The symposium brings together leading experts from universities, industry, and government to explore the state of the art and define a future roadmap in network science. This year's symposium will focus on these graph research topics: responsible AI, adversarial and representation learning on graphs. In order to provide an interactive environment and promote strong interaction among the attendees, the event will be limited to a small group of invited attendees.
In light of on-going developments with COVID-19, the symposium will take place virtually on Monday, May 16th - Tuesday May 17th, 2022.
Symposium Highlights
As part of the two-day technical program, topics of interest include:
- Social Influences,
- Fair, Unbiased, and Ethical Approaches
- Adversarial Graph Learning
- Analysis of Anomalous, Covert, and Hidden Communities
- Inference Under Noise and Uncertainty
- Modeling, Prediction, and Control
- Recent Advances in Machine Learning on Graphs (e.g., GNNs, Knowledge Graphs)
- Various Applications Including Bio, Cyber, Materials, Climate, Infrastructure, and Social Domains
Symposium Organizers
Chairs
Rajmonda Caceres | MIT Lincoln Laboratory
Danelle Shah | MIT Lincoln Laboratory
Technical Co-Chairs
Edoardo Airoldi | Temple & Harvard University
Edward Kao | MIT Lincoln Laboratory
Jason Matterer | MIT Lincoln Laboratory
Lin Li | MIT Lincoln Laboratory
Technical Committee
Nadya Bliss | Arizona State University
Robert Bond | MIT Lincoln Laboratory
Johan Ugander | Stanford University
Jordan Crouser | Smith College
David Martinez | MIT Lincoln Laboratory
Benjamin Miller | MIT Lincoln Laboratory
Alexander Volfovsky | Duke University
Christopher Long | U.S. Department of Defense
Ali Pinar | Sandia National Laboratories
Steven Smith | MIT Lincoln Laboratory
Heidi Perry | MIT Lincoln Laboratory