Graph Contrastive Learning via Spectral Graph Alignment
Given augmented views of each input graph, contrastive learning methods (e.g., InfoNCE) optimize pairwise alignment of graph embeddings across views while providing no mechanism to control the global structure of the view specific graph-of-graphs built from these embeddings. We introduce SpecMatch-CL, a novel loss function that aligns the view specific graph-of-graphs by minimizing the difference between their normalized Laplacians. Theoretically, we show that under certain assumptions, the difference between normalized Laplacians provides an upper bound not only for the difference between the ideal Perfect Alignment contrastive loss and the current loss, but also for the Uniformly loss. Empirically, SpecMatch-CL establishes new state of the art on eight TU benchmarks under unsupervised learning and semi-supervised learning at low label rates, and yields consistent gains in transfer learning on PPI-306K and ZINC 2M datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningTransfer LearningSimilar Papers 제목 키워드 기반
Spectral Augmentations for Graph Contrastive Learning
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, t…
Contrastive LearningGraph EmbeddingGraph Representation LearningRepresentation LearningSpectral Feature Augmentation for Graph Contrastive Learning and Beyond
Although augmentations (e.g., perturbation of graph edges, image crops) boost the efficiency of Contrastive Learning (CL), feature level augmentation is another plausible, complementary yet not well researched strategy. …
Contrastive LearningASPECT: Node-Level Adaptive Spectral Fusion for Graph Contrastive Learning
Spectral graph contrastive learning often constructs low- and high-frequency views to capture complementary graph signals, but these views are commonly combined by graph-level or node-agnostic fusion rules. We show that …
Contrastive LearningGraph Contrastive Learning with Stable and Scalable Spectral Encoding
Graph contrastive learning (GCL) aims to learn representations by capturing the agreements between different graph views. Traditional GCL methods generate views in the spatial domain, but it has been recently discovered …
Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images
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