Continual Learning on a Data Diet

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yildirim, Elif Ceren Gok, Yildirim, Murat Onur, Vanschoren, Joaquin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913561001852928
author Yildirim, Elif Ceren Gok
Yildirim, Murat Onur
Vanschoren, Joaquin
author_facet Yildirim, Elif Ceren Gok
Yildirim, Murat Onur
Vanschoren, Joaquin
contents Continual Learning (CL) methods usually learn from all available data. However, this is not the case in human cognition which efficiently focuses on key experiences while disregarding the redundant information. Similarly, not all data points in a dataset have equal potential; some can be more informative than others. This disparity may significantly impact the performance, as both the quality and quantity of samples directly influence the model's generalizability and efficiency. Drawing inspiration from this, we explore the potential of learning from important samples and present an empirical study for evaluating coreset selection techniques in the context of CL to stimulate research in this unexplored area. We train different continual learners on increasing amounts of selected samples and investigate the learning-forgetting dynamics by shedding light on the underlying mechanisms driving their improved stability-plasticity balance. We present several significant observations: learning from selectively chosen samples (i) enhances incremental accuracy, (ii) improves knowledge retention of previous tasks, and (iii) refines learned representations. This analysis contributes to a deeper understanding of selective learning strategies in CL scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17715
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Continual Learning on a Data Diet
Yildirim, Elif Ceren Gok
Yildirim, Murat Onur
Vanschoren, Joaquin
Machine Learning
Computer Vision and Pattern Recognition
Continual Learning (CL) methods usually learn from all available data. However, this is not the case in human cognition which efficiently focuses on key experiences while disregarding the redundant information. Similarly, not all data points in a dataset have equal potential; some can be more informative than others. This disparity may significantly impact the performance, as both the quality and quantity of samples directly influence the model's generalizability and efficiency. Drawing inspiration from this, we explore the potential of learning from important samples and present an empirical study for evaluating coreset selection techniques in the context of CL to stimulate research in this unexplored area. We train different continual learners on increasing amounts of selected samples and investigate the learning-forgetting dynamics by shedding light on the underlying mechanisms driving their improved stability-plasticity balance. We present several significant observations: learning from selectively chosen samples (i) enhances incremental accuracy, (ii) improves knowledge retention of previous tasks, and (iii) refines learned representations. This analysis contributes to a deeper understanding of selective learning strategies in CL scenarios.
title Continual Learning on a Data Diet
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.17715