Enabling Continual Learning in Neural Networks with Meta Learning
Catastrophic forgetting in neural networks is one of the most well-known problems in continual learning. Previous attempts on addressing the problem focus on preventing important weights from changing. Such methods often require task boundaries to learn effectively and do not support backward transfer learning. In this paper, we propose a meta-learning algorithm which learns to reconstruct the gradients of old tasks w.r.t. the current parameters and combines these reconstructed gradients with the current gradient to enable continual learning and backward transfer learning from the current task to previous tasks. Experiments on standard continual learning benchmarks show that our algorithm can effectively prevent catastrophic forgetting and supports backward transfer learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningMeta-LearningTransfer LearningSimilar Papers 제목 키워드 기반
MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices
Meta-Continual Learning (Meta-CL) has emerged as a promising approach to minimize manual labeling efforts and system resource requirements by enabling Continual Learning (CL) with limited labeled samples. However, while …
Continual LearningMetaCD: A Meta Learning Framework for Cognitive Diagnosis based on Continual Learning
Cognitive diagnosis is an essential research topic in intelligent education, aimed at assessing the level of mastery of different skills by students. So far, many research works have used deep learning models to explore …
Continual LearningLearning to Continually Learn via Meta-learning Agentic Memory Designs
The statelessness of foundation models bottlenecks agentic systems' ability to continually learn, a core capability for long-horizon reasoning and adaptation. To address this limitation, agentic systems commonly incorpor…
Continual LearningMePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collectively known as general continual learnin…
Representation LearningContinual LearningLifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms
Continual Learning (CL) allows applications such as user personalization and household robots to learn on the fly and adapt to context. This is an important feature when context, actions, and users change. However, enabl…
Continual LearningMeta-Learning