Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative

TL;DR

This paper enhances hypergraph neural networks' generalizability in low-label settings by introducing both fabricated and generative augmentation methods within a contrastive learning framework, improving robustness and fairness.

Contribution

It proposes novel fabricated and generative hypergraph augmentation techniques, including a hypergraph generative model and an end-to-end learning pipeline, to improve contrastive learning effectiveness.

Findings

Hyperedge augmentation yields significant performance gains.

Generative augmentations better preserve higher-order information.

HyperGCL improves robustness and fairness in hypergraph learning.

Abstract

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 the following question: How to construct contrastive views for hypergraphs via augmentations? We provide the solutions in two folds. First, guided by domain knowledge, we fabricate two schemes to augment hyperedges with higher-order relations encoded, and adopt three vertex augmentation strategies from graph-structured data. Second, in search of more effective views in a data-driven manner, we for the first time propose a hypergraph generative model to generate 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.