AI RESEARCH
IConE: Batch Independent Collapse Prevention for Self-Supervised Representation Learning
arXiv CS.LG
•
ArXi:2603.15263v1 Announce Type: cross Self-supervised learning (SSL) has revolutionized representation learning, with Joint-Embedding Architectures (JEAs) emerging as an effective approach for capturing semantic features. Existing JEAs rely on implicit or explicit batch interaction -- via negative sampling or statistical regularization -- to prevent representation collapse. This reliance becomes problematic in regimes where batch sizes must be small, such as high-dimensional scientific data, where memory constraints and class imbalance make large, well-balanced batches infeasible. We.