RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging

TL;DR

RegMean++ improves model merging by explicitly modeling layer dependencies, leading to better performance and generalization across various tasks and distribution shifts.

Contribution

It introduces a new method, RegMean++, that incorporates intra-layer and cross-layer dependencies into model merging, surpassing the original RegMean.

Findings

RegMean++ outperforms RegMean in diverse settings.

It achieves better generalization in ID and OOD scenarios.

RegMean++ is robust under distribution shifts.

Abstract

Regression Mean (RegMean), an approach that formulates model merging as a linear regression problem, aims to find the optimal weights for each linear layer in the merged model by minimizing the discrepancy in predictions between the merged and candidate models. RegMean provides a precise closed-form solution for the merging problem; therefore, it offers explainability and computational efficiency. However, RegMean merges each linear layer independently, overlooking how the features and information in earlier layers propagate through deeper layers and influence the final predictions of the merged model. Here, we introduce RegMean++, a simple yet effective alternative to RegMean, that explicitly incorporates both intra-layer and cross-layer dependencies between merged models' layers into RegMean's objective. By accounting for these dependencies, RegMean++ better captures the behaviors of the merged model. Extensive experiments demonstrate that RegMean++ consistently outperforms RegMean across diverse settings, including in-domain (ID) and out-of-domain (OOD) generalization, sequential merging, large-scale tasks, and robustness under several types of distribution shifts. Furthermore, RegMean++ achieves competitive performance across diverse settings compared to various advanced model merging methods.