Research

Research Group

I lead a research group in Trinity College Dublin focused on Reliable and Human-Centered Machine Learning. Currently, I supervise 3 PhD Students and several Masters Students.

Select Conferences and Journals

1. OxonFair: A Flexible Toolkit for Algorithmic Fairness. In NeurIPS 2024 Main Track. Eoin Delaney, Zihao Fu and Chris Russell.
2. Evaluating Model Explanations without Ground Truth. In FAccT 2025. Kai Rawal, Zihou Fu, Eoin Delaney and Chris Russell.
3. FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models. In NeurIPS 2025 Main Track. Zihao Fu, Ryan Brown, Shun Shao, Kai Rawal, Eoin Delaney, Chris Russell.
4. Counterfactual explanations for misclassified images: How human and machine explanations differ. Artificial Intelligence (Top AI Journal). Eoin Delaney, Arjun Pakrashi, Derek Greene and Mark T. Keane.
5. Instance-based Counterfactual Explanations for Time Series Classification. Best Student Paper
   29th International Conference on Case-Based Reasoning (ICCBR-21), Virtual, September 2021
   Eoin Delaney, Derek Greene and Mark T. Keane
6. If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques
   International Joint Conference on Artificial Intelligence (IJCAI-21), Montreal, August 2021
   Mark T. Keane, Eoin M. Kenny, Eoin Delaney, and Barry Smyth
7. Forecasting for Sustainable Dairy Produce: Enhanced Long-Term, Milk-Supply Forecasting Using k-NN for Data Augmentation, with Prefactual Explanations for XAI. Best Paper
   ICCBR-22
   Eoin Delaney, Derek Greene and Mark T. Keane
8. Nearest Neighbour-Based Data Augmentation for Time Series Forecasting. AICS-21.
   Duncan Wallace, Eoin Delaney, Mark T. Keane and Derek Greene

Workshops

1. Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions
   ICML (International Conference on Machine Learning) Workshop on Algorithmic Recourse, Vienna, July 2021
   Eoin Delaney, Derek Greene and Mark T. Keane
2. Twin Systems for DeepCBR: A Menagerie of Deep Learning and Case-Based Reasoning Pairings for Explanation and Data Augmentation
   DeepCBR Workshop (IJCAI-21), Virtual, August 2021
   Mark T. Keane, Eoin M. Kenny, Eoin Delaney, Mohammed Temraz, Derek Greene and Barry Smyth
3. Post-hoc Explanation Options for XAI in Deep Learning: The Insight Centre for Data Analytics Perspective.
   International Conference on Pattern Recognition (ICPR), Virtual, September 2021
   Mark T. Keane, Eoin M. Kenny, Eoin Delaney and Derek Greene

Activities

• I was awarded funding from the Central Bank of Ireland to support my research on XAI, including the recrutiment of a PhD Student.
• I organize the School of Computer Science and Statistics Seminar Series at Trinity College Dublin. We have lots of cool speakers lined up for 2026 such as Abeba Birhane from the AI Accountability Lab and Oisin Mac Aodha from the University of Edinburgh.
• I regularly serve on the program committee for conferences such as ACM FAccT, AIES, NeurIPS, ICCBR and workshops such as the Explainable Agency in Artificial Intelligence Workshop at AAAI.
• I serve as a reviewer for journals such as Data Mining and Knowledge Discovery and Artificial Intelligence.
• I organized a workshop on Auditing Accountability in Trustworthy Artificial Intelligence with Applications in Personalised Medicine. Big shout our and thanks to St Annes College Oxford and the GET team for helping me with this!
• I am honoured to receive the national award of Best Application of AI in a Student Project.
• I have recieved a scholarships from AIES and ICCBR to present my research.
• Check out the UCD Discovery podcast where I discuss my work on Counterfactual Explanations and the overconfident nature of many AI systems.