Year: 2025
Type: conference-paper
Abstract: Group Fairness-aware Continual Learning (GFCL) aims to eradicate discriminatory predictions against certain demographic groups in a sequence of diverse learning tasks. This paper explores an even more challenging GFCL problem – how to sustain a fair classifier across a sequence of tasks with covariate shifts and unlabeled data. We propose the MacFRL solution, with its key idea to optimize the sequence of learning tasks. We hypothesize that high-confident learning can be enabled in the optimized task sequence, where the classifier learns from a set of prioritized tasks to glean knowledge, thereby becoming more capable to handle the tasks with substantial distribution shifts that were originally deferred. Theoretical and empirical studies substantiate that MacFRL excels among its GFCL competitors in terms of prediction accuracy and group fair-ness metrics.
Authors: Heng Lian, Chen Zhao, Zhong Chen, Xingquan Zhu, My T. Thai, Yi He
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
Open Access status: diamond
Funder: National Science Foundation
Awards: FAI: Towards a Computational Foundation for Fair Network Learning, Collaborative Research: PACSP TOOLS: EPICS: Explainable AI Driven Individual Photo-Identification and Tracking for Cost-effective Conservation Study, NSF-CSIRO: Towards Interpretable and Responsible Graph Modeling for Dynamic Systems, CRII: III: Pursuing Interpretability in Utilitarian Online Learning Models, Collaborative Research: III: Small: Taming Large-Scale Streaming Graphs in an Open World, Collaborative Research: III: Small: Taming Large-Scale Streaming Graphs in an Open World, Collaborative Research: SCH: Trustworthy and Explainable AI for Neurodegenerative Diseases, Collaborative Research: PACSP TOOLS: EPICS: Explainable AI Driven Individual Photo-Identification and Tracking for Cost-effective Conservation Study
OpenAlex ID: W4409363967