Building Human-Machine Trust via Interpretability

Umang Bhatt, Pradeep Ravikumar, José M. F. Moura

AAAI 2019 pp. 9919-9920

doi:10.1609/AAAI.V33I01.33019919 /aaai/2019/bhatt2019aaai-building/

Abstract

Developing human-machine trust is a prerequisite for adoption of machine learning systems in decision critical settings (e.g healthcare and governance). Users develop appropriate trust in these systems when they understand how the systems make their decisions. Interpretability not only helps users understand what a system learns but also helps users contest that system to align with their intuition. We propose an algorithm, AVA: Aggregate Valuation of Antecedents, that generates a consensus feature attribution, retrieving local explanations and capturing global patterns learned by a model. Our empirical results show that AVA rivals current benchmarks.

PDF AAAI Semantic Scholar

Cite

Text

Bhatt et al. "Building Human-Machine Trust via Interpretability." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019919

Markdown

[Bhatt et al. "Building Human-Machine Trust via Interpretability." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/bhatt2019aaai-building/) doi:10.1609/AAAI.V33I01.33019919

BibTeX

@inproceedings{bhatt2019aaai-building,
  title     = {{Building Human-Machine Trust via Interpretability}},
  author    = {Bhatt, Umang and Ravikumar, Pradeep and Moura, José M. F.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9919-9920},
  doi       = {10.1609/AAAI.V33I01.33019919},
  url       = {https://mlanthology.org/aaai/2019/bhatt2019aaai-building/}
}