Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning

• URL: http://arxiv.org/abs/2506.05214v1
• Date: Thu, 05 Jun 2025 16:28:12 GMT
• Title: Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning
• Authors: Jingyu Hu, Hongbo Bo, Jun Hong, Xiaowei Liu, Weiru Liu,
• Abstract summary: Graph Neural Networks (GNNs) often suffer from degree bias in node classification tasks.<n>Several approaches, which adopt Graph Contrastive Learning (GCL), have been proposed to mitigate this bias.<n>This paper proposes the Hardness Adaptive Reweighted (HAR) contrastive loss to mitigate degree bias.
• Score: 3.94446329459693
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph Neural Networks (GNNs) often suffer from degree bias in node classification tasks, where prediction performance varies across nodes with different degrees. Several approaches, which adopt Graph Contrastive Learning (GCL), have been proposed to mitigate this bias. However, the limited number of positive pairs and the equal weighting of all positives and negatives in GCL still lead to low-degree nodes acquiring insufficient and noisy information. This paper proposes the Hardness Adaptive Reweighted (HAR) contrastive loss to mitigate degree bias. It adds more positive pairs by leveraging node labels and adaptively weights positive and negative pairs based on their learning hardness. In addition, we develop an experimental framework named SHARP to extend HAR to a broader range of scenarios. Both our theoretical analysis and experiments validate the effectiveness of SHARP. The experimental results across four datasets show that SHARP achieves better performance against baselines at both global and degree levels.

Related papers

• Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling [17.51838571216239]
  Graph Contrastive Learning aims to self-supervised learn low-dimensional graph representations.<n>A consensus has been reached that the effectiveness of GCLs depends on a large number of negative pairs.<n>We propose a new method called GCL with Effective and Efficient Negative samples, E2Neg.
  arXiv  Detail & Related papers  (2025-03-23T03:09:31Z)
• Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning? [54.44813218411879]
  We introduce a new metric, namely Error Passing Rate (EPR), to quantify how a graph fits the network.<n>Inspired by the theoretical conclusions and the idea of positive-incentive noise, we propose a novel GCL algorithm, Error-PAssing-based Graph Contrastive Learning (EPAGCL)<n>We generate views by adding and dropping edges based on the weights derived from EPR.
  arXiv  Detail & Related papers  (2024-12-11T06:31:06Z)
• Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning [27.278097015083343]
  Contrastive learning requires negative samples to prevent model collapse and learn discriminative representations. We introduce a cross-attention module to predict the supportiveness score of a neighbor with respect to the anchor node. Our method mitigates class collision from negative and noisy positive samples, concurrently enhancing intra-class compactness.
  arXiv  Detail & Related papers  (2024-08-09T14:17:52Z)
• Topology Reorganized Graph Contrastive Learning with Mitigating Semantic Drift [28.83750578838018]
  Graph contrastive learning (GCL) is an effective paradigm for node representation learning in graphs. To increase the diversity of the contrastive view, we propose two simple and effective global topological augmentations to compensate current GCL.
  arXiv  Detail & Related papers  (2024-07-23T13:55:33Z)
• Learning to Reweight for Graph Neural Network [63.978102332612906]
  Graph Neural Networks (GNNs) show promising results for graph tasks. Existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability.
  arXiv  Detail & Related papers  (2023-12-19T12:25:10Z)
• Graph Ranking Contrastive Learning: A Extremely Simple yet Efficient Method [17.760628718072144]
  InfoNCE uses augmentation techniques to obtain two views, where a node in one view acts as the anchor, the corresponding node in the other view serves as the positive sample, and all other nodes are regarded as negative samples. The goal is to minimize the distance between the anchor node and positive samples and maximize the distance to negative samples. Due to the lack of label information during training, InfoNCE inevitably treats samples from the same class as negative samples, leading to the issue of false negative samples. We propose GraphRank, a simple yet efficient graph contrastive learning method that addresses the problem of false negative samples
  arXiv  Detail & Related papers  (2023-10-23T03:15:57Z)
• Perfect Alignment May be Poisonous to Graph Contrastive Learning [15.668610380413682]
  Graph Contrastive Learning (GCL) aims to learn node representations by aligning positive pairs and separating negative ones.<n>This paper seeks to establish a connection between augmentation and downstream performance.
  arXiv  Detail & Related papers  (2023-10-06T02:22:49Z)
• Pseudo Contrastive Learning for Graph-based Semi-supervised Learning [67.37572762925836]
  Pseudo Labeling is a technique used to improve the performance of Graph Neural Networks (GNNs) We propose a general framework for GNNs, termed Pseudo Contrastive Learning (PCL)
  arXiv  Detail & Related papers  (2023-02-19T10:34:08Z)
• STERLING: Synergistic Representation Learning on Bipartite Graphs [78.86064828220613]
  A fundamental challenge of bipartite graph representation learning is how to extract node embeddings. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. We introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs.
  arXiv  Detail & Related papers  (2023-01-25T03:21:42Z)
• Uncovering the Structural Fairness in Graph Contrastive Learning [87.65091052291544]
  Graph contrastive learning (GCL) has emerged as a promising self-supervised approach for learning node representations. We show that representations obtained by GCL methods are already fairer to degree bias than those learned by GCN. We devise a novel graph augmentation method, called GRAph contrastive learning for DEgree bias (GRADE), which applies different strategies to low- and high-degree nodes.
  arXiv  Detail & Related papers  (2022-10-06T15:58:25Z)
• Enhancing Graph Contrastive Learning with Node Similarity [4.60032347615771]
  Graph contrastive learning (GCL) is a representative framework for self-supervised learning. GCL learns node representations by contrasting semantically similar nodes (positive samples) and dissimilar nodes (negative samples) with anchor nodes. We propose an enhanced objective that contains all positive samples and no false-negative samples.
  arXiv  Detail & Related papers  (2022-08-13T22:49:20Z)
• Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data [52.771780951404565]
  Shift-Robust GNN (SR-GNN) is designed to account for distributional differences between biased training data and the graph's true inference distribution. We show that SR-GNN outperforms other GNN baselines by accuracy, eliminating at least (40%) of the negative effects introduced by biased training data.
  arXiv  Detail & Related papers  (2021-08-02T18:00:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.