Homomorphism AutoEncoder – Learning Group Structured Representations from Observed Transitions
Metadata only
Date
2023Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
How can agents learn internal models that veridically represent interactions with the real world is a largely open question. As machine learning is moving towards representations containing not just observational but also interventional knowledge, we study this problem using tools from representation learning and group theory. We propose methods enabling an agent acting upon the world to learn internal representations of sensory information that are consistent with actions that modify it. We use an autoencoder equipped with a group representation acting on its latent space, trained using an equivariance-derived loss in order to enforce a suitable homomorphism property on the group representation. In contrast to existing work, our approach does not require prior knowledge of the group and does not restrict the set of actions the agent can perform. We motivate our method theoretically, and show empirically that it can learn a group representation of the actions, thereby capturing the structure of the set of transformations applied to the environment. We further show that this allows agents to predict the effect of sequences of future actions with improved accuracy. Show more
Publication status
publishedExternal links
Editor
Book title
Proceedings of the 40th International Conference on Machine LearningJournal / series
Proceedings of Machine Learning ResearchVolume
Pages / Article No.
Publisher
PMLREvent
Organisational unit
09479 - Grewe, Benjamin F. / Grewe, Benjamin F.
09664 - Schölkopf, Bernhard / Schölkopf, Bernhard
Funding
173721 - Temporal Information Integration in Neural Networks (SNF)
189251 - Ultra compact miniaturized microscopes to image meso-scale brain activity (SNF)
ETH-20 19-1 - A cross‐disciplinary, data‐driven approach to predict stress resilience from large‐scale behavioral, molecular and neural activity data (ETHZ)
More
Show all metadata
ETH Bibliography
yes
Altmetrics