In the past decade, machine learning based decision systems have been widely used in a plethora of applications ranging from credit score, insurance risk, and health monitoring, in which accuracy is of the utmost importance. Although the application of these systems may bring myriad benefits, their use might involve some ethical and legal risks, such as codifying biases; jeopardizing transparency and privacy, reducing accountability. Unfortunately, these risks increase and are made more serious by the opacity of these systems, which often are complex and their internal logic is usually inaccessible to humans.
Nowadays most of the Artificial Intelligence (AI) systems are based on machine learning algorithms. The relevance and need of ethics in AI is supported and highlighted by the various initiatives that in the world provide recommendations and guidelines in the direction of making AI-based decision systems explainable and compliant with legal and ethical issues. These include the EU's GDPR regulation which introduces, to some extent, a right for all individuals to obtain ``meaningful explanations of the logic involved'' when automated decision making takes place, the ``ACM Statement on Algorithmic Transparency and Accountability'', the Informatics Europe's ``European Recommendations on Machine-Learned Automated Decision Making'' and ``The ethics guidelines for trustworthy AI'' provided by the EU High-Level Expert Group on AI.
The challenge to design and develop trustworthy AI-based decision systems is still open and requires a joint effort across technical, legal, sociological and ethical domains.
The purpose of XKDD, eXaplaining Knowledge Discovery in Data Mining, is to encourage principled research that will lead to the advancement of explainable, transparent, ethical and fair data mining and machine learning. The workshop will seek top-quality submissions addressing uncovered important issues related to ethical, explainable and transparent data mining and machine learning. Papers should present research results in any of the topics of interest for the workshop as well as application experiences, tools and promising preliminary ideas. XKDD asks for contributions from researchers, academia and industries, working on topics addressing these challenges primarily from a technical point of view, but also from a legal, ethical or sociological perspective. In the past decade, we have witnessed the increasing deployment of powerful automated decision-making systems in settings ranging from control of safety-critical systems to face detection on mobile phone cameras. Albeit remarkably powerful in solving complex tasks, these systems are typically completely obscure, i.e., they do not provide any mechanism to understand and explore their behavior and the reasons underlying the decisions taken.
Topics of interest include, but are not limited to:
- Explainable Artificial Intelligence
- Interpretable Machine Learning
- Transparent Data Mining
- Explainability in Clustering Analysis
- Technical Aspects of Algorithms for Explanation
- Explaining Black Box Decision Systems
- Adversarial Attack-based Models
- Counterfactual and Prototype-based Explanations
- Causal Discovery for Machine Learning Explanation
- Fairness Checking
- Fair Machine Learning
- Explanation for Privacy Risk
- Ethics Discovery for Explainable AI
- Privacy-Preserving Explanations
- Transparent Classification Approaches
- Anonymity and Information Hiding Problems in Comprehensible Models
- Case Study Analysis
- Experiments on Simulated and Real Decision Systems
- Monitoring and Understanding System Behavior
- Privacy Risk Assessment
- Privacy by Design Approaches for Human Data
- Statistical Aspects, Bias Detection and Causal Inference
- Explanation, Accountability and Liability from an Ethical and Legal Perspective
- Benchmarking and measuring explanation
- Visualization-based explanations
- Iterative dialogue explanations
Submissions with an interdisciplinary orientation are particularly welcome, e.g. works at the boundary between ML, AI, infovis, man-machine interfaces, psychology, etc. Research driven by application cases where interpretability matters are also of our interest, e.g., medical applications, decision systems in law and administrations, industry 4.0, etc.