The call for papers is now open.

We invite submissions contributing novel research incorporating symmetry, geometry, or topology into the design of artificial neural networks, the analysis of neural data, or theories of neural computation. We welcome contributions in the intersection of geometric and topological deep learning, computational and theoretical neuroscience, geometric statistics, and topological data analysis.

The following themes are particularly relevant:

• Theory and methods for learning invariant and equivariant representations

• Statistical learning theory in the context of topology, geometry, and symmetry

• Representational geometry in neural data

• Learning and leveraging group structure in data 

• Equivariant world models for robotics

• Topological deep learning and topological data analysis

• Geometric structure in language

• Geometric and topological analysis of generative models

• Symmetries, dynamical systems, and learning

We hope to see both theoretical contributions and applied results in domains including vision, motor control, navigation, and language as well as the use of diverse mathematical objects such as quotient spaces, fiber bundles, Lie groups, Riemannian manifolds, graphs, topological domains,  and group representations. We are also interested in submissions contributing benchmark datasets or software. This list is intended to provide guidance, but it is far from exhaustive. If you are unsure whether your work is within scope of this workshop, please reach out to the organizers.

There are two tracks for submission to NeurReps. Submissions to both tracks will be featured during the workshop's poster session, and a subset of all submissions will be selected for spotlight talks.

1. Proceedings Track 

NeurReps Proceedings papers may be up to 9 pages long, excluding references and appendices. Accepted papers will be published in the Proceedings of Machine Learning Research (PMLR) Volume on Symmetry and Geometry in Neural Representations. This track is appropriate for self-contained research papers with a high degree of development. 

2. Extended Abstract Track

Extended abstracts may be up to 4 pages long, excluding references and appendices. This track creates space for contributions such as early-stage results, insightful negative findings, opinion pieces, or novel datasets. Extended abstracts will not be included in the PMLR volume, but authors may post to arXiv under the NeurReps index.

Dual Submission Policy

Papers in the Proceedings Track will be archivally published in PMLR. Thus, submissions containing content that has been published or submitted elsewhere must include at least 30% new, unpublished/unsubmitted material. Likewise, to publish a NeurReps paper in another venue down the line, authors must add at least 30% new material. There are no restrictions on Extended Abstract submissions. 

Review Process

Reviews are double-blind and conducted through OpenReview. All submissions will receive a minimum of three reviews.

Dates and Deadlines

Submission: October 4, 2023 11:59 PM AoE
Author Notification: October 20, 2023 11:59 PM AoE

Submission Instructions

All submissions must use the NeurReps 2023 LaTeX style files: [Overleaf template],  [.zip]. 

Authors should select the proceedings or extended abstract format in the pmlr-sample.tex file. 

All submissions should be submitted to OpenReview using the link below.