融合知识图谱与注意力机制的推荐算法

doi:10.3778/j.issn.1002-8331.2109-0126

摘要/Abstract

摘要： 为了解决信息过载问题，提出了一种融合知识图谱与注意力机制的推荐模型。在该模型中，将知识图谱作为辅助信息进行嵌入，可以缓解传统推荐算法数据稀疏和冷启动问题，并且给推荐结果带来可解释性。为了提升推荐准确率以及捕捉用户兴趣的动态变化，再结合深度学习中的神经网络以及注意力机制生成用户自适应表示，加上动态因子来更好地捕捉用户动态兴趣变化，使用多层感知机对项目进行评分预测。在MovieLens-latest-small电影数据集和豆瓣数据集进行仿真验证，结果表明该模型进行TOP-K列表电影推荐相比于其他算法拥有更好的推荐性能。

关键词: 知识图谱, 神经网络, 注意力机制, 多层感知机, 推荐算法

Abstract: In order to solve the problem of information overload, this paper proposes a recommendation model that combines knowledge graph and attention mechanism. First of all, in the model, embedding the knowledge graph as auxiliary information can alleviate the data sparseness and cold start problems of the traditional recommendation algorithm, and bring interpretability to the final recommendation result. Secondly, in order to improve the recommendation accuracy and capture the dynamic changes of user interests, combined with the neural network in deep learning and the attention mechanism to generate user-adaptive representations, plus dynamic factors to better capture user dynamic changes in interest, using multiple layers perceptron makes scoring predictions for items. Finally, the simulation verification is performed on the MovieLens-latest-small movie dataset and the Douban dataset. The results show that the model for TOP-K list recommendation has better recommendation performance than other algorithms.

Key words: knowledge graph, neural network, attention mechanism, multilayer perceptron, recommendation algorithm

唐宏, 范森, 唐帆, 朱龙娇. 融合知识图谱与注意力机制的推荐算法[J]. 计算机工程与应用, 2022, 58(5): 94-103.

TANG Hong, FAN Sen, TANG Fan , ZHU Longjiao. Recommendation Algorithm Combining Knowledge Graph and Attention Mechanism[J]. Computer Engineering and Applications, 2022, 58(5): 94-103.

