TRACE: Memory-Efficient Time Series Class-Incremental Learning via Temporal-Spectral Reconstruction

Paper recorded by Signals 4 on 2026-10-26 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-26 on arXiv · recorded by Signals 4 on 2026-10-27

Category: cs.LG · 机器学习 · first seen 2026-10-27

Abstract

Web-connected sensing applications continuously generate multivariate time series with evolving behavioral categories, making Time Series Class-Incremental Learning (TSCIL) essential for adapting to new classes without forgetting previously acquired knowledge. However, preserving diverse and evolving class distributions under strict privacy and memory constraints remains a fundamental challenge. E

Read on arXiv →