Paper ID: 2408.12105

You Only Merge Once: Learning the Pareto Set of Preference-Aware Model Merging

Weiyu Chen, James Kwok

Model merging, which combines multiple models into a single model, has gained increasing popularity in recent years. By efficiently integrating the capabilities of various models without their original training data, this significantly reduces the parameter count and memory usage. However, current methods can only produce one single merged model. This necessitates a performance trade-off due to conflicts among the various models, and the resultant one-size-fits-all model may not align with the preferences of different users who may prioritize certain models over others. To address this issue, we propose preference-aware model merging, and formulate this as a multi-objective optimization problem in which the performance of the merged model on each base model's task is treated as an objective. In only one merging process, the proposed parameter-efficient structure can generate the whole Pareto set of merged models, each representing the Pareto-optimal model for a given user-specified preference. Merged models can also be selected from the learned Pareto set that are tailored to different user preferences. Experimental results on a number of benchmark datasets demonstrate that the proposed preference-aware Pareto Merging can obtain a diverse set of trade-off models and outperforms state-of-the-art model merging baselines.

Submitted: Aug 22, 2024