Research map / Label-efficient and robust learning / Self-supervised and contrastive
Probabilistic Self-supervised Representation Learning via Scoring Rules Minimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes ProSMin, a probabilistic self-supervised representation learning method that minimizes scoring rules to address dimensional collapse.
Problem
Self-supervised learning suffers from dimensional collapse, where models fail to fully use their representational capacity.
Approach
Frames self-supervised representation learning probabilistically and trains by minimizing scoring rules, aiming to avoid dimensional collapse; the abstract gives no further detail on the mechanism.
Closest papers by meaning
- On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning (ICLR 2025 · similarity 0.88)
- Deep Probabilistic Supervision for Image Classification (NeurIPS 2026 · similarity 0.87)
- Self-supervised Representation Learning from Random Data Projectors (ICLR 2024 · similarity 0.86)
- Exploring Structural Degradation in Dense Representations for Self-supervised Learning (NeurIPS 2025 · similarity 0.86)
- Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features (AAAI 2024 · similarity 0.86)
- Self-Supervised Representation Learning with Meta Comprehensive Regularization (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.