English

Achieving Transparency in Distributed Machine Learning with Explainable Data Collaboration

Machine Learning 2022-12-08 v1 Artificial Intelligence

Abstract

Transparency of Machine Learning models used for decision support in various industries becomes essential for ensuring their ethical use. To that end, feature attribution methods such as SHAP (SHapley Additive exPlanations) are widely used to explain the predictions of black-box machine learning models to customers and developers. However, a parallel trend has been to train machine learning models in collaboration with other data holders without accessing their data. Such models, trained over horizontally or vertically partitioned data, present a challenge for explainable AI because the explaining party may have a biased view of background data or a partial view of the feature space. As a result, explanations obtained from different participants of distributed machine learning might not be consistent with one another, undermining trust in the product. This paper presents an Explainable Data Collaboration Framework based on a model-agnostic additive feature attribution algorithm (KernelSHAP) and Data Collaboration method of privacy-preserving distributed machine learning. In particular, we present three algorithms for different scenarios of explainability in Data Collaboration and verify their consistency with experiments on open-access datasets. Our results demonstrated a significant (by at least a factor of 1.75) decrease in feature attribution discrepancies among the users of distributed machine learning.

Keywords

Cite

@article{arxiv.2212.03373,
  title  = {Achieving Transparency in Distributed Machine Learning with Explainable Data Collaboration},
  author = {Anna Bogdanova and Akira Imakura and Tetsuya Sakurai and Tomoya Fujii and Teppei Sakamoto and Hiroyuki Abe},
  journal= {arXiv preprint arXiv:2212.03373},
  year   = {2022}
}

Comments

Presented at PKAW 2022 (arXiv:2211.03888) Report-no: PKAW/2022/03

R2 v1 2026-06-28T07:24:18.371Z