About

I am a PhD Computing Research Student (started April 2022) at the Department of Computing of Imperial College London, supervised by Professor Francesca Toni and Dr Francesco Leofante, funded by the Interactive Explainable AI project. I’m also a TA at the Department of Computing and Imperial College Business School, helping with several AI / ML and programming courses.

From June to December 2024, I’ll intern as an AI Researcher at J.P. Morgan AI Research in London.

My research interest spans the spectrum of AI trustworthiness, including its explainability, robustness, fairness, privacy, etc. I’m focusing on counterfactual explanations (algorithmic recourse), robustness of explanations, and predictive multiplicity. Other projects I’m working on include explainability for graph neural networks and deep learning for Formula 1 race strategy.

Previously, I completed my MSc Computing degree from Imperial in 2021. I have two BEng degrees (2020), one from the University of Edinburgh where I did the last two years with a dissertation, and one from South China University of Technology where I spent the first two years.

Research

• Interval Abstractions for Robust Counterfactual Explanations
  J. Jiang, F. Leofante, A. Rago, F. Toni. 2024.

• Robust Counterfactual Explanations in Machine Learning: A Survey
  J. Jiang, F. Leofante, A. Rago, F. Toni. The 33rd International Joint Conference on Artificial Intelligence (IJCAI), Survey Track, 2024.

• Recourse under Model Multiplicity via Argumentative Ensembling
  J. Jiang*, A. Rago*, F. Leofante, F. Toni. The 23rd International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2024.

• Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation
  J. Jiang, J. Lan, F. Leofante, A. Rago, F. Toni. The 15th Asian Conference on Machine Learning (ACML), 2023.

• Formalising the Robustness of Counterfactual Explanations for Neural Networks
  J. Jiang*, F. Leofante*, A. Rago, F. Toni. The 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.

• Should Counterfactual Explanations Always Be Data Instances?
  J. Jiang, A. Rago, F. Toni. The 3rd Workshop on Explainable Logic-Based Knowledge Representation (XLoKR @ KR), 2022.

_{*equal contributions}