelming choices for users, such as news, movies, music, restaurants, and books.
    • Recommender systems (RS) intend to address the information explosion by finding a small set of items for.
    • Guo is the corresponding author.
    • Cast Away Back to the Future genre include starred.
    • Adventure include style genre star.
    • Tom Hanks starred collaborate direct directed.
    • The Green Mile Movies the user have watched Robert Zemeckis.
    • Methods:

      The authors evaluate RippleNet on three real-world scenarios: movie, book, and news recommendations 5.
    • 4.1 Datasets.
    • The authors utilize the following three datasets in the experiments for movie, book, and news recommendation: MovieLens-1M Book-Crossing Bing-News # users # items.
    • MovieLens-1M d = 16, H = 2, λ1 = 10−7, λ2 = 0.01, η = 0.02 Book-Crossing d = 4, H = 3, λ1 = 10−5, λ2 = 0.01, η = 0.001
    • Results:

      The results of all methods in CTR prediction and top-K recommendation are presented in Table 3 and Figures 5, 6, 7, respectively.
    • CKE performs comparably poorly than other baselines, which is probably because the authors only have structural knowledge available, without visual and textual input.
    • SHINE performs better in movie and book recommendation than news.
    • This is because the 1-hop triples for news are too complicated when taken as profile input.
    • Precision@K Ripple CKE SHINE DKN PER LibFM Wide&Deep
    • Conclusion:

      A user’s interest in film "Back to the Future" might be explained by the path "user −w−−a−t−c−h−e−→d For r est Gump directed by −−−−−−−−−−−→ Rober t Zemeckis −−d−i−r−e−c−t→s Back to the.
    • RippleNet overcomes the limitations of existing embeddingbased and path-based KG-aware recommendation methods by introducing preference propagation, which automatically propagates users’ potential preferences and explores their hierarchical interests in the KG.
    • The authors plan to (1) further investigate the methods of characterizing entity-relation interactions; (2) design non-uniform samplers during preference propagation to better explore users’ potential interests and improve the performance
    Tables
    • Table1: Basic statistics of the three datasets
    • Table2: Hyper-parameter settings for the three datasets
    • Table3: The results of AUC and Accuracy in CTR prediction
    • Table4: The results of AUC w.r.t. different sizes of a user’s ripple set
    • Table5: The results of AUC w.r.t. different hop numbers
    Download tables as Excel
    Funding
    • This work was partially sponsored by the National Basic Research 973 Program of China under Grant 2015CB352403
    Study subjects and analysis
    datasets: 3
    We first introduce the datasets, baselines, and experiment setup, then present the experiment results. We will also give a case study of visualization and discuss the choice of hyper-parameters in this section. 4.1 Datasets

    We utilize the following three datasets in our experiments for movie, book, and news recommendation: MovieLens-1M Book-Crossing Bing-News # users # items

    # interactions 753,772 # 1-hop triples

    # 2-hop triples 178,049

    # 3-hop triples 318,266

    # 4-hop triples 923,718

    MovieLens-1M d = 16, H = 2, λ1 = 10−7, λ2 = 0.01, η = 0.02 Book-Crossing d = 4, H = 3, λ1 = 10−5, λ2 = 0.01, η = 0.001
    .

    datasets: 3
    4.1 Datasets. We utilize the following three datasets in our experiments for movie, book, and news recommendation: 5Experiment code is provided at https://github.com/hwwang55/RippleNet. MovieLens-1M Book-Crossing Bing-News

    datasets: 3
    The constructing process is similar for Bing-News except that: (1) we use entity linking tools to extract entities in news titles; (2) we do not impose restrictions on the names of relations since the entities in news titles are not within one particular domain. The basic statistics of the three datasets are presented in Table 1. 6 https://grouplens.org/datasets/movielens/1m/ 7 http://www2.informatik.uni- freiburg.de/~cziegler/BX/

    item pairs: 1000000
    We conduct an empirical study to investigate the correlation between the average number of common neighbors of an item pair in the KG and whether they have common rater(s) in RS. For each dataset, we first randomly sample one million item pairs, then count the average number of k-hop neighbors that the two items share in the KG under the following two circumstances: (1) the two items have at least one common rater in RS; (2) the two items have no common rater in RS. The results are presented in Figures 4a, 4b, 4c, respectively, which clearly show that if two items have common rater(s) in RS, they likely share more common k-hop neighbors in the KG for fixed k

    datasets: 3
    We vary the size of a user’s ripple set in each hop to further investigate the robustness of RippleNet. The results of AUC on the three datasets are presented in Table 4, Table 4: The results of AUC w.r.t. different sizes of a user’s ripple set. Size of ripple set MovieLens-1M Book-Crossing

