Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning

Ziqi Gu, Chunyan Xu, Wenxuan Fang, Xin Liu, Yide Qiu, Zhen Cui

Keywords: Multi-domain task incremental learning; Schrödinger Bridge

TL;DR: We propose LEBA, a framework that mitigates forgetting and enhances generalization in multi-domain continual learning via Schrödinger bridge-based optimization and progressive adapter ensembling.

Abstract:

Multi-domain task incremental learning (MTIL) demands models to master domain-specific expertise while preserving generalization capabilities.
Inspired by human lifelong learning, which relies on revisiting, aligning, and integrating past experiences, we propose a Learning and Ensembling Bridge Adapters (LEBA) framework.
To facilitate cohesive knowledge transfer across domains, specifically, we propose a continuous-domain bridge adaptation module, leveraging the distribution transfer capabilities of Schrödinger bridge for stable progressive learning.
To strengthen memory consolidation, we further propose a progressive knowledge ensemble strategy that revisits past task representations via a diffusion model and dynamically integrates historical adapters.
For efficiency, LEBA maintains a compact adapter pool through similarity-based selection and employs learnable weights to align replayed samples with current task semantics.
Together, these components effectively mitigate catastrophic forgetting and enhance generalization across tasks.
Extensive experiments across multiple benchmarks validate the effectiveness and superiority of LEBA over state-of-the-art methods.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 7034