paper-with-me

Papers

Oversmoothing: A Nightmare for Graph Contrastive Learning?

2023-06-03 · Jintang Li, Wangbin Sun, Ruofan Wu, Yuchang Zhu, Liang Chen, Zibin Zheng

Oversmoothing is a common phenomenon observed in graph neural networks (GNNs), in which an increase in the network depth leads to a deterioration in their performance. Graph contrastive learning (GCL) is emerging as a promising way of leveraging vast unlabeled graph data. As a marriage between GNNs and contrastive learning, it remains unclear whether GCL inherits the same oversmoothing defect from GNNs. This work undertakes a fundamental analysis of GCL from the perspective of oversmoothing on the first hand. We demonstrate empirically that increasing network depth in GCL also leads to oversmoothing in their deep representations, and surprisingly, the shallow ones. We refer to this phenomenon in GCL as `long-range starvation', wherein lower layers in deep networks suffer from degradation due to the lack of sufficient guidance from supervision. Based on our findings, we present BlockGCL, a remarkably simple yet effective blockwise training framework to prevent GCL from notorious oversmoothing. Without bells and whistles, BlockGCL consistently improves robustness and stability for well-established GCL methods with increasing numbers of layers on several real-world graph benchmarks.

📄 PDF Abstract BibTeX arXiv:2306.02117

Code (1)

edisonleeeee/blockgcl 공식 구현 pytorch

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond

2023-03-12 · Xiaojun Guo, Yifei Wang, Tianqi Du, Yisen Wang

Oversmoothing is a common phenomenon in a wide range of Graph Neural Networks (GNNs) and Transformers, where performance worsens as the number of layers increases. Instead of characterizing oversmoothing from the view of…

Contrastive Learning

Nightmare Dreamer: Dreaming About Unsafe States And Planning Ahead

2026-01-08 · Oluwatosin Oseni, Shengjie Wang, Jun Zhu, Micah Corah arxiv

Reinforcement Learning (RL) has shown remarkable success in real-world applications, particularly in robotics control. However, RL adoption remains limited due to insufficient safety guarantees. We introduce Nightmare Dr…

Reinforcement Learning

Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering

2024-06-20 · Yihong Wu, Le Zhang, Fengran Mo, Tianyu Zhu 외

Graph-based models and contrastive learning have emerged as prominent methods in Collaborative Filtering (CF). While many existing models in CF incorporate these methods in their design, there seems to be a limited depth…

Collaborative FilteringContrastive Learning

A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks

2022-12-21 · Xinyi Wu, Zhengdao Chen, William Wang, Ali Jadbabaie

Oversmoothing is a central challenge of building more powerful Graph Neural Networks (GNNs). While previous works have only demonstrated that oversmoothing is inevitable when the number of graph convolutions tends to inf…

DenoisingStochastic Block Model

ATNPA: A Unified View of Oversmoothing Alleviation in Graph Neural Networks

2024-05-02 · Yufei Jin, Xingquan Zhu

Oversmoothing is a commonly observed challenge in graph neural network (GNN) learning, where, as layers increase, embedding features learned from GNNs quickly become similar/indistinguishable, making them incapable of di…

Graph Neural NetworkRelation