srch

18.01.2022 · Self-Supervised Learning For Graphs. By Paridhi Maheshwari, Jian Vora, Sharmila Reddy Nangi as part of the Stanford CS 224W course project.

This tutorial introduces major topics within minimally-supervised learning and offers a guide to a new frontier of graph learning. We believe this tutorial is beneficial to researchers and practitioners, allowing them to collaborate on graph learning. Publication series Name

Graph-based representations have been used with considerable success in computer vision in the abstraction and recognition of object shape and scene structure.

Graph regression can be considered a graph-level task. In a self-supervised learning setting, very few amounts of graphs with their known ...

Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for ...

Difficulties of Graph Data: Size and Structure. Applying neural networks and other machine- ...

Graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks.

networks [10,11]. Therefore, the research of self-supervised learning on graphs is still at the initial stage and more systematical and dedicated efforts are pressingly needed. In this paper, we embrace the challenges and opportunities to study self-supervised learning in graph neural networks for node classification with two major goals.

understandings on self-supervised learning on graphs. Specifically, there are a variety of potential pretext tasks for graphs; hence it is important to gain insights on when and why SSL works for GNNs and which strategy can better integrate SSL for GNNs. Second, we target on inspiring new directions of SSL on graphs according to our understandings.

Ding, K, Li, J, Chawla, N & Liu, H 2022, Graph minimally-supervised learning. in WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining. WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining, Association for Computing Machinery, Inc, pp. 1620-1622, 15th ACM International Conference …

Graph Random Neural Network for Semi-Supervised Learning on Graphs, semi-supervised node classification, simplifying graph convolution, data augmentation.

Graph Data and Definitions

09.01.2022 · Self-Supervised Learning Strategies Using Graph Data. As of now, we have discussed why we should use graph data with SSL and what kind of neural network can help us with graph data. To obtain a good result from self-supervised learning with graph data, we are required to have a strong strategy to work.

Abstract. We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, ...

We've seen that there are 4 major types of machine learning tasks on graphs: node classification, link prediction, learning over the whole graph ...