TY - GEN
T1 - Graph minimally-supervised learning
AU - Ding, Kaize
AU - Li, Jundong
AU - Chawla, Nitesh
AU - Liu, Huan
N1 - Funding Information: Jundong Li is an Assistant Professor in the Department of Electrical and Computer Engineering at University of Virginia. His research interests are in data mining and machine learning, with a particular focus on graph mining and causality learning. His work on feature selection and graph representation learning are among the most cited articles in ACM CSUR, WSDM, SDM, and CIKM within the past five years according to Google Scholar Metrics. He was selected for the AAAI 2021 New Faculty Highlights program. More details can be found at: http://www.ece.virginia.edu/˜jl6qk/. Nitesh V. Chawla is the Frank M. Freimann Professor of Computer Science and Engineering at the University of Notre Dame. His research is making fundamental advances in artificial intelligence, data science, and network science, and is motivated by the question of how technology can advance the common good through interdisciplinary research. He is the recipient of National Academy of Engineers New Faculty Fellowship. He also is the recipient of the 2015 IEEE CIS Outstanding Early Career Award; the IBM Watson Faculty Award; the IBM Big Data and Analytics Faculty Award; the National Academy of Engineering New Faculty Fellowship; and the 1st Source Bank Technology Commercialization Award. More details can be found at: https://niteshchawla.nd.edu/. Funding Information: This work is partially supported by Office of Naval Research (ONR) N00014-21-1-4002 and Army Research Office (ARO) W911NF2110030. Publisher Copyright: © 2022 ACM.
PY - 2022/2/11
Y1 - 2022/2/11
N2 - Graphs are widely used for abstracting complex systems of interacting objects, such as social networks, knowledge graphs, and traffic networks, as well as for modeling molecules, manifolds, and source code. To model such graph-structured data, graph learning, in particular deep graph learning with graph neural networks, has drawn much attention in both academic and industrial communities lately. Prevailing graph learning methods usually rely on learning from "big'' data, requiring a large amount of labeled data for model training. However, it is common that graphs are associated with "small'' labeled data as data annotation and labeling on graphs is always time and resource-consuming. Therefore, it is imperative to investigate graph learning with minimal human supervision for the low-resource settings where limited or even no labeled data is available. In this tutorial, we will focus on the state-of-the-art techniques of Graph Minimally-supervised Learning, in particular a series of weakly-supervised learning, few-shot learning, and self-supervised learning methods on graph-structured data as well as their real-world applications. The objectives of this tutorial are to: (1) formally categorize the problems in graph minimally-supervised learning and discuss the challenges under different learning scenarios; (2) comprehensively review the existing and recent advances of graph minimally-supervised learning; and (3) elucidate open questions and future research directions. 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.
AB - Graphs are widely used for abstracting complex systems of interacting objects, such as social networks, knowledge graphs, and traffic networks, as well as for modeling molecules, manifolds, and source code. To model such graph-structured data, graph learning, in particular deep graph learning with graph neural networks, has drawn much attention in both academic and industrial communities lately. Prevailing graph learning methods usually rely on learning from "big'' data, requiring a large amount of labeled data for model training. However, it is common that graphs are associated with "small'' labeled data as data annotation and labeling on graphs is always time and resource-consuming. Therefore, it is imperative to investigate graph learning with minimal human supervision for the low-resource settings where limited or even no labeled data is available. In this tutorial, we will focus on the state-of-the-art techniques of Graph Minimally-supervised Learning, in particular a series of weakly-supervised learning, few-shot learning, and self-supervised learning methods on graph-structured data as well as their real-world applications. The objectives of this tutorial are to: (1) formally categorize the problems in graph minimally-supervised learning and discuss the challenges under different learning scenarios; (2) comprehensively review the existing and recent advances of graph minimally-supervised learning; and (3) elucidate open questions and future research directions. 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.
KW - Few-shot learning
KW - Graph neural networks
KW - Self-supervised learning
KW - Weakly-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85125776501&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125776501&partnerID=8YFLogxK
U2 - 10.1145/3488560.3501390
DO - 10.1145/3488560.3501390
M3 - Conference contribution
T3 - WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining
SP - 1620
EP - 1622
BT - WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining
PB - Association for Computing Machinery, Inc
T2 - 15th ACM International Conference on Web Search and Data Mining, WSDM 2022
Y2 - 21 February 2022 through 25 February 2022
ER -