Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning

• URL: http://arxiv.org/abs/2405.19600v2
• Date: Wed, 04 Dec 2024 04:41:49 GMT
• Title: Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning
• Authors: Xiangru Jian, Xinjian Zhao, Wei Pang, Chaolong Ying, Yimu Wang, Yaoyao Xu, Tianshu Yu,
• Abstract summary: Methods grounded in seemingly conflicting assumptions regarding the spectral domain demonstrate notable enhancements in learning performance. This suggests that the computational overhead of sophisticated spectral augmentations may not justify their practical benefits. The proposed insights represent a significant leap forward in the field, potentially refining the understanding and implementation of graph self-supervised learning.
• Score: 10.803503272887173
• License:
• Abstract: The recent surge in contrast-based graph self-supervised learning has prominently featured an intensified exploration of spectral cues. Spectral augmentation, which involves modifying a graph's spectral properties such as eigenvalues or eigenvectors, is widely believed to enhance model performance. However, an intriguing paradox emerges, as methods grounded in seemingly conflicting assumptions regarding the spectral domain demonstrate notable enhancements in learning performance. Through extensive empirical studies, we find that simple edge perturbations - random edge dropping for node-level and random edge adding for graph-level self-supervised learning - consistently yield comparable or superior performance while being significantly more computationally efficient. This suggests that the computational overhead of sophisticated spectral augmentations may not justify their practical benefits. Our theoretical analysis of the InfoNCE loss bounds for shallow GNNs further supports this observation. The proposed insights represent a significant leap forward in the field, potentially refining the understanding and implementation of graph self-supervised learning.

Related papers

• AS-GCL: Asymmetric Spectral Augmentation on Graph Contrastive Learning [25.07818336162072]
  Graph Contrastive Learning (GCL) has emerged as the foremost approach for self-supervised learning on graph-structured data. We propose a novel paradigm called AS-GCL that incorporates asymmetric spectral augmentation for graph contrastive learning. Our method introduces significant enhancements to each of these components.
  arXiv  Detail & Related papers  (2025-02-19T08:22:57Z)
• Consistency of augmentation graph and network approximability in contrastive learning [3.053989095162017]
  We analyze the pointwise and spectral consistency of the augmentation graph Laplacian. We show that Laplacian converges to a weighted Laplace-Beltrami operator on the natural data manifold. These consistency results ensure that the graph Laplacian spectrum effectively captures the manifold geometry.
  arXiv  Detail & Related papers  (2025-02-06T18:55:51Z)
• Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification [67.35058947477631]
  We introduce Dual-Prism (DP) augmentation methods, including DP-Noise and DP-Mask, which retain essential graph properties while diversifying augmented graphs. Extensive experiments validate the efficiency of our approach, providing a new and promising direction for graph data augmentation.
  arXiv  Detail & Related papers  (2024-01-18T12:58:53Z)
• Spectral Augmentations for Graph Contrastive Learning [50.149996923976836]
  Contrastive learning has emerged as a premier method for learning representations with or without supervision. Recent studies have shown its utility in graph representation learning for pre-training. We propose a set of well-motivated graph transformation operations to provide a bank of candidates when constructing augmentations for a graph contrastive objective.
  arXiv  Detail & Related papers  (2023-02-06T16:26:29Z)
• Spectral Feature Augmentation for Graph Contrastive Learning and Beyond [64.78221638149276]
  We present a novel spectral feature argumentation for contrastive learning on graphs (and images) For each data view, we estimate a low-rank approximation per feature map and subtract that approximation from the map to obtain its complement. This is achieved by the proposed herein incomplete power iteration, a non-standard power regime which enjoys two valuable byproducts (under mere one or two iterations) Experiments on graph/image datasets show that our spectral feature augmentation outperforms baselines.
  arXiv  Detail & Related papers  (2022-12-02T08:48:11Z)
• Spectral Augmentation for Self-Supervised Learning on Graphs [43.19199994575821]
  Graph contrastive learning (GCL) aims to learn representations via instance discrimination. It relies on graph augmentation to reflect invariant patterns that are robust to small perturbations. Recent studies mainly perform topology augmentations in a uniformly random manner in the spatial domain. We develop spectral augmentation which guides topology augmentations by maximizing the spectral change.
  arXiv  Detail & Related papers  (2022-10-02T22:20:07Z)
• Robust Causal Graph Representation Learning against Confounding Effects [21.380907101361643]
  We propose Robust Causal Graph Representation Learning (RCGRL) to learn robust graph representations against confounding effects. RCGRL introduces an active approach to generate instrumental variables under unconditional moment restrictions, which empowers the graph representation learning model to eliminate confounders.
  arXiv  Detail & Related papers  (2022-08-18T01:31:25Z)
• Latent Augmentation For Better Graph Self-Supervised Learning [20.082614919182692]
  We argue that predictive models weaponed with latent augmentations and powerful decoder could achieve comparable or even better representation power than contrastive models. A novel graph decoder named Wiener Graph Deconvolutional Network is correspondingly designed to perform information reconstruction from augmented latent representations.
  arXiv  Detail & Related papers  (2022-06-26T17:41:59Z)
• Bayesian Graph Contrastive Learning [55.36652660268726]
  We propose a novel perspective of graph contrastive learning methods showing random augmentations leads to encoders. Our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector. We show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-15T01:45:32Z)
• Iterative Graph Self-Distillation [161.04351580382078]
  We propose a novel unsupervised graph learning paradigm called Iterative Graph Self-Distillation (IGSD) IGSD iteratively performs the teacher-student distillation with graph augmentations. We show that we achieve significant and consistent performance gain on various graph datasets in both unsupervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2020-10-23T18:37:06Z)
• Spectral Graph Attention Network with Fast Eigen-approximation [103.93113062682633]
  Spectral Graph Attention Network (SpGAT) learns representations for different frequency components regarding weighted filters and graph wavelets bases. Fast approximation variant SpGAT-Cheby is proposed to reduce the computational cost brought by the eigen-decomposition. We thoroughly evaluate the performance of SpGAT and SpGAT-Cheby in semi-supervised node classification tasks.
  arXiv  Detail & Related papers  (2020-03-16T21:49:34Z)

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.