Call For Papers

Neural models, whether in biological or artificial systems, tend to learn similar representations when exposed to similar stimuli. This phenomenon has been observed in various scenarios, e.g. when different individuals are exposed to the same stimulus or in different initializations of the same neural architecture. Similar representations occur in settings where data is acquired from multiple modalities (e.g. text and image representations of the same entity) or when observations in a single modality are acquired under different conditions (e.g. in multiview learning). The emergence of these similar representations has sparked interest in the fields of Neuroscience, Artificial Intelligence, and Cognitive Science. This workshop aims to get a unified view on this topic and facilitate the exchange of ideas and insights across these fields, focusing on three key points:

When: Understanding the patterns by which these similarities emerge in different neural models and developing methods to measure them.

Why: Investigating the underlying causes of these similarities in neural representations, considering both artificial and biological models.

What for: Exploring and showcasing applications in modular deep learning, including model merging, reuse, stitching, efficient strategies for fine-tuning, and knowledge transfer between models and across modalities.

Topics

A non exhaustive list of the preferred topics include:

  • Model merging, stitching and reuse
  • Representational alignment
  • Identifiability in neural models
  • Symmetry and equivariance in NNs
  • Learning dynamics
  • Disentangled representations
  • Multiview representation learning
  • Representation similarity analysis
  • Linear mode connectivity
  • Similarity based learning
  • Multimodal learning
  • Similarity measures in NNs

Important Dates

  • Paper submission deadline: Oct 04, 2023 Oct 06, 23:59 AoE: Submit on OpenReview

  • Final decisions to authors: Oct 27, 2023

  • Camera Ready submission deadline: Nov 16, 23:59 AoE

Tracks

Submissions to the workshop are organized in two tracks, both requiring novel and unpublished results: an Extended abstract track, which will address early-stage results, insightful negative findings, opinion pieces, and a Proceedings track, which will address complete papers to be published in a dedicated workshop proceedings volume. Both tracks will be figured in the workshop poster session to give opportunity to authors to present their work, and a subset of the submissions will be selected for a spotlight talk session during the workshop.

Paper Format

The full paper submissions must be at most 9 pages in length (excluding references and supplementary materials) and anonymized. We will be following the Neurips general conference submission criteria for papers - for details please see: NeurIPS Call For Papers. As a note, the reviewers will not be required to review the supplementary materials so make sure that your paper is self-contained. For the extended non-archival abstracts please use the same template but limit the submission to 4 pages, exclusive of references and supplementary materials. There will be an option on the submission site to differentiate full papers and extended abstracts. Please make sure to use the NeurIPS LaTeX template and style file.

For camera ready submissions download the necessary template and instructions files at the following link