Model merging works better when exploring beyond task weight combinations
A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic
Machine LearningComputation and LanguageComputer Vision and Pattern Recognition
Summary
Combining multiple task-specific AI models into one multi-task model is usually done by mixing their changes in a specific limited way. The authors found that this usual mixing method actually restricts the combined model, which can hurt performance. By allowing the combined model’s weights to be adjusted more freely, they improved performance across different setups and even with very little extra data. This suggests that better combined models exist outside the standard method’s limits and encourages rethinking how we merge models.
What this means in practice
- •For machine learning engineers: Improve multi-task models by optimizing merged weights beyond standard linear combinations for better performance with few extra data samples.
- •For ai platform developers: Build flexible model merging tools that explore a broader range of model weights to enhance multi-task model efficiency and accuracy.
Authors
Sin-Han Yang, Shih-Cheng Huang, Chieh-Yen Lin, Yun-Nung Chen, Shao-Hua Sun, Hung-yi Lee
Abstract
Model merging aims to build a multi-task model cheaply by combining the weights of individual task-specific models. To perform well across multiple tasks, most existing merging methods use an additional dataset to find the coefficients for the best linear combination of task-specific weight updates. However, we identify an implicit regularization in this standard practice: searching over coefficients restricts the candidate models to a subspace spanned by task-specific weight updates. In this work, we investigate whether this regularization is actually useful. Surprisingly, empirical results show that optimizing merged-model weights without this regularization significantly boosts the performance of common merging methods across multiple architectures, domains, and even in an extremely data-limited scenario where only one instance is available per class. Moreover, directly optimizing the pretrained model weights even outperforms some existing merging methods. Analysis shows that better multi-task weights exist outside the subspace and can be found using multiple methods. We study different strategies for using the additional dataset, discussing their practical use and implications for model merging. Overall, this work calls for revisiting the existing model-merging pipeline, motivating a broader exploration of the weight space and a reconsideration of the implicit regularization induced by task arithmetic.