I am an Applied Scientist intern at Amazon Luxembourg working 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.
My PhD thesis involved constructing Knowledge Graph datasets with ground truth explanations, evaluating the quality of explanations generated by current models, and designing new models to generating explanations.
LinkedIn
Twitter
Google Scholar
Github
Email: halliwelln@protonmail.com
-Explainable AI
-Machine Learning
-Deep Learning
-AGI
N. Halliwell, F. Gandon, and F. Lecue. A Simplified Benchmark for Ambiguous Explanations of Knowledge Graph Link Prediction using Relational Graph Convolutional Networks. 36th AAAI Conference on Artificial Intelligence, Feb. 2022a. URL https://hal.archives-ouvertes.fr/hal-03434544.
N. Halliwell. Evaluating Explanations of Relational Graph Convolutional Network Link Predictions on Knowledge Graphs. In AAAI 2022 - 36th AAAI Conference on Artificial Intelligence, Vancouver, Canada, Feb. 2022. URL https://hal.archives-ouvertes.fr/hal-03454121.
N. Halliwell, F. Gandon, F. Lecue, and S. Villata. The Need for Empirical Evaluation of Explanation Quality. In AAAI 2022 - Workshop on Explainable Agency in Artificial Intelligence, Vancouver, Canada, Feb. 2022b. URL https://hal.archives-ouvertes.fr/hal-03591012.
N. Halliwell, F. Gandon, and F. Lecue. User Scored Evaluation of Non-Unique Explanations for Relational Graph Convolutional Network Link Prediction on Knowledge Graphs. In International Conference on Knowledge Capture, Virtual Event, United States, Dec. 2021b. URL https://hal.archives-ouvertes.fr/hal-03402766.
N. Halliwell, F. Gandon, and F. Lecue. A Simplified Benchmark for Non- ambiguous Explanations of Knowledge Graph Link Prediction using Relational Graph Convolutional Networks. International Semantic Web Conference, Oct.2021a. URL https://hal.archives-ouvertes.fr/hal-03339562.
N. Halliwell, F. Gandon, and F. Lecue. Linked Data Ground Truth for Quantitative and Qualitative Evaluation of Explanations for Relational Graph Convolutional Network Link Prediction on Knowledge Graphs. In International Conference on Web Intelligence and Intelligent Agent Technology, Melbourne, Australia, Dec. 2021c. URL https://hal.archives-ouvertes.fr/hal-03430113.
N. Halliwell, F. Gandon, and F. Lecue. Impact of Injecting Ground Truth Explanations on Relational Graph Convolutional Networks and their Explanation Methods for Link Prediction on Knowledge Graphs. In International Conference on Web Intelligence and Intelligent Agent Technology, Niagara Falls, Canada, Nov. 2022b. URL https://hal.archives-ouvertes.fr/hal-03771424.