端到端异构图信息协同过滤推荐

doi:10.19665/j.issn1001-2400.20241101

摘要/Abstract

摘要：

知识图谱(KG)在挖掘推荐场景中项目之间高阶关系方面逐渐成为一项重要趋势。尽管一些基于知识图谱的模型,如知识图注意网络(KGAT),能够有效建模一阶关系,但它们面临着无法对高阶关系中的协作信息进行建模的挑战。此外,现有的基于知识图谱的模型将交互行为简化为一种知识图谱关系,直接将用户-项目二分图与知识图融合成为一个整合图,却忽略了图结构之间的异构性,导致无法充分保留图内特定属性。在这项研究中,深入分析了交互行为和关系链接之间的潜在差异与联系,并提出了一种名为异构图信息协同过滤(HGICF)的创新消息传播机制。该机制能够将用户-项目行为和知识图谱辅助信息的协作特征有效传播到一个综合的模型中。这一解决方案不仅维持了图内属性的依赖关系,而且有助于跨图信息的有效聚合。为了深刻理解知识图谱和二部图之间的协作关系,进一步提出了共享特征协同过滤层,该层能够根据不同的数据结构和需求设置不同的层级。实验结果表明,HGICF在性能上显著优于当前方法。

关键词: 信息系统, 推荐系统, 图神经网络, 知识图谱, 协作过滤

Abstract:

Knowledge Graphs(KG) have emerged as a pivotal trend in uncovering intricate relations between items within recommendation scenarios.While models such as the Knowledge Graph Attention Network(KGAT) focus on establishing first-order relations,their limitations become apparent when attempting to capture collaborative information inherent in high-order relations.Existing KG-based models,including the KGAT,often treat interactive behavior as a mere KG relation.They seamlessly fuse user-item bipartite graphs with knowledge graphs into a unified fusion graph,but neglect the inherent heterogeneity between graph structures.This oversight results in a weakened ability to preserve graph-specific properties.In response to these challenges,we delve into a comprehensive analysis of the latent disparities and connections between user-item interactions and relation links.We introduce a groundbreaking message propagation mechanism known as Heterogeneous Graph Information Collaborative Filtering(HGICF).This mechanism seamlessly propagates collaborative features derived from user-item behaviors and KG side information within a unified model.Unlike existing approaches,HGICF not only upholds the intrinsic attributes of inner-graph structures but also facilitates the aggregation of cross-graph information.To gain a deeper understanding of the collaborative dynamics between knowledge graphs and bipartite graphs,we introduce shared feature collaborative filtering layers.These layers are designed to adapt to various data structures and requirements by allowing different layers to be set based on the specificities of the underlying information,which leads to a flexible and adaptive model capable of capturing the nuances of diverse data sources.Extensive experiments conducted validate the superior performance of HGICF over existing state-of-the-art methods.The proposed model excels in preserving the intricate relationships within knowledge graphs and bipartite graphs,showcasing its efficacy in collaborative filtering scenarios.By addressing the limitations of current KG-based models,HGICF stands as a significant advancement in the realm of recommendation systems,offering a more robust and nuanced approach to collaborative information modeling.

Key words: information systems, recommendation system, graph neural network, knowledge graph, collaborative filtering

中图分类号:

TP181

陈宸, 成蓉, 宋彬. 端到端异构图信息协同过滤推荐[J]. 西安电子科技大学学报, 2025, 52(1): 163-180.

CHEN Chen, CHENG Rong, SONG Bin. End-to-end heterogeneous graph information collaborative filtering for recommendation[J]. Journal of Xidian University, 2025, 52(1): 163-180.

