HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views
Recent advancements in Graph Contrastive Learning (GCL) have demonstrated remarkable effectiveness in improving graph representations. However, relying on predefined augmentations (e.g., node dropping, edge perturbation, attribute masking) may result in the loss of task-relevant information and a lack of adaptability to diverse input data. Furthermore, the selection of negative samples remains rarely explored. In this paper, we introduce HyperGCL, a novel multimodal GCL framework from a hypergraph perspective. HyperGCL constructs three distinct hypergraph views by jointly utilizing the input graph's structure and attributes, enabling a comprehensive integration of multiple modalities in contrastive learning. A learnable adaptive topology augmentation technique enhances these views by preserving important relations and filtering out noise. View-specific encoders capture essential characteristics from each view, while a network-aware contrastive loss leverages the underlying topology to define positive and negative samples effectively. Extensive experiments on benchmark datasets demonstrate that HyperGCL achieves state-of-the-art node classification performance.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeContrastive LearningNode ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (we refer to it as HyperGCL). We focus on …
Contrastive LearningFairnessHypergraph Contrastive LearningRepresentation LearningAutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods em…
Contrastive LearningGraph Representation LearningRepresentation LearningSemantic Similarity+2GraphLearner: Graph Node Clustering with Fully Learnable Augmentation
Contrastive deep graph clustering (CDGC) leverages the power of contrastive learning to group nodes into different clusters. The quality of contrastive samples is crucial for achieving better performance, making augmenta…
AttributeClusteringContrastive LearningData Augmentation+3Mario: Multimodal Graph Reasoning with Large Language Models
Recent advances in large language models (LLMs) have opened new avenues for multimodal reasoning. Yet, most existing methods still rely on pretrained vision-language models (VLMs) to encode image-text pairs in isolation,…
Multimodal ReasoningContrastive LearningNode ClassificationLink PredictionPRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysis
Spatial multi-modal omics technology, highlighted by Nature Methods as an advanced biological technique in 2023, plays a critical role in resolving biological regulatory processes with spatial context. Recently, graph ne…
Contrastive Learning