Learning to Learn without Forgetting using Attention

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vettoruzzo, Anna, Vanschoren, Joaquin, Bouguelia, Mohamed-Rafik, Rögnvaldsson, Thorsteinn
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910564970659840
author Vettoruzzo, Anna
Vanschoren, Joaquin
Bouguelia, Mohamed-Rafik
Rögnvaldsson, Thorsteinn
author_facet Vettoruzzo, Anna
Vanschoren, Joaquin
Bouguelia, Mohamed-Rafik
Rögnvaldsson, Thorsteinn
contents Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods are highly prone to overwrite previously learned patterns and thus forget past experience. Instead, model parameters should be updated selectively and carefully, avoiding unnecessary forgetting while optimally leveraging previously learned patterns to accelerate future learning. Since hand-crafting effective update mechanisms is difficult, we propose meta-learning a transformer-based optimizer to enhance CL. This meta-learned optimizer uses attention to learn the complex relationships between model parameters across a stream of tasks, and is designed to generate effective weight updates for the current task while preventing catastrophic forgetting on previously encountered tasks. Evaluations on benchmark datasets like SplitMNIST, RotatedMNIST, and SplitCIFAR-100 affirm the efficacy of the proposed approach in terms of both forward and backward transfer, even on small sets of labeled data, highlighting the advantages of integrating a meta-learned optimizer within the continual learning framework.
format Preprint
id arxiv_https___arxiv_org_abs_2408_03219
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Learn without Forgetting using Attention
Vettoruzzo, Anna
Vanschoren, Joaquin
Bouguelia, Mohamed-Rafik
Rögnvaldsson, Thorsteinn
Machine Learning
Computer Vision and Pattern Recognition
Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods are highly prone to overwrite previously learned patterns and thus forget past experience. Instead, model parameters should be updated selectively and carefully, avoiding unnecessary forgetting while optimally leveraging previously learned patterns to accelerate future learning. Since hand-crafting effective update mechanisms is difficult, we propose meta-learning a transformer-based optimizer to enhance CL. This meta-learned optimizer uses attention to learn the complex relationships between model parameters across a stream of tasks, and is designed to generate effective weight updates for the current task while preventing catastrophic forgetting on previously encountered tasks. Evaluations on benchmark datasets like SplitMNIST, RotatedMNIST, and SplitCIFAR-100 affirm the efficacy of the proposed approach in terms of both forward and backward transfer, even on small sets of labeled data, highlighting the advantages of integrating a meta-learned optimizer within the continual learning framework.
title Learning to Learn without Forgetting using Attention
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.03219