图/表 16

图1

图2

图3

图4

表1

表2

表3

图5

图6

图7

图8

图9

图10

表4

表5

图11

参考文献 57

[1]	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 Liwei, JIANG Bitao, LV Shouye, et al. A Review of Research on Recommendation Systems Based on Deep Learning[J]. Chinese Journal of Computers, 2018, 41(7):1619-1647.
[2]	DAI S, SHAO N, ZHAO H, et al. Uncovering CHATGPT’S Capabilities in Recommender Systems[C]// Proceedings of the 17th ACM Conference on Recommender Systems. New York: ACM, 2023:1126-1132.
[3]	JIN D, WANG L, ZHANG H, et al. A Survey on Fairness-Aware Recommender Systems[J]. Information Fusion, 2023, 100:101906.
[4]	RAJPUT S, MEHTA N, SINGH A, et al. Recommender Systems with Generative Retrieval[J]. Advances in Neural Information Processing Systems, 2024, 36:10299-10315.
[5]	WANG Y, MA W, ZHANG M, et al. A Survey on the Fairness of Recommender Systems[J]. ACM Transactions on Information Systems, 2023, 41(3):1-43.
[6]	黄河源, 慕彩红, 方云飞, 等. 使用图负采样的图卷积神经网络推荐算法[J]. 西安电子科技大学学报, 2024, 51(1):86-99.
	HUANG Heyuan, MU Caihong, FANG Yunfei, et al. Graph Convolution Neural Network for Recommendation Using Graph Negative Sampling[J]. Journal of Xidian University, 2024, 51(1):86-99.
[7]	YAO F, LI C, SANKARARAMAN K A, et al. Rethinking Incentives in Recommender Systems:Are Monotone Rewards Always Beneficial?[J]. Advances in Neural Information Processing Systems, 2024:36.
[8]	邓爱林, 朱扬勇, 施伯乐. 基于项目评分预测的协同过滤推荐算法[J]. 软件学报, 2003, 14(9):1621-1628.
	DENG Ailin, ZHU Yangyong, SHI Bole. Collaborative Filtering Recommendation Algorithm Based on Item Score Prediction[J]. Journal of Software, 2003, 14(9):1621-1628.
[9]	KUO R J, LI S S. Applying Particle Swarm Optimization Algorithm-Based Collaborative Filtering Recommender System Considering Rating and Review[J]. Applied Soft Computing, 2023, 135:110038.
[10]	REN X, XIA L, ZHAO J, et al. Disentangled Contrastive Collaborative Filtering[C]// Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2023:1137-1146.
[11]	ZHANG Y, ZHU H, SONG Z, et al. Mitigating the Popularity Bias of Graph Collaborative Filtering:A Dimensional Collapse Perspective[J]. Advances in Neural Information Processing Systems, 2023, 36:67533-67550.
[12]	SUN P, WU L, ZHANG K, et al. Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 36(5):2069-2081.
[13]	YING R, HE R, CHEN K, et al. Graph Convolutional Neural Networks for Web-Scale Recommender Systems[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2018:974-983.
[14]	YANG J H, CHEN C M, WANG C J, et al. HOP-Rec:High-Order Proximity for Implicit Recommendation[C]// Proceedings of the 12th ACM Conference on Recommender Systems. New York: ACM, 2018:140-144.
[15]	WANG X, He X, WANG M, et al. Neural Graph Collaborative Filtering[C]// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2019:165-174.
[16]	BERG R, KIPF T N, WELLING M. Graph Convolutional Matrix Completion(2017)[J/OL].[20217-10-25]. https://arxiv.org/abs/1706.02263.
[17]	LI X, SUN L, LING M, et al. A Survey of Graph Neural Network Based Recommendation in Social Networks[J]. Neurocomputing, 2023, 549:126441.
[18]	SHENG Z, ZHANG T, ZHANG Y, et al. Enhanced Graph Neural Network for Session-Based Recommendation[J]. Expert Systems with Applications, 2023, 213:118887.
[19]	HUANG J, XIE R, CAO Q, et al. Negative can be Positive:Signed Graph Neural Networks for Recommendation[J]. Information Processing & Management, 2023, 60(4):103403.
[20]	CAI D, QIAN S, FANG Q, et al. User Cold-Start Recommendation via Inductive Heterogeneous Graph Neural Network[J]. ACM Transactions on Information Systems, 2023, 41(3):1-27.
[21]	SHEN Q, ZHU S, PANG Y, et al. Temporal Aware Multi-Interest Graph Neural Network for Session-Based Recommendation[C]//Asian Conference on Machine Learning. Stroudsburg:PMLR, 2023:189.
[22]	WANG X, HE X, CAO Y, et al. KGAT:Knowledge Graph Attention Network for Recommendation[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2019:950-958.
[23]	ZHANG F, YUAN N J, LIAN D, et al. Collaborative Knowledge Base Embedding for Recommender Systems[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2016:353-362.
[24]	BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating Embeddings forModeling Multi-Relational Data[J]. Advances in Neural Information Processing Systems, 2013, 26:2787-2795.
[25]	KIPF T N, WELLING M. Semi-Supervised Classification with Graph Convolutional Networks(2016)[J/OL].[2017-02-22]. https://arxiv.org/abs/1609.02907.
[26]	KIPF T N, WELLING M. Variational Graph Auto-Encoders(2016)[J/OL].[2016-11-21]. https://arxiv.org/abs/1611.07308.
[27]	DWIVEDI V P, JOSHI C K, LUU A T, et al. Benchmarking Graph Neural Networks[J]. Journal of Machine Learning Research, 2023, 24(43):1-48.
[28]	HE X, DENG K, WANG X, et al. Lightgcn:Simplifying and Powering Graph Convolution Network for Recommendation[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020:639-648.
