第一作者Mengru Chen,此文是google scholar上可查的唯一一篇论文。 通讯作者Chao Huang,在KDD,WSDM,SIGIR等会议中发表多篇异构图,推荐算法相关论文。 Chao Huang - Home (acm.org)dl.acm.org/profile/99660167114 KEYWORDS Recommendation, Self-Supervised Learning, Contrastive Learning, Graph Neural Network, ...
View Mask Mechanism.在生成网络模式表征z_i^{sc}和元路径表征z_i^{mp},本文呢设计了一种视图掩码机制,分别掩码网络模式和元路径视图获取更鲁棒的表示。 Collaboratively Contrastive Optimization.在获取表征后,使用投影头将表征隐射到损失空间: HECO++ Experiments...
论文阅读组会版#Heterogeneous Graph Contrastive Multi-view Learning(HGCML)82 0 2024-01-25 16:55:48 未经作者授权,禁止转载 您当前的浏览器不支持 HTML5 播放器 请更换浏览器再试试哦~2 3 3 分享 记录一下阅读的论文 知识 校园学习 研究生组会 论文 GNN 论文阅读 ...
graph contrastive learninggradient-based optimizationDrug repositioning, which involves identifying new therapeutic indications for approved drugs, is pivotal in accelerating drug discovery. Recently, to mitigate the effect of label sparsity on inferring potential drug鈥揹isease associations (DDAs), graph ...
Graph contrastive learning has been developed to learn discriminative node representations on homogeneous graphs. However, it is not clear how to augment the heterogeneous graphs without substantially altering the underlying semantics or how to design ap
【论文阅读】Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning,程序员大本营,技术文章内容聚合第一站。
Graph contrastive learning for recommendation with generative data augmentation Graph Neural Networks (GNNs) have been successfully adopted in recommender systems by virtue of the message-passing that implicitly captures collaborative ... X Li,Y Wang,Y Wang,... - 《Multimedia Systems》 被引量: 0发...
Heterogeneous Graph Contrastive learning via Intents behind Meta-paths for Recommendation - wangyu0627/IHGCL
Recommendation (HGCL)advances the recommender system with heterogeneous graph contrastive learning. HGCL integrates meta network with contrastive learning for adaptive augmentation to enable user-specific and item-specific knowledge transfer. It advances graph contrastive learning with customized cross-view ...
Learning cell-cell communication by contrastive heterogeneous graph learning We constructed cell-cell communication networks for each cell by leveraging heterogeneous graphs, where each graph represents a ligand-receptor interaction between a cell (or spot) and its spatial \(K\) nearest neighbors (Fig....