Brain-Inspired Hierarchical Modularity for General Continual Learning

2026-09-21

AI Summary

研究通过模仿果蝇学习记忆系统的层级模块化原理，提出一种轻量级的预训练基础模型适应方法，以解决在线、不确定数据流下的持续学习问题。

Abstract

Continual learning, the ability to learn from sequential experience while retaining and adapting prior knowledge, is central to intelligent systems operating in changing environments. However, conventional continual learning is typically studied with offline task-wise training and clear task boundaries, leaving a substantial gap from general continual learning under online, uncertain, and evolving data streams. In this regime, intelligent systems must separate conflicting experience to reduce interference while integrating compatible experience to promote generalization. Inspired by the organization of the Drosophila learning and memory system, we identify a hierarchical modular principle that coordinates both functions through expert specialization and ensemble integration. We instantiate this principle as lightweight modular adaptation of pretrained foundation models, combining brain-inspired random expansion for expert routing and diversified modular integration across spatial and temporal scales. Across visual recognition, vision-language understanding, ego-exo video understanding, and embodied vision-language-action learning, our method consistently improves learning under online and uncertain data streams, with gains exceeding 50 percentage points over replay-free alternatives in embodied manipulation. These findings support hierarchical modularity as a biologically grounded path for learning from dynamic experience.

Problem

• continual learning
• online data streams
• uncertain data
• evolving data
• task boundaries

Innovation

• hierarchical modularity
• continual learning
• expert specialization
• ensemble integration
• random expansion