SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.03801 · NeurIPS · 2022

Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative

Tianlong Chen, Zhangyang Wang, Yuning You, Yang Shen, Jingrui He, Tianxin Wei

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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. N e=1 N e possibilities for one hyperedge on N vertices, versus N 2 for one edge in graphs. To date, the only way of contrasting is between the representations * Equal contribution. 36th Conference on Neural Information Processing Systems (NeurIPS 2022).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.03801")
get_code_for_paper("2210.03801")
have("2210.03801")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.03801.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.03801.svg)](https://syntology.ai/paper/2210.03801)

Connect an agent — have() is free.