其中,图对比学习(graph contrastive learning,GraphCL)具有很好的representation learning performance。 但是不幸的是,和图像数据上的对比学习不同,GraphCL的有效性很大程度上依赖于数据增强,对于每个数据集需要手动选择增强方法,或者通过经验方法or试错法,这可以归因于图数据的多样性。为了fill this重要的gap,本文提出了一...
为了解决上述问题,我们提出了一个全新的框架:Automated Graph Contrastive Learning (AutoGCL)。具体来说: AutoGCL使用了一系列learnable graph view generators orchestrated(策划,安排)by an auto augmentation,其中每个graph view generator学习一个输入图的概率分布。当AutoGCL中的graph view generators在生成每个contrasti...
[ICML 2021] "Graph Contrastive Learning Automated" by Yuning You, Tianlong Chen, Yang Shen, Zhangyang Wang; [WSDM 2022] "Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations" by Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen Topics automated-machine...
graph-neural-networkspretraininggraph-contrastive-learningmolecular-representation-learninggraph-self-supervised-learning UpdatedJun 13, 2022 Python FelixDJC/GRADATE Star51 Code Issues Pull requests An official source code for paper "Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with ...
2.2 AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators 原文链接:https://arxiv.org/abs/2109.10259 作者:Yin, Yihang and Wang, Qingzhong and Huang, Siyu and Xiong, Haoyi and Zhang, Xiang 代码:https://github.com/Somedaywilldo/AutoGCL ...
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 ...
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:...
Contrastive learningThe accurate identification of catalytic residues contributes to our understanding of enzyme functions in biological processes and pathways. The increasing number of protein sequences necessitates computational tools for the automated prediction of catalytic residues in enzymes. Here, we ...
Deep learning models can accurately predict molecular properties and help making the search for potential drug candidates faster and more efficient. Many existing methods are purely data driven, focusing on exploiting the intrinsic topology and construct
Learning Graph Embeddings for Compositional Zero-Shot LearningCVPR 2021paper Learning Graphs for Knowledge Transfer With Limited LabelsCVPR 2021paper SelfSAGCN: Self-Supervised Semantic Alignment for Graph Convolution NetworkCVPR 2021paper Graph Contrastive Learning AutomatedICML 2021papercode ...