Continual Learning with Query-Only Attention

• URL: http://arxiv.org/abs/2510.00365v2
• Date: Sat, 01 Nov 2025 03:58:05 GMT
• Title: Continual Learning with Query-Only Attention
• Authors: Gautham Bekal, Ashish Pujari, Scott David Kelly,
• Abstract summary: Continual learning involves learning from a stream of data without repetition of data points.<n>We propose a query-only attention mechanism that discards keys and values, yet preserves the core inductive bias of transformer architectures.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Advancing Analytic Class-Incremental Learning through Vision-Language Calibration [6.871141687303144]
  Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability.<n>We propose textbfVILA, a novel dual-branch framework that advances analytic CIL via a two-level vision-language calibration strategy.<n>Our framework harmonizes high-fidelity prediction with the simplicity of analytic learning.
  arXiv  Detail & Related papers  (2026-02-14T08:32:51Z)
• Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning [51.07663354001582]
  Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task.<n>We present a novel approach to address this challenge, focusing on the intersection of memory-based methods and regularization approaches.<n>We formulate a regularization strategy, termed Information Maximization (IM) regularizer, for memory-based continual learning methods.
  arXiv  Detail & Related papers  (2025-12-01T15:56:00Z)
• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [55.914891182214475]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• Shortcut Learning Susceptibility in Vision Classifiers [11.599035626374409]
  Shortcut learning is where machine learning models exploit spurious correlations in data instead of capturing meaningful features.<n>This study introduces deliberate shortcuts into the dataset that are correlated with class labels both positionally and via intensity.<n>We evaluate susceptibility to shortcut learning across different learning rates.
  arXiv  Detail & Related papers  (2025-02-13T10:25:52Z)
• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture.<n>We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• A phase transition between positional and semantic learning in a solvable model of dot-product attention [30.96921029675713]
  Morelinear model dot-product attention is studied as a non-dimensional self-attention layer with trainable and low-dimensional query and key data. We show that either a positional attention mechanism (with tokens each other based on their respective positions) or a semantic attention mechanism (with tokens tied to each other based their meaning) or a transition from the former to the latter with increasing sample complexity.
  arXiv  Detail & Related papers  (2024-02-06T11:13:54Z)
• Using Early Readouts to Mediate Featural Bias in Distillation [30.5299408494168]
  Deep networks tend to learn spurious feature-label correlations in real-world supervised learning tasks. We propose a novel early readout mechanism whereby we attempt to predict the label using representations from earlier network layers.
  arXiv  Detail & Related papers  (2023-10-28T04:58:15Z)
• On the Optimization and Generalization of Multi-head Attention [28.33164313549433]
  We investigate the potential optimization and generalization advantages of using multiple attention heads. We derive convergence and generalization guarantees for gradient-descent training of a single-layer multi-head self-attention model.
  arXiv  Detail & Related papers  (2023-10-19T12:18:24Z)
• Untangling tradeoffs between recurrence and self-attention in neural networks [81.30894993852813]
  We present a formal analysis of how self-attention affects gradient propagation in recurrent networks. We prove that it mitigates the problem of vanishing gradients when trying to capture long-term dependencies. We propose a relevancy screening mechanism that allows for a scalable use of sparse self-attention with recurrence.
  arXiv  Detail & Related papers  (2020-06-16T19:24:25Z)
• Meta-learning framework with applications to zero-shot time-series forecasting [82.61728230984099]
  This work provides positive evidence using a broad meta-learning framework. residual connections act as a meta-learning adaptation mechanism. We show that it is viable to train a neural network on a source TS dataset and deploy it on a different target TS dataset without retraining.
  arXiv  Detail & Related papers  (2020-02-07T16:39:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.