paper-with-me

홈 › Papers

Rethinking Graph Contrastive Learning through Relative Similarity Preservation

2025-05-08 · Zhiyuan Ning, Pengfei Wang, Ziyue Qiao, Pengyang Wang, Yuanchun Zhou

Graph contrastive learning (GCL) has achieved remarkable success by following the computer vision paradigm of preserving absolute similarity between augmented views. However, this approach faces fundamental challenges in graphs due to their discrete, non-Euclidean nature -- view generation often breaks semantic validity and similarity verification becomes unreliable. Through analyzing 11 real-world graphs, we discover a universal pattern transcending the homophily-heterophily dichotomy: label consistency systematically diminishes as structural distance increases, manifesting as smooth decay in homophily graphs and oscillatory decay in heterophily graphs. We establish theoretical guarantees for this pattern through random walk theory, proving label distribution convergence and characterizing the mechanisms behind different decay behaviors. This discovery reveals that graphs naturally encode relative similarity patterns, where structurally closer nodes exhibit collectively stronger semantic relationships. Leveraging this insight, we propose RELGCL, a novel GCL framework with complementary pairwise and listwise implementations that preserve these inherent patterns through collective similarity objectives. Extensive experiments demonstrate that our method consistently outperforms 20 existing approaches across both homophily and heterophily graphs, validating the effectiveness of leveraging natural relative similarity over artificial absolute similarity.

📄 PDF Abstract BibTeX arXiv:2505.05533

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Scene Graph Embeddings Using Relative Similarity Supervision

2021-04-06 · Paridhi Maheshwari, Ritwick Chaudhry, Vishwa Vinay

Scene graphs are a powerful structured representation of the underlying content of images, and embeddings derived from them have been shown to be useful in multiple downstream tasks. In this work, we employ a graph convo…

Contrastive LearningImage RetrievalRetrieval

Rethinking Contrastive Learning in Graph Anomaly Detection: A Clean-View Perspective

2025-05-23 · Di Jin, Jingyi Cao, Xiaobao Wang, Bingdao Feng 외

Graph anomaly detection aims to identify unusual patterns in graph-based data, with wide applications in fields such as web security and financial fraud detection. Existing methods typically rely on contrastive learning,…

Anomaly DetectionContrastive LearningFraud DetectionGraph Anomaly Detection

Rethinking Weak Supervision in Helping Contrastive Learning

2023-06-07 · Jingyi Cui, Weiran Huang, Yifei Wang, Yisen Wang

Contrastive learning has shown outstanding performances in both supervised and unsupervised learning, and has recently been introduced to solve weakly supervised learning problems such as semi-supervised learning and noi…

Contrastive LearningDenoisingWeakly-supervised Learning

Symmetric Graph Contrastive Learning against Noisy Views for Recommendation

2024-08-03 · Chu Zhao, Enneng Yang, Yuliang Liang, Jianzhe Zhao 외

Graph Contrastive Learning (GCL) leverages data augmentation techniques to produce contrasting views, enhancing the accuracy of recommendation systems through learning the consistency between contrastive views. However, …

Contrastive LearningData AugmentationRecommendation Systems

How does Contrastive Learning Organize Images?

2023-05-17 · Yunzhe Zhang, Yao Lu, Qi Xuan

Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones. Although low contrastive loss often corre…

ClusteringContrastive Learning