null
(Ed.)
Fairness in AI and Machine Learning is emerging to be a crucial research area to ensure social good. In contrast to offline working fashions, two research paradigms are devised for online learning: (1) Online Meta-Learning (OML learns good priors over model parameters (or learning to learn) in a sequential setting where tasks are revealed one after another. Although it provides a sub-linear regret bound, such techniques completely ignore the importance of learning with fairness which is a significant hallmark of human intelligence. (2) Online Fairness-Aware Learning that captures many classification problems for which fairness is a concern. But it aims to attain zero-shot generalization without any task-specific adaptation. This, therefore, limits the capability of a model to adapt to newly arrived data. To overcome such issues and bridge the gap, this paper is the first to propose a novel online meta-learning algorithm, namely FFML, which is under the setting of unfairness prevention. The key part of FFML is to learn good priors of an online fair classification model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The problem is formulated in the form of a bi-level convex-concave optimization. The theoretic analysis provides sub-linear upper bounds for loss regret and violation of cumulative fairness constraints. The experiments demonstrate the versatility of FFML by applying it to classification on three real-world datasets and show substantial improvements over the best prior work on the tradeoff between fairness and classification accuracy.
more »
« less