Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

KRAN: Knowledge Refining Attention Network for Recommendation

KRAN: Knowledge Refining Attention Network for Recommendation Recommender algorithms combining knowledge graph and graph convolutional network are becoming more and more popular recently. Specifically, attributes describing the items to be recommended are often used as additional information. These attributes along with items are highly interconnected, intrinsically forming a Knowledge Graph (KG). These algorithms use KGs as an auxiliary data source to alleviate the negative impact of data sparsity. However, these graph convolutional network based algorithms do not distinguish the importance of different neighbors of entities in the KG, and according to Pareto’s principle, the important neighbors only account for a small proportion. These traditional algorithms can not fully mine the useful information in the KG. To fully release the power of KGs for building recommender systems, we propose in this article KRAN, a Knowledge Refining Attention Network, which can subtly capture the characteristics of the KG and thus boost recommendation performance. We first introduce a traditional attention mechanism into the KG processing, making the knowledge extraction more targeted, and then propose a refining mechanism to improve the traditional attention mechanism to extract the knowledge in the KG more effectively. More precisely, KRAN is designed to use our proposed knowledge-refining attention mechanism to aggregate and obtain the representations of the entities (both attributes and items) in the KG. Our knowledge-refining attention mechanism first measures the relevance between an entity and it’s neighbors in the KG by attention coefficients, and then further refines the attention coefficients using a “richer-get-richer” principle, in order to focus on highly relevant neighbors while eliminating less relevant neighbors for noise reduction. In addition, for the item cold start problem, we propose KRAN-CD, a variant of KRAN, which further incorporates pre-trained KG embeddings to handle cold start items. Experiments show that KRAN and KRAN-CD consistently outperform state-of-the-art baselines across different settings. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Knowledge Discovery from Data (TKDD) Association for Computing Machinery

KRAN: Knowledge Refining Attention Network for Recommendation

Download PDF
20 pages

Loading next page...
 
/lp/association-for-computing-machinery/kran-knowledge-refining-attention-network-for-recommendation-zNlQKDrXfC

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Association for Computing Machinery
Copyright
Copyright © 2021 Association for Computing Machinery.
ISSN
1556-4681
eISSN
1556-472X
DOI
10.1145/3470783
Publisher site
See Article on Publisher Site

Abstract

Recommender algorithms combining knowledge graph and graph convolutional network are becoming more and more popular recently. Specifically, attributes describing the items to be recommended are often used as additional information. These attributes along with items are highly interconnected, intrinsically forming a Knowledge Graph (KG). These algorithms use KGs as an auxiliary data source to alleviate the negative impact of data sparsity. However, these graph convolutional network based algorithms do not distinguish the importance of different neighbors of entities in the KG, and according to Pareto’s principle, the important neighbors only account for a small proportion. These traditional algorithms can not fully mine the useful information in the KG. To fully release the power of KGs for building recommender systems, we propose in this article KRAN, a Knowledge Refining Attention Network, which can subtly capture the characteristics of the KG and thus boost recommendation performance. We first introduce a traditional attention mechanism into the KG processing, making the knowledge extraction more targeted, and then propose a refining mechanism to improve the traditional attention mechanism to extract the knowledge in the KG more effectively. More precisely, KRAN is designed to use our proposed knowledge-refining attention mechanism to aggregate and obtain the representations of the entities (both attributes and items) in the KG. Our knowledge-refining attention mechanism first measures the relevance between an entity and it’s neighbors in the KG by attention coefficients, and then further refines the attention coefficients using a “richer-get-richer” principle, in order to focus on highly relevant neighbors while eliminating less relevant neighbors for noise reduction. In addition, for the item cold start problem, we propose KRAN-CD, a variant of KRAN, which further incorporates pre-trained KG embeddings to handle cold start items. Experiments show that KRAN and KRAN-CD consistently outperform state-of-the-art baselines across different settings.

Journal

ACM Transactions on Knowledge Discovery from Data (TKDD) – Association for Computing Machinery

