To read

• The ethics of algorithms: key problems and solutions
• Monitoring hiring discrimination through online recruitment platforms
• TimeSHAP: Explaining Recurrent Models through Sequence Perturbations
• Language (Technology) is Power: A Critical Survey of “Bias” in NLP
• Long-Term Trends in the Public Perception of Artificial Intelligence
• GLocalX – From Local to Global Explanations of Black Box AI Models

Radar

• Ensembles of Random SHAPs
• Bias Preservation in Machine Learning: The Legality of Fairness Metrics Under EU Non-Discrimination Law [ tweet ]
• Why Fairness Cannot Be Automated: Bridging the Gap Between EU Non-Discrimination Law and AI
• What went wrong and when? Instance-wise Feature Importance for Time-series Models
• How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations
• The Limits of Computation in Solving Equity Trade-Offs in Machine Learning and Justice System Risk Assessment
• Towards the Right Kind of Fairness in AI
• Fairness assessment for artificial intelligence in financial industry
• BeFair: Addressing Fairness in the Banking Sector
• Improving Keyword Spotting and Language Identification via Neural Architecture Search at Scale [ github ] [ blog post ]
• Making Decisions that Reduce Discriminatory Impacts
• Designing Explanations for Group Recommender Systems
• Fairness, Semi-Supervised Learning, and More: A General Framework for Clustering with Stochastic Pairwise Constraints, AAAI 2021
• Estimating and Improving Fairness with Adversarial Learning

---