Graph Self-Supervised Learning: A Surveyieeexplore.ieee.org/abstract/document/9770382 PDF: https://arxiv.org/pdf/2103.00111.pdfarxiv.org/pdf/2103.00111.pdf 1. 背景与概括 图的深度学习作为一个热门领域引起了广泛的研究兴趣,但是由于当前研究大多集中在半监督或者监督学习上,存在标签依赖严重、泛...
E. Buchatskaya, C. Doersch, B. Avila Pires, Z. Guo, M. Ghesh- laghi Azar, B. Piot, k. kavukcuoglu, R. Munos, and M. Valko, “Bootstrap your own latent - a new approach to self-supervised learning,” in NeurIPS, vol. 33, 2020, pp. 21 271–21 284. ...
【图深度自监督学习Philips S. Yu团队重磅新作】Graph Self-Supervised Learning: A Survey,程序员大本营,技术文章内容聚合第一站。
When does self-supervision help graph convolutional networks?. ICML, 2020. Self-supervised learning on graphs: Deep insights and new direction. arxiv preprint. Strategies for pre-training graph neural networks. ICLR, 2020. Graph-based neural network models with multiple self-supervised auxiliary tasks...
图上的深度学习最近引起了人们的极大兴趣。然而,大多数工作都集中在(半)监督学习上,导致存在标签依赖重、泛化能力差和鲁棒性弱等缺点。为了解决这些问题,自监督学习 (SSL) 通过精心设计的借口任务提取信息知识,而不依赖于手动标签,已成为图数据的一种有前途和趋势的学习范式。与计算机视觉和自然语言处理等其他领域中...
https://github.com/LirongWu/awesome-graph-self-supervised-learning 近些年来,图上的深度学习在各种任务上取得了显著的成功,而这种成功在很大程度上依赖于海量的、精心标注的数据。然而,精确的标注通常非常昂贵和耗时。为了解决这个问题,自监督学习(Self-supervised Learning,SSL)正在成为一种全新的范式,通过精心设计的...
A survey of graph neural networks in various learning paradigms: methods, applications, and challenges 2023, Artificial Intelligence Review A Comprehensive Survey on Deep Graph Representation Learning Methods 2023, Journal of Artificial Intelligence Research Multi-Task Self-Supervised Learning for Vehicle Cla...
Hierarchical Molecular Graph Self-Supervised Learning for property prediction Article Open access 17 February 2023 A knowledge-guided pre-training framework for improving molecular representation learning Article Open access 21 November 2023 Data availability All data used in this paper are publicly av...
本文的贡献主要… stephinwhite30 Graph Self-Supervised Learning: A Survey-对比学习方法 AI知其然发表于图神经网络... Graph Attention Network (GAT)论文分享 周明发表于水木学者 Robustness of deep learning models on graphs: A survey图深度学习鲁棒性综述 数据的小米...发表于图神经网络......
2.2 GraphDA for Low-Resource Graph Learning 2.2.1 Graph Self-Supervised Learning 收auto-encoder 启发,图生成建模方法对输入的图进行数据扩充,然后通过从扩充的图中恢复特征/结构信息来学习模型。对于输入图,节点或边的特征被掩盖然后目标是通过 GNN 根据未屏蔽的信息重新恢复屏蔽的特征/结构[18][19][20][21...