[29]	LIU F, CHENG Z, ZHU L, et al. An Attribute-Aware Attentive GCN Model for Attribute Missing in Recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(9):4077-4088.
[30]	ZHANG H, MCAULEY J. Stacked Mixed-Order Graph Convolutional Networks for Collaborative Filtering[C]//Proceedings of the 2020 SIAM International Conference on Data Mining. Philadelphia:SIAM, 2020:73-81.
[31]	LIU F, CHENG Z, ZHU L, et al. Interest-Aware Message-Passing GCN for Recommendation[C]// Proceedings of the Web Conference 2021. New York: ACM, 2021:1296-1305.
[32]	WANG X, HUANG T, WANG D, et al. Learning Intents Behind Interactions with Knowledge Graph for Recommendation[C]// Proceedings of the Web Conference 2021. New York: ACM, 2021:878-887.
[33]	WU S, TANG Y, ZHU Y, et al. Session-Based Recommendation with Graph Neural Networks[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2019, 33:346-353.
[34]	XU C, ZHAO P, LIU Y, et al. Graph Contextualized Self-Attention Network for Session-Based Recommendation[C]// IJCAI. New York: ACM, 2019, 19:3940-3946.
[35]	QIU R, LI J, HUANG Z, et al. Rethinking the Item Order in Session-Based Recommendation with Graph Neural Networks[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York: ACM, 2019:579-588.
[36]	CHEN C, GUO J, SONG B. Dual Attention Transfer in Session-Based Recommendation with Multi-Dimensional Integration[C]// Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2021:869-878.
[37]	PENG C, XIA F, NASERIPARSA M, et al. Knowledge Graphs:Opportunities and Challenges[J]. Artificial Intelligence Review, 2023, 56(11):13071-13102.
[38]	LIANG K, MENG L, LIU M, et al. A Survey of Knowledge Graph Reasoning on Graph Types:Static,Dynamic,and Multi-Modal[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(12):9456-9478.
[39]	LIN Y, LIU Z, SUN M, et al. Learning Entity and Relation Embeddings for Knowledge Graph Completion[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2015, 29:2181-2187.
[40]	BELL R M, KOREN Y. Lessons from the Netflix Prize Challenge[J]. ACM SIGKDD Explorations Newsletter, 2007, 9(2):75-79.
[41]	WANG H, ZHANG F, WANG J, et al. Ripplenet:Propagating User Preferences on The Knowledge Graph for Recommender Systems[C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM, 2018:417-426.
[42]	WANG Z, LIN G, TAN H, et al. CKAN:Collaborative Knowledge-aware Attentive Network for Recommender Systems[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020:219-228.
[43]	AI Q, AZIZI V, CHEN X, et al. Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation[J]. Algorithms, 2018, 11(9):137.
[44]	WANG Z, ZHANG J, FENG J, et al. Knowledge Graph Embedding by Translating on Hyperplanes[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2014, 28:1112-1119.
[45]	CAO Y, WANG X, HE X, et al. Unifying Knowledge Graph Learning and Recommendation:Towards A Better Understanding of User Preferences[C]// TheWorld Wide Web Conference. New York: ACM, 2019:151-161.
[46]	DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2d Knowledge Graph Embeddings[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2018, 32:1811-1818.
[47]	NGUYEN T D, NGUYEN D Q, PHUNG D. A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network[C]//North American Association for Computational Linguistics 2018. Stroudsburg:ACL, 2018:327-333.
[48]	WANG H, ZHANG F, ZHAO M, et al. Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation[C]// The World Wide Web Conference. New York: ACM, 2019:2000-2010.
[49]	SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling Relational Data with Graph Convolutional Networks[C]// The Semantic Web:15th International Conference,ESWC 2018.Berlin:Springer, 2018:593-607.
[50]	HAMILTON W, YING Z, LESKOVEC J. Inductive Representation Learning on Large Graphs[J]. Advances inNeural Information Processing Systems, 2017, 30:1025-1035.
[51]	RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR:Bayesian Personalized Ranking from Implicit Feedback(2012)[C/OL].[2012-05-09]. https://arxiv.org/abs/1205.2618.
[52]	RENDLE S, GANTNER Z, FREUDENTHALER C, et al. Fast Context-Aware Recommendations with Factorization Machines[C]// Proceedings of the 34th international ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2011:635-644.
[53]	HE X, 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. New York: ACM, 2017:355-364.
[54]	HE X, LIAO L, ZHANG H, et al. Neural Collaborative Filtering[C]// Proceedings of the 26th International Conference on World Wide Web. New York: ACM, 2017:173-182.
[55]	TANG H, ZHAO G, BU X, et al. Dynamic Evolution of Multi-Graph Based Collaborative Filtering for Recommendation Systems[J]. Knowledge-Based Systems, 2021, 228:107251.
[56]	GLOROT X, BENGIO Y. Understandingthe Difficulty of Training Deep Feedforward Neural Networks[C]// Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. New York: JMLR, 2010:249-256.
[57]	KINGMA D P, BA J. Adam:A Method for Stochastic Optimization(2014)[J/OL].[2017-01-30]. https://arxiv.org/abs/1412.6980?file=1412.6980.


