首页 > AI前沿 > Temporal Regularized Learning: Self-Supervised Learning Local in Space and Time

Temporal Regularized Learning: Self-Supervised Learning Local in Space and Time

arXiv机器学习 2026-11-13 00:09 23 阅读 查看原文

Layer-local self-supervised objectives remove the backward pass between layers, but almost all still compute their loss over a batch of samples and are therefore local in space but not in time. We introduce Temporal Regularized Learning (TeReL), a spatially and temporally local learning rule for self-supervised representation learning from sequential input streams.

The key idea is to instantiate a VICReg-style