参考文献

[1] LI K，WAN P Z，ZHANG D Z.Collaborative filtering recommendation algorithm based on improved user simi-larity measure and scoring forecast[J].Journal of Chinese Computer Systems，2018，39（3）：567-571.
[2] LI Y，WANG H J，LIU H L，et al.A study on content-based video recommendation[C]//2017 IEEE International Conference on Image Processing（ICIP），Beijing，China，2017：4581-4585.
[3] 刘纵横，汪海涛，姜瑛，等.基于混合神经网络的序列推荐算法[J].重庆邮电大学学报（自然科学版），2021，33（3）：466-474.
LIU Z H，WANG H T，JIANG Y，et al.Sequence recommendation algorithm based on hybrid neural network[J].Journal of Chongqing University of Posts and Telecommunications（Natural Science Edition），2021，33（3）：466-474.
[4] 王永，万潇逸，陶娅芝，等.基于K-medoids项目聚类的协同过滤推荐算法[J].重庆邮电大学学报（自然科学版），2017，29（4）：521-526.
WANG Y，WAN X Y，TAO Y Z，et al.Collaborative filtering recommendation algorithm based on K-medoids item clustering[J].Journal of Chongqing University of Posts and Telecommunications（Natural Science Edition），2017，29（4）：521-526.
[5] 李浩，张亚钏，康雁，等.融合循环知识图谱和协同过滤电影推荐算法[J].计算机工程与应用，2020，56（2）：106-114.
LI H，ZHANG Y C，KANG Y，et al.Fusion recurrent knowledge graph and collaborative filtering movie recommendation algorithm[J].Computer Engineering and Applications，2020，56（2）：106-114.
[6] 程开原，姚俊萍，李晓军，等.时态网络中知识图谱推荐：关键技术与研究进展[J].中国电子科学研究院学报，2021，16（2）：174-183.
CHENG K Y，YAO J P，LI X J，et al.Knowledge graph recommendation in temporal networks：key technologies and research progress[J].Journal of China Academy of Electronics，2021，16（2）：174-183.
[7] CAO Y，WANG X，HE X，et al.Unifying knowledge graph learning and recommendation：towards a better understanding of user preferences[C]//The World Wide Web Conference，2019：151-161.
[8] LI C，JIA K，SHEN D，et al.Hierarchical representation learning for bipartite graphs[C]//28th International Joint Conference on Artificial Intelligence，2019.
[9] LI Z，SHEN X，JIAO Y，et al.Hierarchical bipartite graph neural networks：towards large-scale e-commerce applications[C]//2020 IEEE 36th International Conference on Data Engineering（ICDE），2020.
[10] HE X N，CHUA T S.Neural factorization machines for sparse predictive analytics[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval，Shinjuku，Tokyo，Japan.New York，NY，USA：ACM，2017：355-364.
[11] ZHENG L，NOROOZI V，YU P S.Joint deep modeling of users and items using reviews for recommendation[C]//Proceedings of the Tenth ACM International Conference on Web Search and Data Mining.New York，NY，USA：ACM，2017：425-434.
[12] HE X N，LIAO L Z，ZHANG H W，et al.Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web，2017：173-182.
[13] ZHANG Q G，CAO L B，ZHU C Z，et al.CoupledCF： learning explicit and implicit user-item couplings in recommendation for deep collaborative filtering[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence，Stockholm，Sweden，2018：3662-3668.
[14] GUO H，TANG R，YE Y，et al.DeepFM：a factorization-machine based neural network for CTR prediction[C]//Proceedings of IJCAI，2017：1725-1731.
[15] WU S，TANG Y，ZHU Y，et al.Session-based recommendation with graph neural networks[C]//Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence，2019.
[16] 刘峤，李杨，段宏，等.知识图谱构建技术综述[J].计算机研究与发展，2016，53（3）：582-600.
LIU Q，LI Y，DUAN H，et al.Konwledge graph construction techniques[J].Journal of Computer Research and Development，2016，53（3）：582-600.
[17] 黄立威，江碧涛，吕守业，等.基于深度学习的推荐系统研究综述[J].计算机学报，2018，41（7）：1619-1647.
HUANG L W，JIANG B T，LV S Y，et al.Survey on deep learning based recommender systems[J].Chinese Journal of Computers，2018，41（7）：1619-1647.
[18] 张硕伟，陈军华，雍睿涵.基于降噪自编码和卷积神网络的协同过滤算法[J].计算机与数字工程，2020，48（10）：2441-2445.
ZHANG S W，CHEN J H，YONG R H.Collaborative filtering algorithm based on denoising auto-encoder and convolutional neural networks[J].Computer and Digital Engineering，2020，48（10）：2441-2445.
[19] 刘纵横，汪海涛，姜瑛，等.基于自注意力机制与知识图谱的序列推荐算法[J].传感器与微系统，2021，40（2）：132-135.
LIU Z H，WANG H T，JIANG Y，et al.Sequence recom-mendation algorithm based on self-attention mechanism and knowledge graph[J].Transducer and Microsystem Technologies，2021，40（2）：132-135.
[20] HE X，CHUA T.Neural factorization machines for sparse predictive analytics[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval，2017：355-364.
[21] HE X N，HE Z K，SONG J K，et al.NAIS：neural attentive item similarity model for recommendation[J].IEEE Transactions on Knowledge and Data Engineering，2018，30（12）：2354-2366.
[22] WANG H，ZHAO M，XIE X，et al.Knowledge graph convolutional networks for recommender sytems[C]//The World Wide Web Conference，San Francisco，May 13-17，2019.New York：ACM，2019：3307-3313.