What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning

TL;DR

This paper introduces a neural architecture search-based method to automatically determine optimal adapter placement and structure in multi-domain learning, enhancing flexibility and efficiency over handcrafted approaches.

Contribution

It proposes a data-driven NAS approach for adaptive adapter plugging and structure design in multi-domain learning, addressing inflexibility and computational costs of prior methods.

Findings

Outperforms existing methods with comparable accuracy

Automatically discovers effective adapter structures for different domains

Reduces manual design effort and computational overhead

Abstract

As an important and challenging problem, multi-domain learning (MDL) typically seeks for a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network. Usually, existing ways of adapter plugging and structure design are handcrafted and fixed for all domains before model learning, resulting in the learning inflexibility and computational intensiveness. With this motivation, we propose to learn a data-driven adapter plugging strategy with Neural Architecture Search (NAS), which automatically determines where to plug for those adapter modules. Furthermore, we propose a NAS-adapter module for adapter structure design in a NAS-driven learning scheme, which automatically discovers effective adapter module structures for different domains. Experimental results demonstrate the effectiveness of our MDL model against existing approaches under the conditions of comparable performance.