Staff Profile
Dr Vlad Gonzalez
Lecturer in Computing
I am a Lecturer of Machine Learning and Data Science at Newcastle University, UK. My area of research is Responsible Artificial Intelligence (RAI), with a focus on algorithmic fairness and transparency. I have developed interpretable preprocessing methods to ensure distributive fairness in datasets, as well as a hybrid method to ensure fairness and data anonymisation. Currently I'm researching how to metricise and visualise procedural fairness. I am interested in interdisciplinary collaborations, particularly with people from the healthcare sector, but I'm open to collaborations in other research areas as well.
Most of my research has been on fairness, privacy and transparency for ML, nowadays referred to as Responsible AI (RAI). Specifically, I have designed algorithms that optimise group fairness for classification tasks through data preprocessing.
Some of my most relevant papers are:
- González, V., Salas, J., Prangle, D. & Missier, P. Optimising fairness through parametrised data sampling English. in Advances in Database Technology - EDBT 2021 (eds Velegrakis, Y., Velegrakis, Y., Zeinalipour, D., Chrysanthis, P., Chrysanthis, P. & Guerra, F. (OpenProceedings.org, Mar. 2021), 445–450.
- González, V. Towards Explaining the Effects of Data Preprocessing on Machine Learning in 2019 IEEE 35th International Conference on Data Engineering (ICDE) (2019), 2086–2090.
- González, V., Salas, J., Megías, D. & Missier, P. Fair and Private Data Preprocessing through Microaggregation. ACM Trans. Knowl. Discov. Data (TKDD) 18. issn: 1556-4681. https://doi.org/10.1145/3617377 (2023).
- González, V., Salas, J., Prangle, D. & Missier, P. Preprocessing matters: Automated pipeline selection for fair classification in International Conference on Modeling Decisions for Artificial Intelligence (2023), 202–213.
For a full list of my publications, check out my Google Scholar profile.
I have lectured since 2012, teaching the following subjects:
- Computing: Introductory Programming, Python Fundamentals, and Python for Research and Education
- Data Science: Data Analysis, Data Visualisation, and Machine Learning
- Mathematics: Calculus, Linear Algebra, Graph Theory, Logic, Statistics, and Operations Research
Next semester, I will be teaching Machine Learning for the Computer Science undergraduate program, as well as for the Degree Aprenticeship in Data Science program.
-
Articles
- Gonzalez-Zelaya V, Salas J, Megias D, Missier P. Fair and Private Data Preprocessing through Microaggregation. ACM Transactions on Knowledge Discovery from Data 2024, 18(3), 49.
- Toreini E, Aitken M, Coopamootoo K, Elliott K, Vladimiro GZ, Missier P, Ng M, van Moorsel A. Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context. IEEE Transactions on Technology and Society 2021. Submitted.
-
Conference Proceedings (inc. Abstract)
- Toreini E, Aitken M, Coopamootoo K, Elliott K, Zelaya CG, van Moorsel A. The relationship between trust in AI and trustworthy machine learning technologies. In: FAT* '20: 2020 Conference on Fairness, Accountability, and Transparency. 2020, Atlanta, GA, USA: ACM.