ShiyinTan/CI-GCL - GitHub
This is the code for "Community-Invariant Graph Contrastive Learning" (CI-GCL). CI-GCL adopt learnable data augmentation with Community-Invariant constraint on both topology and …
• We propose a learnable CI-GCL framework to automat-ically maintain CI during graph augmentation by max-imizing spectral change loss, improving the model’s downstream …
Community-Invariant Graph Contrastive Learning
Based on our observations, we propose a community-invariant GCL framework to maintain graph community structure during learnable graph augmentation. By maximizing the spectral …
社区不变性增强图对比学习鲁棒性 - AI资讯 - 冷月清谈
2024年5月9日 · 本文介绍了一种名为“社区不变图对比学习”（ci-gcl）的新框架，旨在解决当前图对比学习（gcl）方法中存在的泛化能力有限和对噪声敏感的问题。 当前GCL方法主要依赖随机 …
Community-Invariant Graph Contrastive Learning - OpenReview
Based on our observations, we propose a community-invariant GCL framework to maintain graph community structure during learnable graph augmentation. By maximizing the spectral …
CI-GCL/README.md at main · ShiyinTan/CI-GCL - GitHub
2013年3月10日 · This is the code for "Community-Invariant Graph Contrastive Learning" (CI-GCL). CI-GCL adopt learnable data augmentation with Community-Invariant constraint on both …
Community-Invariant Graph Contrastive Learning - Papers With …
2024年5月2日 · Based on our observations, we propose a community-invariant GCL framework to maintain graph community structure during learnable graph augmentation. By maximizing the …
Community-Invariant Graph Contrastive Learning
2024年5月2日 · The key technical contribution of this research is the development of a community-invariant GCL (CI-GCL) framework for learnable graph augmentation. The …
CI-GCL/graph_classification.py at main - GitHub
from GCL.utils import (compute_infonce, cluster_get, CustomDataLoader, compute_cluster_constrain_loss,
论文笔记：WWW'21 Graph Contrastive Learning with Adaptive Augmentation
现有的大多数图对比学习（graph contrastive learning，GCL）方法首先对输入图进行随机扩充，得到两个视角的图，通过模型学习 图嵌入表示 来最大化两个视图中表示的一致性。在 …