用群体演化思路解决深度学习持续学习难题
Achieving Deep Continual Learning via Evolution
- 构建神经网络种群，为每个任务进化专属模型
- 在多个任务上显著超越现有单模型方法
- 适合追求长期学习能力的AI系统设计者
深度神经网络虽取得显著成功，但在持续学习（CL）方面仍存在根本局限。当前多数方法聚焦于提升单个模型能力，受人类群体集体学习机制启发，本文提出演进式持续学习（ECL）框架，维护并演化一个多样化的神经网络模型种群。ECL持续为每个新引入的任务搜索最优架构，训练后存为专用专家模型，形成不断增长的技能库。该方法天然解决核心挑战：通过专家模型隔离实现稳定性，通过演化专属任务架构增强可塑性。实验表明，ECL显著优于现有最先进单模型持续学习方法。通过从个体适应转向集体演化，ECL为具备持续学习能力的AI系统提供了新路径。
原文摘要 · Abstract (English)
Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the collective learning mechanisms of human populations, we introduce Evolving Continual Learning (ECL), a framework that maintains and evolves a diverse population of neural network models. ECL continually searches for an optimal architecture for each introduced incremental task. This tailored model is trained on the corresponding task and archived as a specialized expert, contributing to a growing collection of skills. This approach inherently resolves the core CL challenges: stability is achieved through the isolation of expert models, while plasticity is greatly enhanced by evolving unique, task-specific architectures. Experimental results demonstrate that ECL significantly outperforms state-of-the-art individual-level CL methods. By shifting the focus from individual adaptation to collective evolution, ECL presents a novel path toward AI systems capable of CL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。