    Reference
    • Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).
      Findings
    • Konstantin Bauman, Bing Liu, and Alexander Tuzhilin. 2017. Aspect based recommendations: Recommending items with the most valuable aspects based on user reviews. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 717–725.
      Google ScholarLocate open access versionFindings
    • Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 201Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems. 2787–2795.
      Google ScholarLocate open access versionFindings
    • Jingyuan Chen, Hanwang Zhang, Xiangnan He, Liqiang Nie, Wei Liu, and Tat-Seng Chua. 2017. Attentive collaborative filtering: Multimedia recommendation with item-and component-level attention. In SIGIR. ACM, 335–344.
      Google ScholarLocate open access versionFindings
    • Xu Chen, Hongteng Xu, Yongfeng Zhang, Jiaxi Tang, Yixin Cao, Zheng Qin, and Hongyuan Zha. 2018. Sequential Recommendation with User Memory Networks. In Proceedings of the 11th ACM International Conference on Web Search and Data Mining.
      Google ScholarLocate open access versionFindings
    • Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson, Greg Corrado, Wei Chai, Mustafa Ispir, et al. 201Wide & deep learning for recommender systems. In Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. ACM, 7–10.
      Google ScholarLocate open access versionFindings
    • Li Dong, Furu Wei, Ming Zhou, and Ke Xu. 2015. Question Answering over Freebase with Multi-Column Convolutional Neural Networks. In ACL. 260–269.
      Google ScholarLocate open access versionFindings
    • Haoran Huang, Qi Zhang, and Xuanjing Huang. 2017. Mention Recommendation for Twitter with End-to-end Memory Network. In IJCAI.
      Google ScholarFindings
    • Mohsen Jamali and Martin Ester. 2010. A matrix factorization technique with trust propagation for recommendation in social networks. In Proceedings of the 4th ACM conference on Recommender systems. ACM, 135–142.
      Google ScholarLocate open access versionFindings
    • Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, and Jun Zhao. 2015. Knowledge graph embedding via dynamic mapping matrix. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Vol. 1. 687–696.
      Google ScholarLocate open access versionFindings
    • Yehuda Koren. 2008. Factorization meets the neighborhood: a multifaceted collaborative filtering model. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 426–434.
      Google ScholarLocate open access versionFindings
    • Yehuda Koren, Robert Bell, and Chris Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009).
      Google ScholarLocate open access versionFindings
    • Zheng Li, Yu Zhang, Ying Wei, Yuxiang Wu, and Qiang Yang. 2017. End-to-End Adversarial Memory Network for Cross-domain Sentiment Classification. In Proceedings of the 26th International Joint Conference on Artificial Intelligence.
      Google ScholarLocate open access versionFindings
    • Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, and Xuan Zhu. 2015. Learning Entity and Relation Embeddings for Knowledge Graph Completion. In AAAI. 2181–2187.
      Google ScholarFindings
    • Hanxiao Liu, Yuexin Wu, and Yiming Yang. 2017. Analogical Inference for MultiRelational Embeddings. In Proceedings of the 34th International Conference on Machine Learning. 2168–2178.
      Google ScholarLocate open access versionFindings
    • Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013.
      Google ScholarFindings
    • Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. arXiv preprint arXiv:1606.03126 (2016).
      Findings
    • Volodymyr Mnih, Nicolas Heess, Alex Graves, et al. 2014. Recurrent models of visual attention. In Advances in Neural Information Processing Systems. 2204–2212.
      Google ScholarLocate open access versionFindings
    • Maximilian Nickel, Lorenzo Rosasco, Tomaso A Poggio, et al. 2016. Holographic Embeddings of Knowledge Graphs. In AAAI. 1955–1961.
      Google ScholarFindings
    • Steffen Rendle. 2012. Factorization machines with libfm. ACM Transactions on Intelligent Systems and Technology (TIST) 3, 3 (2012), 57.
      Google ScholarLocate open access versionFindings
    • Tim Rocktäschel, Sameer Singh, and Sebastian Riedel. 2015. Injecting logical background knowledge into embeddings for relation extraction. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1119–1129.
      Google ScholarLocate open access versionFindings
    • Sungyong Seo, Jing Huang, Hao Yang, and Yan Liu. 2017. Interpretable convolutional neural networks with dual local and global attention for review rating prediction. In Proceedings of the Eleventh ACM Conference on Recommender Systems. ACM, 297–305.
      Google ScholarLocate open access versionFindings
    • Amit Sharma and Dan Cosley. 2013. Do social explanations work?: studying and modeling the effects of social explanations in recommender systems. In Proceedings of the 22nd international conference on World Wide Web. ACM, 1133– 1144.
      Google ScholarLocate open access versionFindings
    • Sainbayar Sukhbaatar, Jason Weston, Rob Fergus, et al. 2015. End-to-end memory networks. In Advances in Neural Information Processing Systems. 2440–2448.
      Google ScholarLocate open access versionFindings
    • Yu Sun, Nicholas Jing Yuan, Xing Xie, Kieran McDonald, and Rui Zhang. 2017. Collaborative Intent Prediction with Real-Time Contextual Data. ACM Transactions on Information Systems 35, 4 (2017), 30.
