Skip to main content
SpringerLink
Log in

Entity-driven user intent inference for knowledge graph-based recommendation

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

It has been proven that a knowledge graph (KG) has the ability to improve the accuracy of recommendations, owing to its capability of storing the auxiliary information of items in a heterogeneous structure. Recently, intent inference methods have been developed to explore the user preference information from a KG and user-item interactions and to help improve the recommendation accuracy. The inferred user intent can also be regarded as a part of the reason why the recommendation model recommends a certain item to a user. It is known that there are two types of information in a KG: entities and relations. However, existing recommendation models infer user intents from only the information contained in the relations in a KG.

In this paper, we propose a new recommendation model, the entity-driven knowledge intent network (EKIN) to infer user intents using information from both entities and relations and make recommendations for users. For EKIN, we propose to construct an entity-driven user intent graph (EUIG) for each user. The EUIG exploits two types of information in a KG to infer user intents. A graph neural network is constructed with multi-hop propagation in the KG and EUIG to learn the representation of entities, relations and user intents. Moreover, we distill information on users’ interactions based on their inferred intents and aggregate the interactions to encode the user characteristics. The experimental results on three real-world datasets demonstrate that the proposed EKIN outperforms the state-of-the-art KG-based recommendation models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Ji S, Pan S et al (2022) A survey on knowledge graphs: Representation, acquisition, and applications[J]. IEEE Trans Neural Netw Learn Syst (TNNLS) 33(2):494–514. https://doi.org/10.1109/TNNLS.2021.3070843https://doi.org/10.1109/TNNLS.2021.3070843

    Article  MathSciNet  Google Scholar 

  2. Wang Q, Mao Z et al (2017) Knowledge graph embedding: A survey of approaches and applications[J]. IEEE Trans Knowl Data Eng (TKDE) 29(12):2724–2743. https://doi.org/10.1109/TKDE.2017.2754499https://doi.org/10.1109/TKDE.2017.2754499

    Article  Google Scholar 

  3. Guo Q, Zhuang F et al (2020) A survey on knowledge graph-based recommender systems[J]. IEEE Trans Knowl Data Eng (TKDE). https://doi.org/10.1109/TKDE.2020.3028705

  4. Hsu PY, Chen CT et al (2022) Explainable mutual fund recommendation system developed based on knowledge graph embeddings[J], Applied Intelligence. pp 1–26. https://doi.org/10.1007/s10489-021-03136-1https://doi.org/10.1007/s10489-021-03136-1

  5. Wu Z, Pan S et al (2021) A comprehensive survey on graph neural networks[J]. IEEE Trans Neural Netw Learn Syst (TNNLS) 32(1):4–24. https://doi.org/10.1109/TNNLS.2020.2978386

    Article  MathSciNet  Google Scholar 

  6. Zhang Z, Cui P et al (2022) Deep learning on graphs: a survey[J]. IEEE Trans Knowl Data Eng (TKDE) 34(1):249–270. https://doi.org/10.1109/TKDE.2020.2981333

    Article  Google Scholar 

  7. Hamilton W, Ying R et al (2017) Inductive representation learning on large graphs[C]. In: Proceedings of the 31st conference on neural information processing systems (NIPS), pp 1025–1035

  8. Wang X, He X et al (2019) KGAT: Knowledge graph attention network for recommendation[C]. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (KDD). https://doi.org/10.1145/3292500.3330989https://doi.org/10.1145/3292500.3330989, pp 950–958

  9. Zhang Z, Zhang L et al (2022) KRAN: Knowledge refining attention network for recommendation[J]. ACM Trans Knowl Discov Data Mining (TKDD) 16(2):39. https://doi.org/10.1145/3470783

    Google Scholar 

  10. Wang H, Zhao M et al (2019) Knowledge graph convolutional networks for recommender systems[C]. In: Proceedings of the world wide web conference (WWW). https://doi.org/10.1145/3308558.3313417, pp 3307–3313

