Adaptive Fairness-Aware Online Meta-Learning for Changing Environments

05/20/2022
by   Chen Zhao, et al.
5

The fairness-aware online learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for the learner is to sequentially learn new tasks where they come one after another over time and the learner ensures the statistic parity of the new coming task across different protected sub-populations (e.g. race and gender). A major drawback of existing methods is that they make heavy use of the i.i.d assumption for data and hence provide static regret analysis for the framework. However, low static regret cannot imply a good performance in changing environments where tasks are sampled from heterogeneous distributions. To address the fairness-aware online learning problem in changing environments, in this paper, we first construct a novel regret metric FairSAR by adding long-term fairness constraints onto a strongly adapted loss regret. Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision. The problem is formulated in the form of a bi-level convex-concave optimization with respect to the model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The theoretic analysis provides sub-linear upper bounds for both loss regret and violation of cumulative fairness constraints. Our experimental evaluation on different real-world datasets with settings of changing environments suggests that the proposed FairSAOML significantly outperforms alternatives based on the best prior online learning approaches.

READ FULL TEXT

page 8

page 11

research
08/21/2021

Fairness-Aware Online Meta-learning

In contrast to offline working fashions, two research paradigms are devi...
research
05/31/2023

Towards Fair Disentangled Online Learning for Changing Environments

In the problem of online learning for changing environments, data are se...
research
09/29/2021

Dynamic Regret Analysis for Online Meta-Learning

The online meta-learning framework has arisen as a powerful tool for the...
research
06/11/2021

Online Continual Adaptation with Active Self-Training

Models trained with offline data often suffer from continual distributio...
research
11/06/2017

Online Learning for Changing Environments using Coin Betting

A key challenge in online learning is that classical algorithms can be s...
research
02/22/2019

Online Meta-Learning

A central capability of intelligent systems is the ability to continuous...
research
09/04/2023

Adaptive Resource Allocation for Virtualized Base Stations in O-RAN with Online Learning

Open Radio Access Network systems, with their virtualized base stations ...

Please sign up or login with your details

Forgot password? Click here to reset