Continual Learning with Query-Only Attention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bekal, Gautham, Pujari, Ashish, Kelly, Scott David
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914129484185600
author Bekal, Gautham
Pujari, Ashish
Kelly, Scott David
author_facet Bekal, Gautham
Pujari, Ashish
Kelly, Scott David
contents Continual learning involves learning from a stream of data without repetition of data points, a scenario that is inherently complex due to distributional shift across tasks. We propose a query-only attention mechanism that discards keys and values, yet preserves the core inductive bias of transformer architectures. In continual learning scenarios, this simplified mechanism significantly mitigates both loss of plasticity and catastrophic forgetting, outperforming baselines such as selective re-initialization. We establish a conceptual link between query-only attention, full transformer attention, and model agnostic meta-learning, framing them as instances of meta-learning. We further provide intuition for why query-based models and attention networks help preserve plasticity in continual settings. Finally, through preliminary Hessian spectrum analysis, we observe that models maintaining higher curvature rank across tasks tend to retain plasticity. Our findings suggest that full attention may not be essential for capturing the benefits of meta-learning in continual learning.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00365
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continual Learning with Query-Only Attention
Bekal, Gautham
Pujari, Ashish
Kelly, Scott David
Machine Learning
Continual learning involves learning from a stream of data without repetition of data points, a scenario that is inherently complex due to distributional shift across tasks. We propose a query-only attention mechanism that discards keys and values, yet preserves the core inductive bias of transformer architectures. In continual learning scenarios, this simplified mechanism significantly mitigates both loss of plasticity and catastrophic forgetting, outperforming baselines such as selective re-initialization. We establish a conceptual link between query-only attention, full transformer attention, and model agnostic meta-learning, framing them as instances of meta-learning. We further provide intuition for why query-based models and attention networks help preserve plasticity in continual settings. Finally, through preliminary Hessian spectrum analysis, we observe that models maintaining higher curvature rank across tasks tend to retain plasticity. Our findings suggest that full attention may not be essential for capturing the benefits of meta-learning in continual learning.
title Continual Learning with Query-Only Attention
topic Machine Learning
url https://arxiv.org/abs/2510.00365