  11. Tian Y, Yang Y et al (2021) Joint knowledge pruning and recurrent graph convolution for news recommendation[C]. In: Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval (SIGIR). https://doi.org/10.1145/3404835.3462912, pp 51–60

  12. Sang L, Xu M et al (2021) Knowledge graph enhanced neural collaborative recommendation[J]. Expert Syst Appl 164:113992. https://doi.org/10.1016/j.eswa.2020.113992

    Article  Google Scholar 

  13. Hui B, Zhang L et al (2022) Personalized recommendation system based on knowledge embedding and historical behavior[J]. Appl Intell 52(1):954–966. https://doi.org/10.1007/s10489-021-02363-whttps://doi.org/10.1007/s10489-021-02363-w

    Article  Google Scholar 

  14. Wang X, Xu Y et al (2020) Reinforced negative sampling over knowledge graph for recommendation[C]. In: Proceedings of the world wide web conference (WWW). https://doi.org/10.1145/3366423.3380098, pp 99–109

  15. Chen C, Zhang M et al (2020) Jointly non-sampling learning for knowledge graph enhanced recommendation[C]. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval (SIGIR). https://doi.org/10.1145/3397271.3401040, pp 189–198

  16. Wang H, Zhang F et al (2019) Knowledge-aware graph neural networks with label smoothness regularization for recommender systems[C]. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (KDD). https://doi.org/10.1145/3292500.3330836, pp 968–977

  17. Wang Z, Lin G et al (2020) CKAN: Collaborative knowledge-aware attentive network for recommender systems[C]. In: Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval (SIGIR). https://doi.org/10.1145/3397271.3401141, pp 219–228

  18. Wang X, Huang T et al (2021) Learning intents behind interactions with knowledge graph for recommendation[C]. In: Proceedings of the world wide web conference (WWW). https://doi.org/10.1145/3442381.3450133, pp 878–887

  19. Cao Y, Wang X et al (2019) Unifying knowledge graph learning and recommendation: towards a better understanding of user preferences[C]. In: Proceedings of the world wide web conference (WWW). https://doi.org/10.1145/3308558.3313705, pp 151–161

  20. Chen W, Huang P et al (2019) POG: personalized outfit generation for fashion recommendation at Alibaba iFashion[C]. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (KDD). https://doi.org/10.1145/3292500.3330652, pp 2662–2670

  21. Rendle S, Freudenthaler C et al (2009) BPR: Bayesian personalized ranking from implicit feedback[C]. In: Proceedings of the 25th conference on uncertainty in artificial intelligence (UAI), pp 452–461

  22. Zhang F, Yuan N et al (2016) Collaborative knowledge base embedding for recommender systems[C]. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (KDD). https://doi.org/10.1145/2939672.2939673, pp 353–362

  23. Vaswani A, Shazeer N et al (2017) Attention is all you need[C]. In: Proceedings of the 31st annual conference on neural information processing systems (NIPS), pp 6000–6010

  24. Brauwers G, Frasincar F et al (2021) A general survey on attention mechanisms in deep learning[J], IEEE Transactions on Knowledge and Data Engineering (TKDE). https://doi.org/10.1109/TKDE.2021.3126456

  25. He X, Liao L et al (2017) Neural collaborative filtering[C]. In: Proceedings of the world wide web conference (WWW). https://doi.org/10.1145/3038912.3052569, pp 173–182

  26. Covington P, Adams J et al (2016) Deep neural networks for YouTube recommendations[C]. In: Proceedings of the 10th ACM Conference on Recommender Systems (RecSys). https://doi.org/10.1145/2959100.2959190, pp 191–198

  27. Wang H, Zhang F et al (2018) RippleNet: Propagating user preferences on the knowledge graph for recommender systems[C]. In: Proceedings of the 27th ACM international conference on information and knowledge management (CIKM). https://doi.org/10.1145/3269206.3271739, pp 417–426

  28. Wang S, Qiu J et al (2021) A deep neural network model for fashion collocation recommendation using side information in e-commerce[J]. Appl Soft Comput 110:107753. https://doi.org/10.1016/j.asoc.2021.107753

