Can I read HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models on EtoBox?

HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models by Zhou, Yu; Wu, Xingyu; Wu, Jibin; Feng, Liang; Tan, Kay Chen is a scholarly article available to read on EtoBox.

What is HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models about?

Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in large pretrained model development due to its ability to bypass the need for original training data and further training processes. However, most existing model merging approaches focus solely on exploring the parameter space, merging models with identical architectures. Merging within the architecture space, despite its potential, remains in its early stages due to the vast search space and the challenges of layer compatibility. This paper marks a significant advance toward more flexible and comprehensive model merging techniques by modeling the architecture-space merging process as a reinforcement learning task. We train policy and value networks using offline sampling of weight vectors, which are then employed for the online optimization of merging strategies. Moreover, a multi-objective optimization paradigm is introduced to accommodate users' diverse task preferences, learning the Pareto front of optimal models to offer customized merging suggestions. Experimental results across multiple tasks, incl

Author

Zhou, Yu; Wu, Xingyu; Wu, Jibin; Feng, Liang; Tan, Kay Chen

Published

2024

Language

EN