Heterogeneous Debiasing Contrastive Learning for Graph Recommendation

借记 计算机科学 人工智能 图形 自然语言处理 语义学(计算机科学) 机器学习 知识图 任务(项目管理) 结构化预测
作者
Lei Sang,Jiahao Cheng,Lin Mu,Yiwen Zhang,Xindong Wu
出处
期刊:IEEE transactions on systems, man, and cybernetics [Institute of Electrical and Electronics Engineers]
卷期号:56 (10): 5510-5523
标识
DOI:10.1109/tsmc.2026.3703824
摘要

Heterogeneous graph neural networks (HGNNs) have demonstrated exceptional capabilities in modeling complex relationships for recommendation tasks. Their integration with contrastive learning (CL) has recently garnered significant attention due to its ability to effectively capture both structural and semantic features, while leveraging unlabeled data to improve robustness. However, existing methods face two key challenges: 1) noise in metapath-based message passing weakens user and item representations, especially with sparse data and 2) popularity bias in heterogeneous graphs causes popular items to dominate, while less popular “tail” items suffer from limited connections and relations. To address these challenges, we propose heterogeneous debiasing CL (HDCL), which combines heterogeneous graph debiasing with a neighborhood-aggregated strategy to enhance recommendation accuracy and diversity. Specifically, HDCL employs a neighborhood-aggregated CL (NACL) algorithm, which utilizes k-nearest neighbor features to enhance training signals and mitigate noise in sparse data settings. Additionally, HDCL introduces a hierarchical clustering-based debiasing (HCD) mechanism that dynamically distinguishes head nodes from tail nodes, refining the embedding space and improving recommendations for long-tail items. Extensive experiments on public datasets demonstrate that HDCL consistently outperforms state-of-the-art methods in terms of Recall and NDCG. The source code for the model implementation is available at the linkhttps://github.com/Jhcodeno1/HDCL
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
小一完成签到,获得积分20
刚刚
刚刚
Rocky完成签到,获得积分10
刚刚
1秒前
1秒前
缓慢的孱的应助被虚心的向秋采纳,获得10
2秒前
4秒前
李爱国的应助被FGGFGGU采纳,获得10
4秒前
李健的应助被LIU采纳,获得10
4秒前
SciGPT的应助被飘飘采纳,获得10
4秒前
Hello的应助被细腻驳采纳,获得10
4秒前
Aaa__JiAn完成签到,获得积分10
5秒前
5秒前
怪默完成签到,获得积分10
6秒前
专注数据线完成签到,获得积分20
7秒前
qqww2233发布了新的文献求助30
7秒前
8秒前
开放满天发布了新的文献求助10
8秒前
miaomiao完成签到,获得积分10
8秒前
8秒前
9秒前
Abracadabra的应助被chen采纳,获得10
9秒前
10秒前
10秒前
11秒前
CodeCraft的应助被静哥哥采纳,获得10
11秒前
11秒前
12秒前
12秒前
pumpkin完成签到,获得积分10
13秒前
13秒前
SRJ完成签到,获得积分10
13秒前
村民发布了新的文献求助30
14秒前
花呗发布了新的文献求助20
14秒前
木子发布了新的文献求助10
14秒前
BanghaoWei发布了新的文献求助10
15秒前
xing_xing的应助被小付采纳,获得100
15秒前
16秒前
Sheng发布了新的文献求助10
16秒前
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
Resource Recovery Handbook 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8175157
求助须知:如何正确求助?哪些是违规求助? 9566975
关于积分的说明 21789458
捐赠科研通 7769647
什么是DOI,文献DOI怎么找? 3431836
关于科研通互助平台的介绍 2556078
邀请新用户注册赠送积分活动 2477241