Continual Learning Beyond a Single Model
A growing body of research in continual learning focuses on the catastrophic forgetting problem. While many attempts have been made to alleviate this problem, the majority of the methods assume a single model in the continual learning setup. In this work, we question this assumption and show that employing ensemble models can be a simple yet effective method to improve continual performance. However, ensembles' training and inference costs can increase significantly as the number of models grows. Motivated by this limitation, we study different ensemble models to understand their benefits and drawbacks in continual learning scenarios. Finally, to overcome the high compute cost of ensembles, we leverage recent advances in neural network subspace to propose a computationally cheap algorithm with similar runtime to a single model yet enjoying the performance benefits of ensembles.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningmodelSimilar Papers 제목 키워드 기반
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even…
Reinforcement LearningBeyond Entropy: Style Transfer Guided Single Image Continual Test-Time Adaptation
Continual test-time adaptation (cTTA) methods are designed to facilitate the continual adaptation of models to dynamically changing real-world environments where computational resources are limited. Due to this inherent …
image-classificationImage ClassificationSemantic SegmentationStyle Transfer+1Scalable Language Model with Generalized Continual Learning
Continual learning has gained increasing importance as it facilitates the acquisition and refinement of scalable knowledge and skills in language models. However, existing methods typically encounter strict limitations a…
Continual LearningLanguage ModelingLanguage ModellingLarge Language Model+1Bookworm continual learning: beyond zero-shot learning and continual learning
We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually. Thus BCL generalizes both continual learning (CL…
AttributeContinual LearningZero-Shot LearningLearning Beyond the Surface: How Far Can Continual Pre-Training with LoRA Enhance LLMs' Domain-Specific Insight Learning?
Large Language Models (LLMs) have demonstrated remarkable performance on various tasks, yet their ability to extract and internalize deeper insights from domain-specific datasets remains underexplored. In this study, we …