论文标题:Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive论文作者:Lirong Wu, Haitao Lin, Cheng Tan,Zhangyang Gao, and Stan.Z.Li论文来源:2022, ArXiv论文地址:download 1介绍图深度学习的发展是由于能够捕获图的结构和节点/边特征。
论文信息 论文标题:Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive论文作者:Lirong Wu, Haitao Lin, Cheng Tan,Zhangyang Gao, and Stan.Z.Li论
Tang, “Self-supervised learning on graphs: Deep insights and new direction,” arXiv preprint arXiv:2006.10141, 2020. [10] Z. Hu, C. Fan, T. Chen, K.-W. Chang, and Y. Sun, “Pretraining graph neural networks for generic structural feature extraction,” arXiv preprint arXiv:1905.13728...
[84] S. Thakoor, C. Tallec, M. G. Azar, R. Munos, P. Velicˇkovic ́, and M. Valko, “Bootstrapped representation learning on graphs,” in ICLR Workshop, 2021. [85] Z. T. Kefato and S. Girdzijauskas, “Self-supervised graphneural networkswithout explicit negative sampling,” ...
27 p. HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation 18 p. Dynamic magnetic response in ABA type trilayered systems and compensation phenomenon 12 p. A Large-Scale Study on Video Action Dataset Condensation 关于...
Self-supervised learning on graphs: Deep insights and new direction. arxiv preprint. Classification-based Approach(C-APP) C-APP 依赖伪标签进行快速的模型训练。 Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes. AAAI, 2020. ...
To keep the diversity of information during aggregation, it is mandatory to use the most appropriate different aggregators for specific graphs or subgraphs. However, when and what aggregators to be used remain mostly unsolved. To tackle this problem, we introduce a general contrastive learning ...
The success of deep learning notoriously requires larger amounts of costly annotated data. This has led to the development of self-supervised learning (SSL) that aims to alleviate this limitation by creating domain specific pretext tasks on unlabeled data. Simultaneously, there are increasing interests...
The artificial intelligence (AI) community has recently made tremendous progress in developing self-supervised learning (SSL) algorithms that can learn high-quality data representations from massive amounts of unlabeled data. These methods brought great
Basic Pretext Tasks on Graphs(基本代理任务) Structure Information(结构信息) 在图中提取自监督信息的第一自然选择是数据背后的固有结构. 这是因为与图像和文本不同. 在图中, 我们的数据实例是相关的(即节点链接在一起). 因此, 一个主要方向是基于未标记节点的局部结构信息, 或者它们如何与图的其余部分相关联...