Timezone: »

Inferring Relational Potentials in Interacting Systems
Armand Comas · Yilun Du · Christian Fernandez Lopez · Sandesh Ghimire · Mario Sznaier · Josh Tenenbaum · Octavia Camps

Thu Jul 27 06:24 PM -- 06:32 PM (PDT) @ Meeting Room 316 A-C

Systems consisting of interacting agents are prevalent in the world, ranging from dynamical systems in physics to complex biological networks. To build systems which can interact robustly in the real world, it is thus important to be able to infer the precise interactions governing such systems. Existing approaches typically discover such interactions by explicitly modeling the feed-forward dynamics of the trajectories. In this work, we propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions that enables greater flexibility in trajectory modeling: it discovers a set of relational potentials, represented as energy functions, which when minimized reconstruct the original trajectory. NIIP assigns low energy to the subset of trajectories which respect the relational constraints observed. We illustrate that with these representations NIIP displays unique capabilities in test-time. First, it allows trajectory manipulation, such as interchanging interaction types across separately trained models, as well as trajectory forecasting. Additionally, it allows adding external hand-crafted potentials at test-time. Finally, NIIP enables the detection of out-of-distribution samples and anomalies without explicit training.

Author Information

Armand Comas (Northeastern University)
Yilun Du (MIT)
Christian Fernandez Lopez (Universidad Polit├ęcnica de Cataluna)
Sandesh Ghimire (QualComm)

Researcher working on ML, Computer Vision, Generative Models Personal Website: https://sandeshgh.com/ Twitter: https://twitter.com/drsandeshgh

Mario Sznaier (Northeastern University)
Josh Tenenbaum (MIT)

Joshua Brett Tenenbaum is Professor of Cognitive Science and Computation at the Massachusetts Institute of Technology. He is known for contributions to mathematical psychology and Bayesian cognitive science. He previously taught at Stanford University, where he was the Wasow Visiting Fellow from October 2010 to January 2011. Tenenbaum received his undergraduate degree in physics from Yale University in 1993, and his Ph.D. from MIT in 1999. His work primarily focuses on analyzing probabilistic inference as the engine of human cognition and as a means to develop machine learning.

Octavia Camps (Northeastern University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors