FusionBench: A Comprehensive Benchmark of Deep Model Fusion

This project is still in testing phase as the API may be subject to change. Please report any issues you encounter.

Documentation is available at tanganke.github.io/fusion_bench/.

Overview

FusionBench is a benchmark suite designed to evaluate the performance of various deep model fusion techniques. It aims to provide a comprehensive comparison of different methods on a variety of datasets and tasks.

Installation

install from PyPI:

pip install fusion-bench

or install the latest version in development from github repository

git clone https://github.com/tanganke/fusion_bench.git
cd fusion_bench

pip install -e . # install the package in editable mode

Introduction to Deep Model Fusion

Deep model fusion is a technique that merges, ensemble, or fuse multiple deep neural networks to obtain a unified model. It can be used to improve the performance and robustness of model or to combine the strengths of different models, such as fuse multiple task-specific models to create a multi-task model. For a more detailed introduction to deep model fusion, you can refer to W. Li, 2023, 'Deep Model Fusion: A Survey'. We also provide a brief overview of deep model fusion in our documentation. In this benchmark, we evaluate the performance of different fusion methods on a variety of datasets and tasks.

Project Structure

The project is structured as follows:

• fusion_bench/: the main package of the benchmark.
• config/: configuration files for the benchmark. We use Hydra to manage the configurations.
• docs/: documentation for the benchmark. We use mkdocs to generate the documentation. Start the documentation server locally with mkdocs serve. The required packages can be installed with pip install -r mkdocs-requirements.txt.
• examples/: example scripts for running some of the experiments.
• tests/: unit tests for the benchmark.

Citation

If you find this benchmark useful, please consider citing our work:

@misc{tangFusionBenchComprehensiveBenchmark2024,
  title = {{{FusionBench}}: {{A Comprehensive Benchmark}} of {{Deep Model Fusion}}},
  shorttitle = {{{FusionBench}}},
  author = {Tang, Anke and Shen, Li and Luo, Yong and Hu, Han and Do, Bo and Tao, Dacheng},
  year = {2024},
  month = jun,
  number = {arXiv:2406.03280},
  eprint = {2406.03280},
  publisher = {arXiv},
  url = {http://arxiv.org/abs/2406.03280},
  archiveprefix = {arxiv},
  langid = {english},
  keywords = {Computer Science - Artificial Intelligence,Computer Science - Computation and Language,Computer Science - Machine Learning}
}