{"ID":2895125,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.09471","arxiv_id":"2507.09471","title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","abstract":"Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They typically allocate a unique sub-module for learning each task, with a task recognizer to select the appropriate sub-modules for testing images. However, due to the feature subspace misalignment from independently trained sub-modules, these methods tend to produce ambiguous decisions under misleading task-ids. To address this, we propose Cross-subspace Knowledge Alignment and Aggregation (CKAA), a novel framework that enhances model robustness against misleading task-ids through two key innovations: (1) Dual-level Knowledge Alignment (DKA): By aligning intra-class feature distributions across different subspaces and learning a robust global classifier through a feature simulation process, DKA enables the model to distinguish features from both correct and incorrect subspaces during training. (2) Task-Confidence-guided Mixture of Adapters (TC-MoA): A robust inference scheme that adaptively aggregates task-specific knowledge from relevant sub-modules based on task-confidence scores, avoiding overconfidence in misleading task-id predictions. Extensive experiments demonstrate that CKAA outperforms existing PEFT-based CL methods.","short_abstract":"Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They typically allocate a unique sub-module for learning each task, with a task recognize...","url_abs":"https://arxiv.org/abs/2507.09471","url_pdf":"https://arxiv.org/pdf/2507.09471v1","authors":"[\"Lingfeng He\",\"De Cheng\",\"Zhiheng Ma\",\"Huaijie Wang\",\"Dingwen Zhang\",\"Nannan Wang\",\"Xinbo Gao\"]","published":"2025-07-13T03:11:35Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}