BECAME: BayEsian Continual Learning with Adaptive Model MErging
Continual Learning (CL) strives to learn incrementally across tasks while mitigating catastrophic forgetting. A key challenge in CL is balancing stability (retaining prior knowledge) and plasticity (learning new tasks). While representative gradient projection methods ensure stability, they often limit plasticity. Model merging techniques offer promising solutions, but prior methods typically rely on empirical assumptions and carefully selected hyperparameters. In this paper, we explore the potential of model merging to enhance the stability-plasticity trade-off, providing theoretical insights that underscore its benefits. Specifically, we reformulate the merging mechanism using Bayesian continual learning principles and derive a closed-form solution for the optimal merging coefficient that adapts to the diverse characteristics of tasks. To validate our approach, we introduce a two-stage framework named BECAME, which synergizes the expertise of gradient projection and adaptive merging. Extensive experiments show that our approach outperforms state-of-the-art CL methods and existing merging strategies.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningmodelSimilar Papers 제목 키워드 기반
Multi-label Classification via Adaptive Resonance Theory-based Clustering
This paper proposes a multi-label classification algorithm capable of continual learning by applying an Adaptive Resonance Theory (ART)-based clustering algorithm and the Bayesian approach for label probability computati…
ClassificationClusteringContinual LearningGeneral Classification+2AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning
Continual learning (CL) is essential for deploying large language models (LLMs) in dynamic real-world environments without the need for costly retraining. Recent model merging-based methods have attracted significant att…
Continual LearningMerge before Forget: A Single LoRA Continual Learning via Continual Merging
Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks. Current Low-Rank Adaptation (LoRA) c…
Continual LearningMerging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains. Current model merging techniques focus o…
Addressing Client Drift in Federated Continual Learning with Adaptive Optimization
Federated learning has been extensively studied and is the prevalent method for privacy-preserving distributed learning in edge devices. Correspondingly, continual learning is an emerging field targeted towards learning …
Continual LearningFederated LearningPrivacy Preserving