Workshop at ECMLPKDD 2020, Ghent, Belgium, September 18, 2020
News! SIGKDD Explorations special issues on Fairness and Bias in AI published!
News! the 2nd BIAS workshop at ECMLPKDD 2021
News! call for papers: special issue on Bias and Fairness in AI in the Data Mining and Knowledge Discovery journal
AI techniques based on big data and algorithmic processing are increasingly used to guide decisions in important societal spheres, including hiring decisions, university admissions, loan granting, and crime prediction. They are applied by search engines, Internet recommendation systems and social media bots, influencing our perceptions of political developments and even of scientific findings. However, there are growing concerns with regard to the epistemic and normative quality of AI evaluations and predictions. In particular, there is strong evidence that algorithms may sometimes amplify rather than eliminate existing bias and discrimination, and thereby have negative effects on social cohesion and on democratic institutions.
Scholarly reflection of these issues has begun and despite the large volume of related research lately a lot of work remains to be done. In particular, we still lack a comprehensive understanding of how pertinent concepts of bias or discrimination should be interpreted in the context of AI and which technical options to combat bias and discrimination are both realistically possible and normatively justified. The workshop will discuss these issues based on the shared research question: How can standards of unbiased attitudes and non-discriminatory practices be met in (big) data analysis and algorithm-based decision-making?
The workshop will focus (but is not limited) on the following topics:
Fairness measures, Statistical fairness
Methods for detecting algorithmic discrimination
Debiasing strategies
“Interaction” between fairness and other learning challenges like imbalanced data or rare classes
Explainability, traceability, data and model lineage
Benchmark datasets
Formalization, measurement and mitigation of unfairness in machine learning, including construction of training data sets, model induction/selection and model outputs
New or reconciled fairness impossibility results
Fairness, equity and justice by design
Fairness in predictive modeling used for decision making and decision support
Fairness in non-iid data including network, text, time series and other complex evolving data
Fairness in unsupervised learning (clustering, PCA), network embeddings
Fairness in federated learning
Fairness in matchmaking, recommenders and search engines
Fairness in resource allocation
Fairness in personalized interventions
Counterfactual reasoning for fairness
Visual analytics for studying / auditing fairness
HCI for studying / auditing fairness
Auditing machine learning wrt fairness
Case studies of fairness-aware machine learning
Interdisciplinary studies (law, social sciences) on fairness in machine learning
New benchmarks for fairness research
Software and demonstrations for studying fairness
The BIAS 2020 workshop is proudly a part of the FAccT network, to research and engage with fairness, accountability, and transparency scholars across connected disciplines.