Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
复制标题
DOI：
10.48550/arxiv.2210.03801
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Tianxin Wei;Yuning You;Tianlong Chen;Yang Shen;Jingrui He;Zhangyang Wang
中科院分区：
文献类型：
--
作者：
Tianxin Wei;Yuning You;Tianlong Chen;Yang Shen;Jingrui He;Zhangyang Wang
本文旨在通过应用图像/图形的对比学习方法（我们称之为HyperGCL）来提高超图神经网络在低标签区域的泛化能力。我们主要研究了以下问题：如何通过增广构造超图的对比视图？我们提供了两个折叠的解决方案。首先，在领域知识的指导下，我们提出了两种方案来增加超边与高阶关系编码，并采用三个顶点增加策略，从图结构的数据。其次，为了以数据驱动的方式寻找更有效的视图，我们首次提出了一个超图生成模型来生成增强视图，然后提出了一个端到端的可微分管道来共同学习超图增强和模型参数。我们的技术创新体现在设计超图的制造和生成增强。实验结果包括：（i）在HyperGCL中的构造扩充中，扩充超边提供了最多的数值增益，这意味着结构中的高阶信息通常更下游相关;（ii）生成扩充在保留高阶信息方面做得更好，以进一步有利于推广;（iii）HyperGCL还提高了超图表示学习的鲁棒性和公平性。代码发布于https://github.com/weitianxin/HyperGCL。
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.