Getting aligned on representational alignment

• Main Authors: Sucholutsky, Ilia, Muttenthaler, Lukas, Weller, Adrian, Peng, Andi, Bobu, Andreea, Kim, Been, Love, Bradley C, Grant, Erin, Groen, Iris, Achterberg, Jascha, Tenenbaum, Joshua B, Collins, Katherine M, Hermann, Katherine L, Oktar, Kerem, Greff, Klaus, Hebart, Martin N, Jacoby, Nori, Zhang, Qiuyi, Marjieh, Raja, Geirhos, Robert, Chen, Sherol, Kornblith, Simon, Rane, Sunayana, Konkle, Talia, O'Connell, Thomas P, Unterthiner, Thomas, Lampinen, Andrew K, Müller, Klaus-Robert, Toneva, Mariya, Griffiths, Thomas L
• Format: Journal Article
• Language: English
• Published: 18.10.2023
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning; Computer Science - Neural and Evolutionary Computing; Quantitative Biology - Neurons and Cognition
• DOI: 10.48550/arxiv.2310.13018

Biological and artificial information processing systems form representations that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the extent to which the representations formed by these diverse systems agree? Do similarities in representations then translate into similar behavior? How can a system's representations be modified to better match those of another system? These questions pertaining to the study of representational alignment are at the heart of some of the most active research areas in cognitive science, neuroscience, and machine learning. For example, cognitive scientists measure the representational alignment of multiple individuals to identify shared cognitive priors, neuroscientists align fMRI responses from multiple individuals into a shared representational space for group-level analyses, and ML researchers distill knowledge from teacher models into student models by increasing their alignment. Unfortunately, there is limited knowledge transfer between research communities interested in representational alignment, so progress in one field often ends up being rediscovered independently in another. Thus, greater cross-field communication would be advantageous. To improve communication between these fields, we propose a unifying framework that can serve as a common language between researchers studying representational alignment. We survey the literature from all three fields and demonstrate how prior work fits into this framework. Finally, we lay out open problems in representational alignment where progress can benefit all three of these fields. We hope that our work can catalyze cross-disciplinary collaboration and accelerate progress for all communities studying and developing information processing systems. We note that this is a working paper and encourage readers to reach out with their suggestions for future revisions.