Interactive Sequential Generative Models

Dennis Fassmeyer, Pascal Fassmeyer, Ulf Brefeld

Keywords: Generative Models and Autoencoders, Graph Neural Networks, Recurrent Networks, Sequential Models, Multi-Agent

Abstract: Understanding spatiotemporal relationships among several agents is of considerable relevance for many domains. Team sports represent a particularly interesting real-world proving ground since modeling interacting athletes requires capturing highly dynamic and complex agent-agent dependencies in addition to temporal components. However, existing generative methods in this field either entangle all latent factors into a single variable and are thus constrained in practical applicability, or they focus on uncovering interaction structures, which restricts their generative ability. To address this gap, we propose a framework for multiagent trajectories that augments sequential generative models with latent social structures. First, we derive a novel objective via approximate inference using a disentangled latent space that accurately describes the data generating process in such systems. Based on the proposed training criterion, we then present a model architecture that unifies insights from neural interaction inference and graph-structured variational recurrent neural networks for generating collective movements while allocating latent information. We validate our model on data from professional soccer and basketball. Our framework not only improves upon existing state-of-the-art approaches in forecasting trajectories, but also infers semantically meaningful representations that can be used in downstream tasks.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Generative models

TL;DR: We propose a novel framework for multiagent trajectories that augments sequential generative models with latent social structures.