用户-产品交互记录	#用户	70 679	23 566	45 919
	#产品	24 915	48 123	45 538
	#交互记录	847 733	1 331 638	1 185 068
知识图谱	#节点	88 572	106 389	90 961
	#关系	39	9	42
	#三元组	2 557 746	464 567	1 853 704

Amazon-book	Last-FM	Yelp2018	Amazon-book-part
工作	著名类型	城市	体裁
作者	艺术家	类别	类型
体裁	制作者	拥有电视	话题
角色	工程师	是否提供24小时营业服务	著名类型
…	…	…	…
“1-to-N” “N-to-N”	“1-to-N” “N-to-N”	“1-to-N”	“N-to-N”

	Last-FM		Yelp2018		Amazon-book		Amazon-book-part
	Recall	NDCG	Recall	NDCG	Recall	NDCG	Recall	NDCG
FM	0.077 8	0.118 1	0.062 7	0.076 8	0.134 5	0.088 6	0.144 8	0.098 3
NFM	0.082 9	0.121 4	0.066 0	0.081 0	0.136 6	0.091 3	0.131 0	0.090 1
NCF	0.061 5	0.136 5	0.060 9	0.051 7	0.134 3	0.087 0	0.133 7	0.090 6
NGCF	0.067 2	0.140 8	0.062 3	0.052 1	0.142 8	0.089 7	0.139 3	0.093 4
LightGCN			0.063 6	0.052 7	0.150 3	0.093 4	0.146 6	0.096 3
DMGCF	0.070 1	0.142 4	0.063 3	0.060 3	0.146 8	0.092 3	0.140 4	0.096 1
CKE	0.073 6	0.118 4	0.065 7	0.080 5	0.134 3	0.088 5	0.132 9	0.089 9
CFKG	0.072 3	0.114 3	0.052 2	0.064 4	0.114 2	0.077 0	0.116 2	0.078 4
KGIN	0.091 0	0.140 6	0.070 5	0.086 4	0.150 0	0.101 7	0.148 9	0.101 0
KGAT	0.088 2	0.136 6	0.071 2	0.086 7	0.149 7	0.101 9	0.149 3	0.101 2
HGICF	0.092 8	0.143 6	0.073 4	0.088 8	0.152 0	0.103 1	0.151 6	0.102 9
%improv.	1.93%	2.10%	3.09%	2.42%	1.54%	1.18%	1.54%	1.68%

	Amazon-book		Last-FM		Yelp2018
	Recall	NDCG	Recall	NDCG	Recall	NDCG
HGICF_H	0.130 6	0.089 0	0.083 7	0.133 1	0.067 9	0.081 7
HGICF_S	0.142 4	0.096 6	0.090 5	0.137 9	0.070 8	0.085 4
HGICF	0.152 0	0.103 1	0.092 8	0.143 6	0.073 4	0.088 8

	Amazon-book		Last-FM		Yelp2018
	Recall	NDCG	Recall	NDCG	Recall	NDCG
HGICF3-1	0.152 0	0.103 1	0.092 8	0.143 6	0.071 6	0.087 3
HGICF3-2	0.148 9	0.100 2	0.091 7	0.141 3	0.073 2	0.088 7
HGICF3-3	0.149 6	0.101 2	0.091 5	0.142 0	0.073 4	0.088 8