Published: Sep 4, 2021

Keywords: Knowledge graph

References

  • Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions
    Adomavicius, Gediminas; Tuzhilin, Alexander
  • Exploring synergies between content-based filtering and spreading activation techniques in knowledge-based recommender systems
    Blancofernandez, Yolanda; Lopeznores, Martin; Gilsolla, Alberto; Ramoscabrer, Manuel; Pazosarias, Jose J.
  • A novel collaborative filtering model based on combination of correlation method with matrix completion technique
    Bojnordi, Ehsan; Moradi, Parham
  • Hybrid recommender systems: Survey and experiments
    Burke, Robin
  • Content-based recommendation in social tagging systems
    Cantador, Ivan; Bellogin, Alejandro; Vallet, David
  • Cluster-GCN: An efficient algorithm for training deep and large graph convolutional networks
    Chiang, Weilin; Liu, Xuanqing; Si, Si; Li, Yang; Bengio, Samy; Hsieh, Chojui
  • Application of web usage mining and product taxonomy to collaborative recommendations in e-commerce
    Cho, Yoon Ho; Kim, Jae Kyeong
  • Gift-giving, sharing, and commodity exchange at bookcrossing
    Corciolani, Matteo; Dalli, Daniele
  • Emotion-based recommender system for overcoming the problem of information overload
    Costa, Hernani; Macedo, Luis
  • Organization and integration of chinese encyclopedia knowledge based on semantic web
    Fu, Yuxin; Wang, Xin; Feng, Zhiyong
  • Singular value decomposition and least squares solutions
    Golub, Gene H.; Reinsch, C.
  • Inductive representation learning on large graphs
    Hamilton, William L.; Ying, Zhitao; Leskovec, Jure
  • The movielens datasets: History and context
    Harper, F. Maxwell; Konstan, Joseph A.
  • Last
    Haupt, Jon
  • An e-commerce recommender system based on content-based filtering
    He, Weihong; Cao, Yi
  • LightGCN: Simplifying and powering graph convolution network for recommendation
    He, Xiangnan; Deng, Kuan; Wang, Xiang; Li, Yan; Zhang, Yongdong; Wang, Meng
  • Field-aware factorization machines for CTR prediction
    Juan, Yuchin; Zhuang, Yong; Chin, Weisheng; Lin, Chihjen
  • Semi-supervised classification with graph convolutional networks
    Kipf, Thomas; Welling, Max
  • Factorization meets the neighborhood: A multifaceted collaborative filtering model
    Koren, Yehuda
  • Combining collaborative filtering and semantic content-based approaches to recommend web services
    Lecue, Freddy
  • Efficient backprop
    Lecun, Yann; Bottou, Leon; Orr, Genevieve; Muller, Klausrobert
  • DeepGCNs: Can GCNs go as deep as CNNs? In Proceedings of the IEEE International Conference on Computer Vision, 9267–9276
    Li, Guohao; Muller, Matthias; Thabet, Ali; Ghanem, Bernard
  • Neural network-based question answering over knowledge graphs on word and character level
    Lukovnikov, Denis; Fischer, Asja; Lehmann, Jens; Auer, Soren
  • Sound and music recommendation with knowledge graphs
    Oramas, Sergio; Ostuni, Vito Claudio; Di Noia, Tommaso; Serra, Xavier; Di Sciascio, Eugenio
  • DeepWalk: Online learning of social representations
    Perozzi, Bryan; Alrfou, Rami; Skiena, Steven
  • Factorization machines
    Rendle, Steffen
  • The graph neural network model
    Scarselli, Franco; Gori, Marco; Tsoi, Ah Chung; Hagenbuchner, Markus; Monfardini, Gabriele
  • Unified filtering by combining collaborative filtering and content-based filtering via mixture model and exponential model
    Si, Luo; Jin, Rong
  • Knowledge-based recommendation: A review of ontology-based recommender systems for e-learning
    Tarus, John K.; Niu, Zhendong; Mustafa, Ghulam M.
  • Affective labeling in a content-based recommender system for images
    Tkalcic, Marko; Odic, Ante; Kosir, Andrej; Tasic, Jurij F.
  • Graph attention networks
    Velickovic, Petar; Cucurull, Guillem; Casanova, Arantxa; Romero, Adriana; Lio, Pietro; Bengio, Yoshua
  • Survey of personalized recommendation system
    Wang, Guoxia; Liu, Heping
  • Shine: Signed heterogeneous information network embedding for sentiment link prediction
    Wang, Hongwei; Zhang, Fuzheng; Hou, Min; Xie, Xing; Guo, Minyi; Liu, Qi
  • RippleNet: Propagating user preferences on the knowledge graph for recommender systems
    Wang, Hongwei; Zhang, Fuzheng; Wang, Jialin; Zhao, Miao; Li, Wenjie; Xie, Xing; Guo, Minyi
  • DKN: Deep knowledge-aware network for news recommendation
    Wang, Hongwei; Zhang, Fuzheng; Xie, Xing; Guo, Minyi
  • Knowledge graph convolutional networks for recommender systems
    Wang, Hongwei; Zhao, Miao; Xie, Xing; Li, Wenjie; Guo, Minyi
  • KGAT: Knowledge graph attention network for recommendation
    Wang, Xiang; He, Xiangnan; Cao, Yixin; Liu, Meng; Chua, Tatseng
  • Graph convolutional neural networks for web-scale recommender systems
    Ying, Rex; He, Ruining; Chen, Kaifeng; Eksombatchai, Pong; Hamilton, William L.; Leskovec, Jure
  • Personalized entity recommendation: A heterogeneous information network approach
    Yu, Xiao; Ren, Xiang; Sun, Yizhou; Gu, Quanquan; Sturt, Bradley; Khandelwal, Urvashi; Norick, Brandon; Han, Jiawei
  • UR: A user-based collaborative filtering recommendation system based on trust mechanism and time weighting
    Zhang, Lei; Zhang, Zhijun; He, Jufang; Zhang, Zhenyu