Cross-Behavior Feature Regularization and Interaction Contrastive Learning Based Multi-Behavior Recommendation

doi:10.19678/j.issn.1000-3428.0070453

Abstract

Abstract:

Multi-behavioral recommendations have become a research hotspot for personalized recommendation tasks. To address the issues of biased information transfer between front and back behaviors and low differentiation between samples in existing multi-behavioral recommendation models, a Cross-Behavior Feature Regularization and Interaction Contrastive Learning based multi-behavior recommendation model (CBFRICL) is proposed. Cross-behavioral feature regularization is used to improve the inter-behavioral feature transfer mechanism based on the differences in pre- and post-behavioral features. Redundant information from previous behaviors is filtered to reduce the enforced dependence between consecutive behaviors. Therefore, the diversity and relative independence of information across different behaviors are preserved. The learning process of the model is constrained using regularization terms. Feature interference is prevented during the transfer process, reducing information distortion and mitigating error accumulation in cascaded Graph Convolutional Network (GCN) structures. An interaction contrastive learning method is proposed based on the spatial distribution rules of user-item interactions. Positive and negative sample pairs are generated using information on user interaction history. Positive samples are brought closer together, and negative samples are pushed away in the feature space, aiding the model in defining the sample boundaries. The sample clustering effect in the feature space is enhanced by capturing the personalized preferences of each user. Thus, the accuracy of the item recommendations is improved. The experimental results show that on the public datasets Tmall, Beibei, and Jdata, CBFRICL improves the HR@K and NDCG@K metrics by a minimum of 4.88% and 1.58%, respectively, compared to the CRGCN model.

Key words: multi-behavior recommendation, contrastive learning, feature regularization, cascaded Graph Convolutional Network (GCN), sample boundary

摘要：

多行为推荐已经成为个性化推荐任务的研究热点。针对现有多行为推荐模型存在前后行为信息传递偏移, 以及样本间区分度较低的问题, 提出了一种基于跨行为特征正则化和交互对比学习的多行为推荐模型(CBFRICL)。根据前后行为特点差异, 采用跨行为特征正则化, 改进行为间特征传递机制, 过滤前一行为传递的冗余信息, 降低前后行为的强制依赖性, 保持行为间信息的多样性与相对独立性, 利用正则项约束模型的学习过程, 防止传递过程中特征相互干扰导致信息失真, 进而缓解级联图卷积神经网络(GCN)结构中的误差累积。根据用户-项目交互的空间分布规则, 提出交互对比学习方法, 利用用户交互历史信息生成正负样本对, 在特征空间中拉近正样本距离, 推开负样本, 辅助模型界定样本边界, 同时增强特征空间的样本聚类效应, 捕捉每个用户的个性化偏好, 提升项目推荐的准确性。实验结果表明, 在公开数据集Tmall、Beibei和Jdata上, CBFRICL相较于CRGCN模型, HR@K和NDCG@K指标最低提升了4.88%、1.58%。

WU Di, ZHANG Le, CHEN Yao. Cross-Behavior Feature Regularization and Interaction Contrastive Learning Based Multi-Behavior Recommendation[J]. Computer Engineering, 2026, 52(7): 143-154.

吴迪, 张乐, 陈尧. 跨行为特征正则化和交互对比学习多行为推荐[J]. 计算机工程, 2026, 52(7): 143-154.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070453

