Timezone: »

Learning and Reasoning with Graph-Structured Representations
Ethan Fetaya · Zhiting Hu · Thomas Kipf · Yujia Li · Xiaodan Liang · Renjie Liao · Raquel Urtasun · Hao Wang · Max Welling · Eric Xing · Richard Zemel

Sat Jun 15 08:30 AM -- 06:00 PM (PDT) @ Grand Ballroom B
Event URL: https://graphreason.github.io/ »

Graph-structured representations are widely used as a natural and powerful way to encode information such as relations between objects or entities, interactions between online users (e.g., in social networks), 3D meshes in computer graphics, multi-agent environments, as well as molecular structures, to name a few. Learning and reasoning with graph-structured representations is gaining increasing interest in both academia and industry, due to its fundamental advantages over more traditional unstructured methods in supporting interpretability, causality, transferability, etc. Recently, there is a surge of new techniques in the context of deep learning, such as graph neural networks, for learning graph representations and performing reasoning and prediction, which have achieved impressive progress. However, it can still be a long way to go to obtain satisfactory results in long-range multi-step reasoning, scalable learning with very large graphs, flexible modeling of graphs in combination with other dimensions such as temporal variation and other modalities such as language and vision. New advances in theoretical foundations, models and algorithms, as well as empirical discoveries and applications are therefore all highly desirable.

The aims of this workshop are to bring together researchers to dive deeply into some of the most promising methods which are under active exploration today, discuss how we can design new and better benchmarks, identify impactful application domains, encourage discussion and foster collaboration. The workshop will feature speakers, panelists, and poster presenters from machine perception, natural language processing, multi-agent behavior and communication, meta-learning, planning, and reinforcement learning, covering approaches which include (but are not limited to):

-Deep learning methods on graphs/manifolds/relational data (e.g., graph neural networks)
-Deep generative models of graphs (e.g., for drug design)
-Unsupervised graph/manifold/relational embedding methods (e.g., hyperbolic embeddings)
-Optimization methods for graphs/manifolds/relational data
-Relational or object-level reasoning in machine perception
-Relational/structured inductive biases for reinforcement learning, modeling multi-agent behavior and communication
-Neural-symbolic integration
-Theoretical analysis of capacity/generalization of deep learning models for graphs/manifolds/ relational data
-Benchmark datasets and evaluation metrics

Sat 8:45 a.m. - 9:00 a.m.
Opening remarks (NA)
Sat 9:00 a.m. - 9:30 a.m.
William L. Hamilton, McGill University (Invited talk)
Will Hamilton
Sat 9:30 a.m. - 9:45 a.m.
Evolutionary Representation Learning for Dynamic Graphs; Aynaz Taheri and Tanya Berger-Wolf (Contributed talk)
aynaz taheri
Sat 9:45 a.m. - 10:00 a.m.
Poster spotlights #1 (Spotlight talks)
Siheng Chen, Vedran Hadziosmanovic, Adín Ramírez Rivera
Sat 10:00 a.m. - 11:00 a.m.
Morning poster session and coffee break (Posters)
Sat 11:00 a.m. - 11:30 a.m.
Marwin Segler, Benevolent AI (Invited talk)
Marwin Segler
Sat 11:30 a.m. - 12:00 p.m.
Yaron Lipman, Weizmann Institute of Science (Invited talk)
Yaron Lipman
Sat 12:00 p.m. - 12:15 p.m.
PAN: Path Integral Based Convolution for Deep Graph Neural Networks; Zheng Ma, Ming Li and Yu Guang Wang (Contributed talk)
Zheng Ma
Sat 12:15 p.m. - 12:30 p.m.
Poster spotlights #2 (Spotlight talks)
Leonardo Teixeira, Federico Baldassarre
Sat 12:30 p.m. - 2:00 p.m.
Lunch break (Break)
Sat 2:00 p.m. - 2:30 p.m.
Alex Polozov, Microsoft Research (Invited talk)
Alex Polozov
Sat 2:30 p.m. - 3:00 p.m.
Sanja Fidler, University of Toronto (Invited talk)
Sanja Fidler
Sat 3:00 p.m. - 3:15 p.m.
On Graph Classification Networks, Datasets and Baselines; Enxhell Luzhnica, Ben Day and Pietro Lió (Contributed talk)
Sat 3:15 p.m. - 3:30 p.m.
Poster spotlights #3 (Spotlight talks)
Sumit Kumar, Nicola De Cao, Benson Chen
Sat 3:30 p.m. - 4:30 p.m.
Afternoon poster session and coffee break (Posters)
Ming Tu, Xinhua Zhang, Lee Chen
Sat 4:30 p.m. - 5:00 p.m.
Caroline Uhler, MIT (Invited talk)
Caroline Uhler
Sat 5:00 p.m. - 5:30 p.m.
Alexander Schwing, University of Illinois at Urbana-Champaign (Invited talk)
Alex Schwing

Author Information

Ethan Fetaya (University of Toronto)
Zhiting Hu Hu (Carnegie Mellon University)
Thomas Kipf (University of Amsterdam)
Yujia Li (DeepMind)
Xiaodan Liang (Sun Yat-sen University)
Renjie Liao (University of Toronto)
Raquel Urtasun (University of Toronto)
Hao Wang (MIT)
Max Welling (University of Amsterdam)

Prof. Dr. Max Welling is a research chair in Machine Learning at the University of Amsterdam and a VP Technologies at Qualcomm. He has a secondary appointment as a senior fellow at the Canadian Institute for Advanced Research (CIFAR). He is co-founder of “Scyfer BV” a university spin-off in deep learning which got acquired by Qualcomm in summer 2017. In the past he held postdoctoral positions at Caltech (’98-’00), UCL (’00-’01) and the U. Toronto (’01-’03). He received his PhD in ’98 under supervision of Nobel laureate Prof. G. 't Hooft. Max Welling has served as associate editor in chief of IEEE TPAMI from 2011-2015 (impact factor 4.8). He serves on the board of the NIPS foundation since 2015 (the largest conference in machine learning) and has been program chair and general chair of NIPS in 2013 and 2014 respectively. He was also program chair of AISTATS in 2009 and ECCV in 2016 and general chair of MIDL 2018. He has served on the editorial boards of JMLR and JML and was an associate editor for Neurocomputing, JCGS and TPAMI. He received multiple grants from Google, Facebook, Yahoo, NSF, NIH, NWO and ONR-MURI among which an NSF career grant in 2005. He is recipient of the ECCV Koenderink Prize in 2010. Welling is in the board of the Data Science Research Center in Amsterdam, he directs the Amsterdam Machine Learning Lab (AMLAB), and co-directs the Qualcomm-UvA deep learning lab (QUVA) and the Bosch-UvA Deep Learning lab (DELTA). Max Welling has over 200 scientific publications in machine learning, computer vision, statistics and physics.

Eric Xing (Petuum Inc. and CMU)
Richard Zemel (Vector Institute)

More from the Same Authors