paper-with-me

Papers

Continual Learning with Query-Only Attention

2025-10-01 · Gautham Bekal, Ashish Pujari, Scott David Kelly arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.00365

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

One-stage Prompt-based Continual Learning

2024-02-25 · Youngeun Kim, Yuhang Li, Priyadarshini Panda

Prompt-based Continual Learning (PCL) has gained considerable attention as a promising continual learning solution as it achieves state-of-the-art performance while preventing privacy violation and memory overhead issues…

Continual Learning

Real-Time Trend Prediction via Continually-Aligned LLM Query Generation

2026-01-24 · Zijing Hui, Wenhan Lyu, Shusen Wang, Li Chen 외 arxiv

Trending news detection in low-traffic search environments faces a fundamental cold-start problem, where a lack of query volume prevents systems from identifying emerging or long-tail trends. Existing methods relying on …

Continual Learning

CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning

2022-11-23 · CVPR 2023 1 · James Seale Smith, Leonid Karlinsky, Vyshnavi Gutta, Paola Cascante-Bonilla 외

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extens…

Continual LearningNovel Concepts

SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers

2023-06-09 · BoWen Zhang, Liyang Liu, Minh Hieu Phan, Zhi Tian 외

This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework and introduces \textbf{SegViTv2}. In this study, we introduce a novel Attention-to-…

Continual LearningContinual Semantic SegmentationDecoderSegmentation+1

Causal Attention with Lookahead Keys

2025-09-09 · Zhuoqing Song, Peng Sun, Huizhuo Yuan, Quanquan Gu arxiv

In standard causal attention, each token's query, key, and value (QKV) are static and encode only preceding context. We introduce CAuSal aTtention with Lookahead kEys (CASTLE), an attention mechanism that continually upd…