Abstract
Machine Learning (ML) is increasingly used to automate impactful decisions, and the risks arising from this wide-spread use are garnering attention from policymakers, scientists, and the media. ML applications are often very brittle with respect to their input data, which leads to concerns about their reliability, accountability, and fairness. While bias detection cannot be fully automated, computational tools can help pinpoint particular types of data issues. We recently proposed mlinspect, a library that enables lightweight lineage-based inspection of ML preprocessing pipelines. In this demonstration, we show how mlinspect can be used to detect data distribution bugs in a representative pipeline. In contrast to existing work, mlinspect operates on declarative abstractions of popular data science libraries like estimator/transformer pipelines, can handle both relational and matrix data, and does not require manual code instrumentation. The library is publicly available at https://github.com/stefan-grafberger/mlinspect.
Original language | English (US) |
---|---|
Pages (from-to) | 2736-2739 |
Number of pages | 4 |
Journal | Proceedings of the ACM SIGMOD International Conference on Management of Data |
DOIs | |
State | Published - 2021 |
Event | 2021 International Conference on Management of Data, SIGMOD 2021 - Virtual, Online, China Duration: Jun 20 2021 → Jun 25 2021 |
Keywords
- data distribution debugging
- machine learning pipelines
- responsible data science
- technical bias
ASJC Scopus subject areas
- Software
- Information Systems