Temporal Conformity-aware Hawkes Graph Network for Recommendations
Chenglong Ma, Yongli Ren, Pablo Castells, Mark Sanderson
Abstract
Many existing recommender systems (RSs) assume user behavior is governed solely by their interests. However, the peer effect often influences individual decision-making, which leads to conformity behavior. Conventional solutions that eliminate indiscriminately such bias may cause RSs to neglect valuable information and depersonalize the recommendation results. Also, conformity can transform into user interest, e.g., discovering new tastes after a glance at popular music. By better representing different forms of conformity influence, we can do a better job at interest mining and debiasing. In certain extreme circumstances, the herd effect may be exacerbated by user anxiety with uncertainty (e.g., panic buying during the COVID-19 pandemic). RSs may thus fail to respond in time due to sudden and dramatic changes. Moreover, many existing studies potentially conflate conformity bias with popularity bias and lump together various factors responsible for differences in popularity. In this paper, we identify two distinct types of conformity behavior: informational conformity and normative conformity. To address this, we introduce the TCHN model, which utilizes attentional Hawkes processes to disentangle user self-interest and conformity in a personalized manner. Our approach incorporates temporal graph attention networks to capture users' stable and volatile dynamics. We conduct experiments on three real-world datasets, which uncover diverse levels of conformity among users. The results show that TCHN excels in recommendation accuracy, diversity, and fairness across various user groups. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Sequential Recommendation with Graph Neural Networks cites Global Context Enhanced Graph Neural Networks for Session-based Recommendation
- Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphs cites Inductive representation learning on temporal graphs
Cited by top-tier papers3
- SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain AdaptationXingtong Yu, Zechuan Gong, Chang Zhou, Yuan Fang et al.WWW 2025 · 45 citations
- Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed GraphsYuanyuan Xu, Wenjie Zhang, Ying Zhang, Xuemin Lin et al.AAAI 2026 · 2 citations
- Know Your Neighbors: Subgraph Importance Sampling for Heterophilic Graph Active LearningWenjie Yang, Shengzhong Zhang, Chen Ye, Jiaxing Guo et al.AAAI 2026
Builds on10
- Inductive representation learning on temporal graphsDa Xu, Chuanwei Ruan, Evren Körpeoglu, Sushant Kumar et al.ICLR 2020 · 901 citations
- Global Context Enhanced Graph Neural Networks for Session-based RecommendationZiyang Wang, Wei Wei, Gao Cong, Xiao-Li Li et al.SIGIR 2020 · 558 citations
- Sequential Recommendation with Graph Neural NetworksJianxin Chang, Chen Gao, Yu Zheng, Yiqun Hui et al.SIGIR 2021 · 435 citations
- Causal Intervention for Leveraging Popularity Bias in RecommendationYang Zhang, Fuli Feng, Xiangnan He, Tianxin Wei et al.SIGIR 2021 · 431 citations
- Disentangling User Interest and Conformity for Recommendation with Causal EmbeddingYu Zheng, Chen Gao, Xiang Li, Xiangnan He et al.WWW 2021 · 392 citations
Related papers
- Modeling Social Behavior in Collaborative FilteringYihong Zhang, Takahiro HaraSIGIR 2025
- Taming Recommendation Bias with Causal Intervention on Evolving Personal PopularityShiyin Tan, Dongyuan Li, Renhe Jiang, Zhen Wang et al.KDD 2025 · 1 citation
- Debiased Contrastive Learning for Sequential RecommendationYuhao Yang, Chao Huang, Lianghao Xia, Chunzhen Huang et al.WWW 2023 · 199 citations
- HDNR: A Hyperbolic-Based Debiased Approach for Personalized News RecommendationShicheng Wang, Shu Guo, Lihong Wang, Tingwen Liu et al.SIGIR 2023 · 15 citations
- CausalRD: A Causal View of Rumor Detection via Eliminating Popularity and Conformity BiasesWeifeng Zhang, Ting Zhong, Ce Li, Kunpeng Zhang et al.INFOCOM 2022 · 13 citations