https://www.ecice06.com/EN/Y2026/V52/I7/143

Figures/Tables 15

Fig.1 CBFRICL model framework

Fig.2 User behavior chain logical diagram

Fig.3 Positive and negative sample distribution adjustment diagram

Fig.4 Model metric changes under different Dropout rates

Fig.5 Model metric changes under different numbers of GCN layers

Fig.6 Comparison of model performence under cold-start conditions

References 27

1	姚迅, 王海鹏, 胡新荣, 等. 基于自适应增强的多视图对比推荐算法. 计算机工程, 2025, 51 (5): 103- 113. doi: 10.19678/j.issn.1000-3428.0069219
	YAO X , WANG H P , HU X R , et al. Multi-view contrastive recommendation algorithm based on adaptive enhancement. Computer Engineering, 2025, 51 (5): 103- 113. doi: 10.19678/j.issn.1000-3428.0069219
2	严明时, 程志勇, 孙静, 等. 基于两阶段学习的多行为推荐. 软件学报, 2024, 35 (5): 2446- 2465.
	YAN M S , CHENG Z Y , SUN J , et al. Two-stage learning for multi-behavior recommendation. Journal of Software, 2024, 35 (5): 2446- 2465.
3	DING J T, YU G H, HE X N, et al. Improving implicit recommender systems with view data[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. New York, USA: ACM Press, 2018: 3343-3349.
4	QIU H H , LIU Y , GUO G B , et al. BPRH: Bayesian personalized ranking for heterogeneous implicit feedback. Information Sciences, 2018, 453, 80- 98. doi: 10.1016/j.ins.2018.04.027
5	CHO J , HYUN D , LIM D W , et al. Dynamic multi-behavior sequence modeling for next item recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 37 (4): 4199- 4207. doi: 10.1609/aaai.v37i4.25537
6	LUO X , WU D Q , GU Y Y , et al. Criterion-based heterogeneous collaborative filtering for multi-behavior implicit recommendation. ACM Transactions on Knowledge Discovery from Data, 2024, 18 (1): 1- 26.
7	田志轩, 刘骊, 付晓东, 等. 融合偏好学习和意图建模的个性化服装序列推荐. 计算机工程, 2025, 51 (12): 130- 139. doi: 10.19678/j.issn.1000-3428.0069819
	TIAN Z X , LIU L , FU X D , et al. Personalized clothing sequence recommendation fused with preference learning and intention modeling. Computer Engineering, 2025, 51 (12): 130- 139. doi: 10.19678/j.issn.1000-3428.0069819
8	CAI H Y , MENG J , YUAN S L , et al. A robust sequential recommendation model based on multiple feedback behavior denoising and trusted neighbors. Neural Processing Letters, 2024, 56 (1): 1.
9	ZHANG C, CHEN R, ZHAO X Y, et al. Denoising and prompt-tuning for multi-behavior recommendation[C]//Proceedings of the ACM Web Conference 2023. New York, USA: ACM Press, 2023: 1355-1363.
10	钱忠胜, 叶祖铼, 姚昌森, 等. 融合自适应周期与兴趣量因子的轻量级GCN推荐. 软件学报, 2024, 35 (6): 2974- 2998.
	QIAN Z S , YE Z L , YAO C S , et al. Lightweight GCN recommendation combining adaptive period and interest factor. Journal of Software, 2024, 35 (6): 2974- 2998.
11	XU J C, WANG C K, WU C, et al. Multi-behavior self-supervised learning for recommendation[C]//Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM Press, 2023: 496-505.
12	WEI Y H , MA H F , WANG Y K , et al. Dual graph attention networks for multi-behavior recommendation. International Journal of Machine Learning and Cybernetics, 2023, 14 (8): 2831- 2846. doi: 10.1007/s13042-023-01801-0
13	娄铮铮, 朱军娇, 张万闯, 等. 用户生成内容场景下角色导向图神经推荐方法. 计算机学报, 2024, 47 (6): 1288- 1303.
	LOU Z Z , ZHU J J , ZHANG W C , et al. Role-guided graph neural recommendation in user-generated content scenarios. Chinese Journal of Computers, 2024, 47 (6): 1288- 1303.
14	LI Y , ZHAO F T , CHEN Z , et al. Multi-behavior enhanced heterogeneous graph convolutional networks recommendation algorithm based on feature-interaction. Applied Artificial Intelligence, 2023, 37, 2201144. doi: 10.1080/08839514.2023.2201144
15	CHENG Z Y, HAN S, LIU F, et al. Multi-behavior recommendation with cascading graph convolution networks[C]//Proceedings of the ACM Web Conference 2023. New York, USA: ACM Press, 2023: 1181-1189.
16	MENG C, ZHAI C H, YANG Y, et al. Parallel knowledge enhancement based framework for multi-behavior recommendation[C]// Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. New York, USA: ACM Press, 2023: 1797-1806.
17	JIANG S P , ZHAO C . A cascaded embedding method with graph neural network for multi-behavior recommendation. International Journal of Machine Learning and Cybernetics, 2024, 15 (6): 2513- 2526. doi: 10.1007/s13042-023-02045-8
18	XUAN H R, LIU Y, LI B H, et al. Knowledge enhancement for contrastive multi-behavior recommendation[C]//Proceedings of the 16th ACM International Conference on Web Search and Data Mining. New York, USA: ACM Press, 2023: 195-203.
19	钱忠胜, 黄恒, 朱辉, 等. 融合层注意力机制的多视角图对比学习推荐方法. 计算机研究与发展, 2025, 62 (1): 160- 178.
	QIAN Z S , HUANG H , ZHU H , et al. Multi-perspective graph contrastive learning recommendation method with layer attention mechanism. Journal of Computer Research and Development, 2025, 62 (1): 160- 178.
20	YU W X, BIN C Z, LIU W Q, et al. Contrastive learning-based multi-behavior recommendation with semantic knowledge enhancement[C]//Proceedings of the IEEE International Conference on Data Mining (ICDM). Shanghai, China: IEEE Press, 2024: 1511-1516.
21	PENG X C , SUN J , YAN M S , et al. Attention-guided graph convolutional network for multi-behavior recommendation. Knowledge-Based Systems, 2023, 280, 111040. doi: 10.1016/j.knosys.2023.111040
22	MENG C , ZHAO Z Q , GUO W , et al. Coarse-to-fine knowledge-enhanced multi-interest learning framework for multi-behavior recommendation. ACM Transactions on Information Systems, 2024, 42 (1): 1- 27.
23	JIN B W, GAO C, HE X N, et al. Multi-behavior recommendation with graph convolutional networks[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM Press, 2020: 659-668.
24	HE X N, 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, USA: ACM Press, 2020: 639-648.
25	XIA L H, HUANG C, XU Y, et al. Multi-behavior enhanced recommendation with cross-interaction collaborative relation modeling[C]//Proceedings of the IEEE 37th International Conference on Data Engineering (ICDE). Chania, Greece: IEEE Press, 2021: 1931-1936.
26	GU S Y, WANG X, SHI C, et al. Self-supervised graph neural networks for multi-behavior recommendation[C]//Proceedings of the International Joint Conference on Artificial Intelligence. New York, USA: ACM Press, 2022: 2052-2058.
27	YAN M , CHENG Z , GAO C , et al. Cascading residual graph convolutional network for multi-behavior recommendation. ACM Transactions on Information Systems, 2023, 42 (1): 1- 26.

