# Improved Structural Discovery and Representation Learning of Multi-Agent Data

arXiv: https://arxiv.org/abs/1912.13107 · HTML: https://mlsanity.com/paper/1912.13107/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2019.

## Built on by (most cited first, 1 of 1)

- [Data-driven Analysis for Understanding Team Sports Behaviors](https://mlsanity.com/paper/2102.07545/) (2021)

## Abstract (arXiv)

Central to all machine learning algorithms is data representation. For multi-agent systems, selecting a representation which adequately captures the interactions among agents is challenging due to the latent group structure which tends to vary depending on context. However, in multi-agent systems with strong group structure, we can simultaneously learn this structure and map a set of agents to a consistently ordered representation for further learning. In this paper, we present a dynamic alignment method which provides a robust ordering of structured multi-agent data enabling representation learning to occur in a fraction of the time of previous methods. We demonstrate the value of this approach using a large amount of soccer tracking data from a professional league.