    Article  Google Scholar 

  29. Ding Y, Ma Y et al (2021) Leveraging two types of global graph for sequential fashion recommendation[C]. In: Proceedings of the 2021 international conference on multimedia retrieval (ICMR). https://doi.org/10.1145/3460426.3463638, pp 73–81

  30. Wang H, Zhang F et al (2019) Multi-task feature learning for knowledge graph enhanced recommendation[C]. In: Proceedings of the World Wide Web Conference (WWW). https://doi.org/10.1145/3308558.3313411, pp 2000–2010

  31. Huang W, Wu J et al (2022) Cross attention fusion for knowledge graph optimized recommendation[J], Applied Intelligence. https://doi.org/10.1007/s10489-021-02930-1

  32. Paszke A, Gross S et al (2019) PyTorch: An imperative style, high-performance deep learning library[C]. In: Proceedings of the 33rd international conference on neural information processing systems (NIPS), pp 8026–8037

  33. Huang X, Zhang J et al (2019) Knowledge graph embedding based question answering[C]. In: Proceedings of the 12th ACM International Conference on Web Search and Data Mining (WSDM). https://doi.org/10.1145/3289600.3290956, pp 105–113

  34. Wang H, Zhang F et al (2018) DKN: Deep knowledge-aware network for news recommendation[C]. In: Proceedings of the World Wide Web Conference (WWW). https://doi.org/10.1145/3178876.3186175, pp 1835–1844

  35. Ji G, He S, Xu L et al (2015) Knowledge graph embedding via dynamic mapping matrix[C]. In: Proceedings of the 53rd annual meeting of the association for computational linguistics (ACL) and the 7th international joint conference on natural language processing, pp 687–696

  36. Shi C, Zhang Z et al (2015) Semantic path based personalized recommendation on weighted heterogeneous information networks[C]. In: Proceedings of the 24th ACM international on conference on information and knowledge management (CIKM). https://doi.org/10.1145/2806416.2806528, pp 453–462

  37. Zhao H, Yao Q et al (2017) Meta-graph based recommendation fusion over heterogeneous information networks[C]. In: Proceedings of the 23rd ACM SIGKDD International conference on knowledge discovery and data mining (KDD). https://doi.org/10.1145/3097983.3098063, pp 635–644

  38. Wang X, Wang D et al (2019) Explainable reasoning over knowledge graphs for recommendation[C]. In: Proceedings of the 33rd AAAI Conference on artificial intelligence and 31st Innovative applications of artificial intelligence conference and 9th AAAI Symposium on educational advances in artificial intelligence (AAAI/IAAI/EAAI). https://doi.org/10.1609/aaai.v33i01.33015329https://doi.org/10.1609/aaai.v33i01.33015329, pp 5329–5336

  39. Ma W, Zhang M et al (2019) Jointly learning explainable rules for recommendation with knowledge graph[C]. In: Proceedings of the world wide web conference (WWW). https://doi.org/10.1145/3308558.3313607, pp 1210–1221

  40. Xian Y, Fu Z et al (2019) Reinforcement knowledge graph reasoning for explainable recommendation[C]. In: Proceedings of the 42nd International ACM SIGIR conference on research and development in information retrieval (SIGIR). https://doi.org/10.1145/3331184.3331203, pp 285–294

Download references

Acknowledgements

This work is supported by the National Natural Science Foundation of China under Project No. 61977013.

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China

    Shaosong Li & Bo Yang

  2. School of Computer Science, Fudan University, Shanghai, 200441, China

    Dongsheng Li

Authors
  1. Shaosong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bo Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dongsheng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bo Yang.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, S., Yang, B. & Li, D. Entity-driven user intent inference for knowledge graph-based recommendation. Appl Intell 53, 10734–10750 (2023). https://doi.org/10.1007/s10489-022-04048-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04048-4

Keywords

Search

Navigation