COMP2261 - Bias in AI Module


The physical classes for this module are going to be as follows:


For each lecture session, you should read a paper (as listed below). I will use this paper as the basis of the discussions in the session. I know reading a paper can be boring and tedious sometime but here is an instruction (I guess it is rather trivial) on how to read a paper.

The overall summary and learning objectives of the module is available in here.

Date Session Topic Reading Additional sources
1 Discrimination in law and society The impact of AI on business and society (2020) Independent UK government report into bias in algorithmic decision-making (2020)
2 Trust issues of Artificial Intelligence The relationship between trust in AI and trustworthy machine learning technologies (2020) Creating Trustworthy AI (2020)
3 Sources and causes of machine bias A Survey on Bias and Fairness in Machine Learning (2021) A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle (2021)
Coursework release
4 Mathematics of fairness On Formalizing Fairness in Prediction with Machine Learning (2018)
5 Mathematics of fairness (cont.) On the apparent conflict between individual and group fairness (2020) Machine learning fairness notions: Bridging the gap with real-world applications (2021)
6 Fair machine learning + pre-processing methods Data preprocessing techniques for classification without discrimination (2012)
7 inProcessing methods Fairness-aware Classifier with Prejudice Remover Regularizer (2012) Learning Adversarially Fair and Transferable Representations (2018)
8 Post-processing methods Equality of Opportunity in Supervised Learning (2016)
9 Counterfactual fairness Counterfactual Fairness (2017)
10 Fairness mitigation in action Addressing bias in big data and AI for health care: A call for open science (2021) Delayed Impact of Fair Machine Learning (2018)

Book Recommendations

Our discussion will be guided by papers, monographs, and lecture notes that are available online. Recommended (online) textbook: Barocas, Solon, Moritz Hardt, and Arvind Narayanan. Fairness and Machine Learning , 2018, Available online:

Time Management



This submodule is assessed by a piece of summative coursework.

© Ehsan Toreini