[1]	ZHENG Yuhao, LI Jianhua. Initial Phase Training Method of Class Incremental Learning Based on Class Boundary Sample Generation and Fine-Tuning [J]. Computer Engineering, 2026, 52(7): 86-93.
[2]	YU Zhengtao, SUN Ziqin, ZHANG Yongbing, GAO Shengxiang, HUANG Yuxin, TAN Kaiwen. Self-Supervised Sequence Recommendation Method Based on Random Self-Attention and Momentum Contrastive Learning [J]. Computer Engineering, 2026, 52(6): 132-140.
[3]	XUE Hanbing, NI Chen, LI Yuying, GUAN Jia, FANG Kai, CUI Wenqian. Entity Canonicalization Method Based on Dual-View Contrastive Learning and Submodular Optimization [J]. Computer Engineering, 2026, 52(6): 80-95.
[4]	HE Hongguang, XIAN Yantuan, XIANG Yan. Commonsense Knowledge Graph Completion Method Based on Relation-Constrained Contrastive Learning [J]. Computer Engineering, 2026, 52(4): 122-130.
[5]	ZHANG Zhen, YOU Lan, PENG Qingxi, JIN Hong, ZENG Haoqiu, XIA Yuchun. XSGCL: A Lightweight Graph Contrastive Learning Framework for Recommendation [J]. Computer Engineering, 2026, 52(4): 163-175.
[6]	GUO Tiansheng, XIE Jinkui. Adaptive Adjustment Graph Augmentation and Representation Structures for Recommendation Model [J]. Computer Engineering, 2026, 52(2): 69-78.
[7]	LI Qiang, TAN Xingyi, ZHENG Wei, LIU Zhen, YANG Wenhai. Graph Neural Network Inference Optimization Based on Adversarial Training and Contrastive Representation Distillation [J]. Computer Engineering, 2026, 52(1): 126-135.
[8]	YU Peng, YANG Jiaqi, CHEN Xinran, HE Chaobo. Feature-enhanced Recommendation Algorithm Based on Bipartite Graph Contrastive Learning [J]. Computer Engineering, 2025, 51(7): 100-110.
[9]	YAO Xun, WANG Haipeng, HU Xinrong, YANG Jie. Multi-view Contrastive Recommendation Algorithm Based on Adaptive Enhancement [J]. Computer Engineering, 2025, 51(5): 103-113.
[10]	QIAN Lifeng, LI Jing, ZOU Xuxi, CHEN Yu, GU Yalin, WEI Xunhu. Multi-view Graph Clustering Algorithm Based on Dual Contrastive Learning and Hard Sample Mining [J]. Computer Engineering, 2025, 51(12): 82-95.
[11]	Shuang GAO, Yilun SHI, Qiaozhi XU, Lei YU. Research on Cardiac MRI Segmentation Based on Asymmetric Encoding and Decoding Structure of Contrastive Learning [J]. Computer Engineering, 2024, 50(8): 290-300.
[12]	Lai QIAN, Weiwei ZHAO. Text Classification Method Based on Contrastive Learning and Attention Mechanism [J]. Computer Engineering, 2024, 50(7): 104-111.
[13]	Juan LIU, Youxiang DUAN, Yuxi LU, Lu ZHANG. Knowledge Graph Completion with Knowledge Enhancement and Contrastive Learning [J]. Computer Engineering, 2024, 50(7): 112-122.
[14]	WU Xing, YIN Haoyu, YAO Junfeng, LI Weimin, QIAN Quan. Multimodal Sentiment Analysis for Video Data [J]. Computer Engineering, 2024, 50(6): 218-227.
[15]	LI Tianfang, PU Yuanyuan, ZHAO Zhengpeng, XU Dan, QIAN Wenhua. Image-to-Image Translation Based on CLIP and Dual-Spatially Adaptive Normalization [J]. Computer Engineering, 2024, 50(5): 229-240.

Please choose a citation manager

Content to export