UvA-DARE (University of Amsterdam) · 2020 · 14 citations · 7 references
ComputingComputer ScienceData ScienceData EngineeringData VisualizationMachine LearningAlgorithmic FairnessData AnalysisData PreprocessingData-flow AnalysisDataflow ModelingFairness In Machine LearningAcyclic Directed Graph RepresentationsData Flow PatternsDirected Acyclic Graph LearningDirected Acyclic Graph PipelinesFairness-aware OptimizationPipeline DebuggingPipelinesPreprocessing Bias Mitigation
Surfacing and mitigating bias in ML pipelines is a complex topic, with a dire need to provide system-level support to data scientists. Humans should be empowered to debug these pipelines, in order to control for bias and to improve data quality and representativeness. We propose fair-DAGs, an open-source library that extracts directed acyclic graph (DAG) representations of the data flow in preprocessing pipelines for ML. The library subsequently instruments the pipelines with tracing and visualization code to capture changes in data distributions and identify distortions with respect to protected group membership as the data travels through the pipeline. We illustrate the utility of fair-DAGs with experiments on publicly available ML pipelines.
7
Batya Friedman, Helen Nissenbaum · ACM Transactions on Information Systems · 1996 · 1.1K citations · Full text
Solon Barocas · California Law Review · 2016 · 1.1K citations · Full text
Law, Employment Law, Data Mining +16
Data Management Challenges in Production Machine Learning
Neoklis Polyzotis, Sudip Roy, Steven Euijong Whang et al. · 2017 · 209 citations · Full text
Babak Salimi, Luke Rodriguez, Bill Howe et al. · 2019 · 144 citations · Full text