2021 TRIPODS Winter School & Workshop on Graph Learning and Deep Learning

/ December 8, 2020/ Uncategorized

This event aims to bring together experts in machine learning, statistical inference and learning on graphs, and optimization to share basic principles, recent research results, and practical ideas, on the foundations of graph and deep learning.

A series of tutorials and hands-on sessions will be virtually presented over the first week, followed by a workshop covering recent results on the area,  with opportunities for discussion with peers and leaders in the field.

TRIPODS Winter School will be held January 6-8th, 2021, with workshops held January 13-15. Please register here

Confirmed Speakers


Edo Airoldi
Associate Professor
Harvard University

Taco Cohen
Researcher
Qualcomm

William Hamilton
Assistant Professor
McGill University

Stefanie Jegelka
Associate Professor
MIT
George Karypis
Senior Principal Scientist
Amazon Web Services

Eric Kolaczyk
Professor
Boston University

Gitta Kutyniok
Professor
LMU Munich

Elizaveta Levina
Professor
University of Michigan

Jason Lee
Assistant Professor
Princeton University

Jure Leskovec
Associate Professor
Stanford University

Guido Montúfar
Assistant Professor
UCLA

Hanie Sedghi
Research Scientist
Google Brain

Alex Smola
Director
Amazon Web Services

Matus Telgarsky
Assistant Professor
UIUC

Agenda

Times shown in EST

TimeSessionSpeakerPresentation

Wednesday January 6

11:45AMRene VidalWelcome & Introduction
12:00PMTutorialMatus TelgarskyGeneralization in Deep Learning
1:00PMTutorialJason LeeOptimization Beyond Linearization in Neural Networks
2:00PMBreak
2:30PMTutorialEric KolaczykStatistical Analysis on Network Data
3:30PMTutorialWilliam Hamilton Representation Learning on Graphs
4:30PMAlex Smola Practicum Warmup

Thursday January 7

12:00PM-5:00PMPracticumAlex SmolaDNNs Practicum

Friday January 8

12:00PMTutorialStefanie Jegelka Graph Neural Networks
1:00PMTutorialGitta KutyniokThe Expressive Power of Deep Learning
2:00PMBreak
2:30PMTutorialEdo AiroldiApplications of Graph Learning
3:30PMTutorialTaco CohenEquivariant Networks

Wednesday January 13

12:00PMWorkshopMatus TelgarskyImproved analyses and rates of gradient descent’s implicit bias
12:45PMWorkshopJure LeskovecReasoning Over Knowledge Graphs using Embeddings
1:30PMWorkshopJason LeeProvable representation learning in deep learning
2:15PMBreak
2:45PMWorkshopStefanie JegelkaLearning and Generalization in Graph Neural Networks
3:30PMWorkshopHanie SedghiWhat is being transferred in transfer learning?
4:15PMWorkshopEric KolaczykWhy Aren’t Network Summary Statistics Accompanied by Uncertainty Statements?

Thursday January 14

12:00PM-5:00PMPracticumGeorge KarypisGraph NNs Practicum

Friday January 15

12:00PMWorkshopEdo AiroldiLeveraging probabilistic models for designing causal analyses resilient to model failure
12:45PMBreak
1:30PMWorkshopGuido MontufarImplicit bias of gradient descent for mean squared error regression with wide neural networks
2:15PMBreak
2:45PMWorkshopElizaveta LevinaHierarchical community detection by recursive partitioning
3:30PMWorkshopWilliam HamiltonLearning Dynamic Belief Graphs to Generalize on Text-Based Games
4:15PMPanelGeorge Karypis, Eric Kolaczyk & Elizaveta LevinaFuture Directions in Graph Learning & Deep Learning

Share this Post