MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning

2026-09-04

AI Summary

本文提出MePo++框架，通过表示精炼和调和解决一般持续学习中的预训练模型适应性问题，提高模型对新概念的学习能力和在数据流演变中的稳定性。

Abstract

General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous data, making it a realistic yet challenging setting for continual intelligence. Although pretrained models (PTMs) provide rich prior knowledge for addressing the limited supervision and non-stationary nature of GCL, existing PTM-based methods often directly adapt pretrained representations and overlook two critical gaps: the misalignment between upstream pretraining and downstream continual adaptation, and the unreliability of conventional output alignment under blurry streams. Here we propose MePo++, a unified post-training framework that bridges pretrained knowledge and downstream GCL through representation refinement and reconciliation. MePo++ introduces two complementary components: MetaPrep, which improves representation plasticity for continual adaptation through unsupervised meta-refinement over pseudo continual sequences; and StreamAlign, which reinforces representation stability by reconciling evolving online features with a stable pretrained geometry. By improving representation learnability before adaptation and preserving alignment during continual learning, MePo++ enables PTMs to remain both plastic for new concepts and stable over evolving streams. Experiments across diverse PTMs, datasets, and continual learning baselines demonstrate the consistent effectiveness and generality of MePo++ for PTM-based GCL. Our code is available at https://github.com/SunGL001/MePo_Plus.

Problem

• General Continual Learning
• Pretrained Models
• Representation Refinement
• Representation Reconciliation
• Non-stationary Nature

Innovation

• Unifying Post-Training Framework
• Representation Refinement and Reconciliation
• MetaPrep
• StreamAlign
• General Continual Learning