paper-with-me

Papers

Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative

2022-10-07 · Tianxin Wei, Yuning You, Tianlong Chen, Yang shen, Jingrui He, Zhangyang Wang

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.

📄 PDF Abstract BibTeX arXiv:2210.03801

Code (1)

weitianxin/HyperGCL 공식 구현 pytorch

Tasks

Contrastive LearningFairnessHypergraph Contrastive LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

HiTeC: Hierarchical Contrastive Learning on Text-Attributed Hypergraph with Semantic-Aware Augmentation

2025-08-05 · Mengting Pan, Fan Li, Chen Chen, Xiaoyang Wang 외 arxiv

Contrastive learning (CL) has become a dominant paradigm for self-supervised hypergraph learning, enabling effective training without costly labels. However, node entities in real-world hypergraphs are often associated w…

Self-Supervised LearningRepresentation LearningContrastive Learning

Time Series Contrastive Learning with Information-Aware Augmentations

2023-03-21 · Dongsheng Luo, Wei Cheng, Yingheng Wang, Dongkuan Xu 외

Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key…

Contrastive LearningOpen-Ended Question AnsweringRepresentation LearningTime Series

Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations

2022-01-04 · Yuning You, Tianlong Chen, Zhangyang Wang, Yang shen

Self-supervision is recently surging at its new frontier of graph learning. It facilitates graph representations beneficial to downstream tasks; but its success could hinge on domain knowledge for handcraft or the often …

Contrastive LearningGraph Learning

Information-Aware Time Series Meta-Contrastive Learning

2021-09-29 · Dongsheng Luo, Wei Cheng, Yingheng Wang, Dongkuan Xu 외

Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key…

Contrastive LearningMeta-LearningOpen-Ended Question AnsweringRepresentation Learning+2

HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views

2025-02-18 · Khaled Mohammed Saifuddin, Jonathan Shihao Ji, Esra Akbas

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,…

AttributeContrastive LearningNode Classification