Parameter-Efficient Interventions for Enhanced Model Merging
This addresses efficiency and performance issues in multi-task learning for AI practitioners, though it appears incremental as it builds on existing merging techniques.
The paper tackles the problem of representation bias in multi-task model merging, proposing IntervMerge with mini-interventions to reduce parameters while outperforming state-of-the-art methods.
Model merging combines knowledge from task-specific models into a unified multi-task model to avoid joint training on all task data. However, current methods face challenges due to representation bias, which can interfere with tasks performance. As a remedy, we propose IntervMerge, a novel approach to multi-task model merging that effectively mitigates representation bias across the model using taskspecific interventions. To further enhance its efficiency, we introduce mini-interventions, which modify only part of the representation, thereby reducing the additional parameters without compromising performance. Experimental results demonstrate that IntervMerge consistently outperforms the state-of-the-art approaches using fewer parameters.