A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning
Recent advancements in deep models have highlighted the need for intelligent systems that combine continual learning (CL) for knowledge acquisition with machine unlearning (MU) for data removal, forming the Continual Learning-Unlearning (CLU) paradigm. While existing work treats CL and MU as separate processes, we reveal their intrinsic connection through a unified optimization framework based on Kullback-Leibler divergence minimization. This framework decomposes gradient updates for approximate CLU into four components: learning new knowledge, unlearning targeted data, preserving existing knowledge, and modulation via weight saliency. A critical challenge lies in balancing knowledge update and retention during sequential learning-unlearning cycles. To resolve this stability-plasticity dilemma, we introduce a remain-preserved manifold constraint to induce a remaining Hessian compensation for CLU iterations. A fast-slow weight adaptation mechanism is designed to efficiently approximate the second-order optimization direction, combined with adaptive weighting coefficients and a balanced weight saliency mask, proposing a unified implementation framework for gradient-based CLU. Furthermore, we pioneer task-agnostic CLU scenarios that support fine-grained unlearning at the cross-task category and random sample levels beyond the traditional task-aware setups. Experiments demonstrate that the proposed UG-CLU framework effectively coordinates incremental learning, precise unlearning, and knowledge stability across multiple datasets and model architectures, providing a theoretical foundation and methodological support for dynamic, compliant intelligent systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningIncremental LearningMachine UnlearningSimilar Papers 제목 키워드 기반
GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning
Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences. However, existing methods often rely on task-aware inference and maintain an expanding se…
Continual LearningSplit-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning
Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typicall…
parameter-efficient fine-tuningContinual LearningMitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models
Unified Multimodal Generative Models (UMGMs) unify visual understanding and image generation within a single autoregressive framework. However, their ability to continually learn new tasks is severely hindered by catastr…
Knowledge Distillationmultimodal generationContinual LearningImage GenerationSparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typicall…
Continual LearningContinual Gradient Low-Rank Projection Fine-Tuning for LLMs
Continual fine-tuning of Large Language Models (LLMs) is hampered by the trade-off between efficiency and expressiveness. Low-Rank Adaptation (LoRA) offers efficiency but constrains the model's ability to learn new tasks…
Continual Learning