Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative

2022/10/07 by Tianxin Wei, Wei, Tianxin, Yuning You +9 · 7 citations
Computer Science · #Multimodal Machine Learning Applications #Advanced Graph Neural Networks #Topic Modeling

paper · doi:10.48550/arxiv.2210.03801

Abstract

augmented views, and then an end-to-end differentiable pipeline to jointly learn hypergraph augmentations and model parameters. Our technical innovations are reflected in designing both fabricated and generative augmentations of hypergraphs. The experimental findings include: (i) Among fabricated augmentations in HyperGCL, augmenting hyperedges provides the most numerical gains, implying that higher-order information in structures is usually more downstream-relevant; (ii) Generative augmentations do better in preserving higher-order information to further benefit generalizability; (iii) HyperGCL also boosts robustness and fairness in hypergraph representation learning. Codes are released at https://github.com/weitianxin/HyperGCL.

Cited by

• Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs
• Graph4MM: Weaving Multimodal Learning with Structural Information
• Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
• Graph Concept Bottleneck Models
• DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning
• Effective and Efficient Attributed Hypergraph Embedding on Nodes and Hyperedges
• HiTeC: Hierarchical Contrastive Learning on Text-Attributed Hypergraph with Semantic-Aware Augmentation

Related

• HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views
• CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network
• HiTeC: Hierarchical Contrastive Learning on Text-Attributed Hypergraph with Semantic-Aware Augmentation
• Closer through commonality: Enhancing hypergraph contrastive learning with shared groups
• MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning