{"ID":2850916,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20108","arxiv_id":"2510.20108","title":"Why Prototypes Collapse: Diagnosing and Preventing Partial Collapse in Prototypical Self-Supervised Learning","abstract":"Prototypical self-supervised learning methods consistently suffer from partial prototype collapse, where multiple prototypes converge to nearly identical representations. This undermines their central purpose -- providing diverse and informative targets to guide encoders toward rich representations -- and has led practitioners to over-parameterize prototype sets or add ad-hoc regularizers, which mitigate symptoms rather than address the root cause. We empirically trace the collapse to the joint optimization of encoders and prototypes, which encourages a type of shortcut learning: early in training prototypes drift toward redundant representations that minimize loss without necessarily enhancing representation diversity. To break the joint optimization, we introduce a fully decoupled training strategy that learns prototypes and encoders under separate objectives. Concretely, we model prototypes as a Gaussian mixture updated with an online EM-style procedure, independent of the encoder's loss. This simple yet principled decoupling eliminates prototype collapse without explicit regularization and yields consistently diverse prototypes and stronger downstream performance.","short_abstract":"Prototypical self-supervised learning methods consistently suffer from partial prototype collapse, where multiple prototypes converge to nearly identical representations. This undermines their central purpose -- providing diverse and informative targets to guide encoders toward rich representations -- and has led pract...","url_abs":"https://arxiv.org/abs/2510.20108","url_pdf":"https://arxiv.org/pdf/2510.20108v2","authors":"[\"Gabriel Y. Arteaga\",\"Marius Aasan\",\"Rwiddhi Chakraborty\",\"Martine Hjelkrem-Tan\",\"Thalles Silva\",\"Michael Kampffmeyer\",\"Adín Ramírez Rivera\"]","published":"2025-10-23T01:25:10Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CV\"]","methods":"[]","has_code":false}