GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.
Graph Contrastive Learning with Augmentations NeurIPS2020 GitHub - Shen-Lab/GraphCL: [NeurIPS 2020] "Graph Contrastive Learning with Augmentations" by Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen 摘要: 图结构数据的可推广、可迁移和鲁棒表示学习仍然是当前图神经网络...
Graph Contrastive modes 对比模式定义了将哪些嵌入拉到一起或将其推开。主流工作包括两种模式:全局-局部和局部-局部对比学习。 Global-local contrastive learning: DGI [Veličković et al., 2019] and MVGRL [Hassani and Khasahmadi, 2020] maximize the agreement between node- and graph-level representation...
InfoGCL: Information-Aware Graph Contrastive LearningNeurIPS 2021paper Graph Contrastive Learning with AugmentationsNeurIPS 2021paper Self-supervised Heterogeneous Graph Neural Network with Co-contrastive LearningKDD 2021papercode MoCL: Contrastive Learning on Molecular Graphs with Multi-level Domain KnowledgeKDD...
Graph contrastive learning, which aims to learn supervised signals from unlabeled graph data, has gained popularity as an effective method for learning node representations. However, most existing methods leverage random edge dropping to obtain the augmented view, which results in many isolated nodes ...
Keywords: micro-video recommendation, multi-modal, graph contrastive learning, self-supervised URLs:https://doi.org/10.1145/3477495.3532027, GitHub: None 摘要: a.本文的研究背景: 提出了一种新颖的多模态图对比学习方法,即MMGCL,以增强微视频推荐中的多模态表示学习。
2.2 Contrastive Learning 2.3 Graph Pre-Training 3 GRAPH CONTRASTIVE CODING (GCC) 3.1 The GNN Pre-Training Problem 3.2 GCC Pre-Training 3.3 GCC Fine-Tuning 4 EXPERIMENTS 4.1 Pre-Training 4.2 Downstream Task Evaluation 4.2.1 Node Classification ...
论文链接：https://ojs.aaai.org/index.php/AAAI/article/view/26168论文代码：https://github.com/shenxiaocam/NCLA 一、前言 近几年来，对比学习在 CV 和 NLP 领域的无监督表示学习任务上展现了显著的成果。受此启发，研究者们提出一系列图对比学习（Graph Contrastive Learning）方法 [2, 3]，通过结合图神经...
The code for this work is publicly available in the https://github.com/sun281210/SSGCL-LG . 展开 关键词: Heterogeneous graph neural networks Semi-supervised learning Contrastive learning Label information DOI: 10.1007/s10489-024-05703-8
AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators 论文链接: https://arxiv.org/abs/2109.10259 论文作者: Yin, Yihang and Wang, Qingzhong and Huang, Siyu and Xiong, Haoyi and Zhang, Xiang 代码链接: https://github.com/Somedaywilldo/AutoGCL ...