InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning

• URL: http://arxiv.org/abs/2505.06282v1
• Date: Wed, 07 May 2025 05:27:36 GMT
• Title: InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning
• Authors: Zixu Wang, Bingbing Xu, Yige Yuan, Huawei Shen, Xueqi Cheng,
• Abstract summary: Graph Contrastive Learning (GCL) continues to play a crucial role in the ongoing surge of research on graph foundation models or LLM as enhancer for graphs.<n>Traditional GCL uses augmentations to define self-supervised tasks, treating augmented pairs as positive samples and others as negative.<n>In this paper, we argue that GCL is essentially a Positive-Unlabeled (PU) learning problem, where the definition of self-supervised tasks should be semantically guided.
• Score: 60.61079931266331
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As an important graph pre-training method, Graph Contrastive Learning (GCL) continues to play a crucial role in the ongoing surge of research on graph foundation models or LLM as enhancer for graphs. Traditional GCL optimizes InfoNCE by using augmentations to define self-supervised tasks, treating augmented pairs as positive samples and others as negative. However, this leads to semantically similar pairs being classified as negative, causing significant sampling bias and limiting performance. In this paper, we argue that GCL is essentially a Positive-Unlabeled (PU) learning problem, where the definition of self-supervised tasks should be semantically guided, i.e., augmented samples with similar semantics are considered positive, while others, with unknown semantics, are treated as unlabeled. From this perspective, the key lies in how to extract semantic information. To achieve this, we propose IFL-GCL, using InfoNCE as a "free lunch" to extract semantic information. Specifically, We first prove that under InfoNCE, the representation similarity of node pairs aligns with the probability that the corresponding contrastive sample is positive. Then we redefine the maximum likelihood objective based on the corrected samples, leading to a new InfoNCE loss function. Extensive experiments on both the graph pretraining framework and LLM as an enhancer show significantly improvements of IFL-GCL in both IID and OOD scenarios, achieving up to a 9.05% improvement, validating the effectiveness of semantically guided. Code for IFL-GCL is publicly available at: https://github.com/Camel-Prince/IFL-GCL.

Related papers

• Unveiling Contrastive Learning's Capability of Neighborhood Aggregation for Collaborative Filtering [16.02820746003461]
  graph contrastive learning (GCL) has gradually become a dominant approach in recommender systems.<n>In this paper, we reveal via theoretical derivation that the gradient descent process of the CL objective is formally equivalent to graph convolution.<n>We propose a novel neighborhood aggregation objective to bring users closer to all interacted items while pushing them away from other positive pairs.
  arXiv  Detail & Related papers  (2025-04-14T11:22:41Z)
• 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)
• L^2CL: Embarrassingly Simple Layer-to-Layer Contrastive Learning for Graph Collaborative Filtering [33.165094795515785]
  Graph neural networks (GNNs) have recently emerged as an effective approach to model neighborhood signals in collaborative filtering. We propose L2CL, a principled Layer-to-Layer Contrastive Learning framework that contrasts representations from different layers. We find that L2CL, using only one-hop contrastive learning paradigm, is able to capture intrinsic semantic structures and improve the quality of node representation.
  arXiv  Detail & Related papers  (2024-07-19T12:45:21Z)
• Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning [71.9954600831939]
  Positive-Unlabeled (PU) learning is vital in many real-world scenarios, but its application to graph data remains under-explored. We unveil that a critical challenge for PU learning on graph lies on the edge heterophily, which directly violates the irreducibility assumption for Class-Prior Estimation. In response to this challenge, we introduce a new method, named Graph PU Learning with Label Propagation Loss (GPL)
  arXiv  Detail & Related papers  (2024-05-30T10:30:44Z)
• Decoupled Contrastive Learning for Long-Tailed Recognition [58.255966442426484]
  Supervised Contrastive Loss (SCL) is popular in visual representation learning. In the scenario of long-tailed recognition, where the number of samples in each class is imbalanced, treating two types of positive samples equally leads to the biased optimization for intra-category distance. We propose a patch-based self distillation to transfer knowledge from head to tail classes to relieve the under-representation of tail classes.
  arXiv  Detail & Related papers  (2024-03-10T09:46:28Z)
• Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning [34.566003077992384]
  We present a systematic study of various graph contrastive learning (GCL) methods. By uncovering how the implicit inductive bias of GNNs works in contrastive learning, we theoretically provide insights into the above intriguing properties of GCL. Rather than directly porting existing NN methods to GCL, we advocate for more attention toward the unique architecture of graph learning.
  arXiv  Detail & Related papers  (2023-11-05T15:54:17Z)
• HomoGCL: Rethinking Homophily in Graph Contrastive Learning [64.85392028383164]
  HomoGCL is a model-agnostic framework to expand the positive set using neighbor nodes with neighbor-specific significances. We show that HomoGCL yields multiple state-of-the-art results across six public datasets.
  arXiv  Detail & Related papers  (2023-06-16T04:06:52Z)
• Adversarial Learning Data Augmentation for Graph Contrastive Learning in Recommendation [56.10351068286499]
  We propose Learnable Data Augmentation for Graph Contrastive Learning (LDA-GCL) Our methods include data augmentation learning and graph contrastive learning, which follow the InfoMin and InfoMax principles, respectively. In implementation, our methods optimize the adversarial loss function to learn data augmentation and effective representations of users and items.
  arXiv  Detail & Related papers  (2023-02-05T06:55:51Z)
• Unifying Graph Contrastive Learning with Flexible Contextual Scopes [57.86762576319638]
  We present a self-supervised learning method termed Unifying Graph Contrastive Learning with Flexible Contextual Scopes (UGCL for short) Our algorithm builds flexible contextual representations with contextual scopes by controlling the power of an adjacency matrix. Based on representations from both local and contextual scopes, distL optimises a very simple contrastive loss function for graph representation learning.
  arXiv  Detail & Related papers  (2022-10-17T07:16:17Z)
• 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)

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.