      Google ScholarLocate open access versionFindings
    • Kai Sheng Tai, Richard Socher, and Christopher D Manning. 2015. Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Vol. 1. 1556–1566.
      Google ScholarLocate open access versionFindings
    • Nava Tintarev and Judith Masthoff. 2007. A survey of explanations in recommender systems. In IEEE 23rd International Conference on Data Engineering Workshop. IEEE, 801–810.
      Google ScholarLocate open access versionFindings
    • Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, and Guillaume Bouchard. 2016. Complex embeddings for simple link prediction. In International Conference on Machine Learning. 2071–2080.
      Google ScholarLocate open access versionFindings
    • Jesse Vig, Shilad Sen, and John Riedl. 2009. Tagsplanations: explaining recommendations using tags. In Proceedings of the 14th international conference on Intelligent user interfaces. ACM, 47–56.
      Google ScholarLocate open access versionFindings
    • Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang, Xing Xie, and Minyi Guo. 2018. Graphgan: Graph representation learning with generative adversarial nets. In AAAI. 2508–2515.
      Google ScholarFindings
    • Hongwei Wang, Jia Wang, Miao Zhao, Jiannong Cao, and Minyi Guo. 2017. Joint Topic-Semantic-aware Social Recommendation for Online Voting. In Proceedings of the 2017 ACM Conference on Information and Knowledge Management. ACM, 347–356.
      Google ScholarLocate open access versionFindings
    • Hongwei Wang, Fuzheng Zhang, Min Hou, Xing Xie, Minyi Guo, and Qi Liu. 2018. Shine: Signed heterogeneous information network embedding for sentiment link prediction. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining. ACM, 592–600.
      Google ScholarLocate open access versionFindings
    • Hongwei Wang, Fuzheng Zhang, Xing Xie, and Minyi Guo. 2018. DKN: Deep Knowledge-Aware Network for News Recommendation. In Proceedings of the 2018 World Wide Web Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 1835–1844.
      Google ScholarLocate open access versionFindings
    • Jin Wang, Zhongyuan Wang, Dawei Zhang, and Jun Yan. 2017. Combining Knowledge with Deep Convolutional Neural Networks for Short Text Classification. In IJCAI.
      Google ScholarFindings
    • Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. 2017. Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering 29, 12 (2017), 2724–2743.
      Google ScholarLocate open access versionFindings
    • Xuejian Wang, Lantao Yu, Kan Ren, Guanyu Tao, Weinan Zhang, Yong Yu, and Jun Wang. 2017. Dynamic attention deep model for article recommendation by learning human editors’ demonstration. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2051– 2059.
      Google ScholarLocate open access versionFindings
    • Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. 2014. Knowledge Graph Embedding by Translating on Hyperplanes. In AAAI. 1112–1119.
      Google ScholarFindings
    • Jason Weston, Sumit Chopra, and Antoine Bordes. 2014. Memory networks. arXiv preprint arXiv:1410.3916 (2014).
      Findings
    • Ruobing Xie, Zhiyuan Liu, and Maosong Sun. 2016. Representation Learning of Knowledge Graphs with Hierarchical Types.. In IJCAI. 2965–2971.
      Google ScholarFindings
    • Chang Xu, Yalong Bai, Jiang Bian, Bin Gao, Gang Wang, Xiaoguang Liu, and Tie-Yan Liu. 2014. Rc-net: A general framework for incorporating knowledge into word representations. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. ACM, 1219–1228.
      Google ScholarLocate open access versionFindings
    • Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In Proceedings of the 3rd International Conference on Learning Representations.
      Google ScholarLocate open access versionFindings
    • Xiao Yu, Xiang Ren, Yizhou Sun, Quanquan Gu, Bradley Sturt, Urvashi Khandelwal, Brandon Norick, and Jiawei Han. 2014. Personalized entity recommendation: A heterogeneous information network approach. In Proceedings of the 7th ACM International Conference on Web Search and Data Mining. 283–292.
      Google ScholarLocate open access versionFindings
    • Fuzheng Zhang, Nicholas Jing Yuan, Defu Lian, Xing Xie, and Wei-Ying Ma.
      Google ScholarFindings
    • 2016. Collaborative knowledge base embedding for recommender systems. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 353–362.
      Google ScholarLocate open access versionFindings
    • [44] Yongfeng Zhang, Guokun Lai, Min Zhang, Yi Zhang, Yiqun Liu, and Shaoping Ma. 2014. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval. ACM, 83–92.
      Google ScholarLocate open access versionFindings
    • [45] Huan Zhao, Quanming Yao, Jianda Li, Yangqiu Song, and Dik Lun Lee. 2017. Metagraph based recommendation fusion over heterogeneous information networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 635–644.
      Google ScholarLocate open access versionFindings
    • [46] Huaping Zhong, Jianwen Zhang, Zhen Wang, Hai Wan, and Zheng Chen. 2015. Aligning knowledge and text embeddings by entity descriptions. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 267–272.
      Google ScholarLocate open access versionFindings
    • [47] Guorui Zhou, Chengru Song, Xiaoqiang Zhu, Xiao Ma, Yanghui Yan, Xingya Dai, Han Zhu, Junqi Jin, Han Li, and Kun Gai. 2017. Deep interest network for click-through rate prediction. arXiv preprint arXiv:1706.06978 (2017).
      Findings
    Your rating :
    0

     

    Tags
    Comments