Nicholas Halliwell

I am a former Applied Scientist intern at Amazon Luxembourg where I worked on transportation execution.

Previously I was a PhD student in Computer Science at Université Côte d’Azur, on the WIMMICS team at Inria-Sophia Antipolis (France).

My research interests include understanding and interpreting the decisions made by black box machine learning models, and creating machine learning models with generalizable intelligence.

My PhD thesis involved constructing Knowledge Graph datasets with ground truth explanations, evaluating the quality of explanations generated by current models, and designing new algorithms to generating explanations.

In my free time, I write a basketball data science blog: Backcourt Analytics.

LinkedIn
Twitter
Google Scholar
Github

Email: halliwelln@protonmail.com

Research interests:

-Explainable AI
-Machine Learning
-Deep Learning
-AGI

Publications

• Nicholas Halliwell, Fabien Gandon, Freddy Lecue (2021)
  “User Scored Evaluation of Non-Unique Explanations for Relational Graph Convolutional Network Link Prediction.”
  International Conference on Knowledge Capture
  Link

• Nicholas Halliwell, Fabien Gandon, Freddy Lecue, Serena Villata (2022)
  “The Need for Empirical Evaluation of Explanation Quality.”
  AAAI Workshop on Explainable Agency in Artificial Intelligence
  Link

• Nicholas Halliwell (2022)
  “Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs.”
  36th AAAI Conference on Artificial Intelligence
  Link

• Nicholas Halliwell, Fabien Gandon, Freddy Lecue (2022)
  “A Simplified Benchmark for Ambiguous Explanations of Knowledge Graph Link Prediction using Relational Graph Convolutional Networks.”
  36th AAAI Conference on Artificial Intelligence
  Link

• Nicholas Halliwell, Fabien Gandon, Freddy Lecue (2022)
  “Impact of Injecting Ground Truth Explanations on Relational Graph Convolutional Networks.”
  International Conference on Web Intelligence and Intelligent Agent Technology
  Link

• Nicholas Halliwell, Fabien Gandon, Freddy Lecue (2021)
  “A Simplified Benchmark for Non-Ambiguous Explanations of Knowledge Graph Link Prediction.”
  International Semantic Web Conference
  Link

• Nicholas Halliwell, Fabien Gandon, Freddy Lecue (2021)
  “Linked Data Ground Truth for Evaluation of Explanations in Knowledge Graph Link Prediction.”
  International Conference on Web Intelligence and Intelligent Agent Technology
  Link