paper-with-me

Papers

Spectral Augmentations for Graph Contrastive Learning

2023-02-06 · Amur Ghose, Yingxue Zhang, Jianye Hao, Mark Coates

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. Despite successes, the understanding of how to design effective graph augmentations that can capture structural properties common to many different types of downstream graphs remains incomplete. We propose a set of well-motivated graph transformation operations derived via graph spectral analysis to provide a bank of candidates when constructing augmentations for a graph contrastive objective, enabling contrastive learning to capture useful structural representation from pre-training graph datasets. We first present a spectral graph cropping augmentation that involves filtering nodes by applying thresholds to the eigenvalues of the leading Laplacian eigenvectors. Our second novel augmentation reorders the graph frequency components in a structural Laplacian-derived position graph embedding. Further, we introduce a method that leads to improved views of local subgraphs by performing alignment via global random walk embeddings. Our experimental results indicate consistent improvements in out-of-domain graph data transfer compared to state-of-the-art graph contrastive learning methods, shedding light on how to design a graph learner that is able to learn structural properties common to diverse graph types.

📄 PDF Abstract BibTeX arXiv:2302.02909

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningGraph EmbeddingGraph Representation LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Spectral Augmentation for Self-Supervised Learning on Graphs

2022-10-02 · Lu Lin, Jinghui Chen, Hongning Wang

Graph contrastive learning (GCL), as an emerging self-supervised learning technique on graphs, aims to learn representations via instance discrimination. Its performance heavily relies on graph augmentation to reflect in…

Contrastive LearningNode ClassificationRepresentation LearningSelf-Supervised Learning+1

Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum

2022-10-05 · Nian Liu, Xiao Wang, Deyu Bo, Chuan Shi 외

Graph Contrastive Learning (GCL), learning the node representations by augmenting graphs, has attracted considerable attentions. Despite the proliferation of various graph augmentation strategies, some fundamental questi…

Contrastive Learning

Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations

2025-06-25 · Lorenzo Bini, Stephane Marchand-Maillet

We present LaplaceGNN, a novel self-supervised graph learning framework that bypasses the need for negative sampling by leveraging spectral bootstrapping techniques. Our method integrates Laplacian-based signals into the…

Graph Learning

Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images

2024-03-04 · Jianhan Qi, Yuheng Jia, Hui Liu, Junhui Hou

Hyperspectral images (HSI) clustering is an important but challenging task. The state-of-the-art (SOTA) methods usually rely on superpixels, however, they do not fully utilize the spatial and spectral information in HSI …

ClusteringContrastive LearningSuperpixels

Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss

2021-06-08 · NeurIPS 2021 12 · Jeff Z. HaoChen, Colin Wei, Adrien Gaidon, Tengyu Ma

Recent works in self-supervised learning have advanced the state-of-the-art by relying on the contrastive learning paradigm, which learns representations by pushing positive pairs, or similar examples from the same class…

Contrastive LearningGeneralization BoundsSelf-Supervised Learning