@inproceedings{TomaCAIN2024,

title = {An Exploratory Study of Dataset and Model Management in Open Source Machine Learning Applications},

author = {Tajkia Rahman Toma and Cor-Paul Bezemer},

year  = {2024},

date = {2024-01-17},

urldate = {2024-01-17},

booktitle = {3rd IEEE/ACM International Conference on AI Engineering - Software Engineering for AI (CAIN)},

pages = {1--11},

abstract = {Datasets and models are two key artifacts in machine learning

(ML) applications. Although there exist tools to support dataset

and model developers in managing ML artifacts, little is known

about how these datasets and models are integrated into ML ap-

plications. In this paper, we study how datasets and models in ML

applications are managed. In particular, we focus on how these

artifacts are stored and versioned alongside the applications. After

analyzing 93 repositories, we identified the most common storage

location to store datasets and models is the file system, which causes

availability issues. Notably, large data and model files, exceeding

approximately 60 MB, are stored exclusively in remote storage and

downloaded as needed. Most of the datasets and models lack proper

integration with the version control system, posing potential trace-

ability and reproducibility issues. Additionally, although datasets

and models are likely to evolve during the application development,

they are rarely updated in application repositories.},

keywords = {Data maintenance, SE4ML},

pubstate = {published},

tppubtype = {inproceedings}

}