Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus

April 20, 2026 ยท Grace Period ยท ๐Ÿ› ChileCON 2025 proceedings

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Esteban Rodrรญguez-Betancourt, Edgar Casasola-Murillo arXiv ID 2604.18390 Category cs.LG: Machine Learning Cross-listed cs.AI Citations 0 Venue ChileCON 2025 proceedings
Abstract
In self-supervised learning, self-distilled methods have shown impressive performance, learning representations useful for downstream tasks and even displaying emergent properties. However, state-of-the-art methods usually rely on ensembles of complex mechanisms, with many design choices that are empirically motivated and not well understood. In this work, we explore the role of self-distillation within learning dynamics. Specifically, we isolate the effect of self-distillation by training a group of randomly initialized networks, removing all other common components such as projectors, predictors, and even pretext tasks. Our findings show that even this minimal setup can lead to learned representations with non-trivial improvements over a random baseline on downstream tasks. We also demonstrate how this effect varies with different hyperparameters and present a short analysis of what is being learned by the models under this setup.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning