AI RESEARCH
Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR
arXiv CS.LG
•
ArXi:2604.10586v1 Announce Type: new This paper explores Online Continual Self-Supervised Learning (OCSSL), a scenario in which models learn from continuous streams of unlabeled, non-stationary data, where methods typically employ replay and fast convergence is a central desideratum. We find that OCSSL requires particular attention to the stability-plasticity trade-off: stable methods (e.g. replay with Reservoir sampling) are able to converge faster compared to plastic ones (e.g. FIFO buffer), but incur in performance drops under certain conditions.