Learning by Grouping: A Multilevel Optimization Framework for Improving Fairness in Classification without Losing Accuracy

by   Ramtin Hosseini, et al.

The integration of machine learning models in various real-world applications is becoming more prevalent to assist humans in their daily decision-making tasks as a result of recent advancements in this field. However, it has been discovered that there is a tradeoff between the accuracy and fairness of these decision-making tasks. In some cases, these AI systems can be unfair by exhibiting bias or discrimination against certain social groups, which can have severe consequences in real life. Inspired by one of the most well-known human learning skills called grouping, we address this issue by proposing a novel machine learning framework where the ML model learns to group a diverse set of problems into distinct subgroups to solve each subgroup using its specific sub-model. Our proposed framework involves three stages of learning, which are formulated as a three-level optimization problem: (i) learning to group problems into different subgroups; (ii) learning group-specific sub-models for problem-solving; and (iii) updating group assignments of training examples by minimizing the validation loss. These three learning stages are performed end-to-end in a joint manner using gradient descent. To improve fairness and accuracy, we develop an efficient optimization algorithm to solve this three-level optimization problem. To further reduce the risk of overfitting in small datasets, we incorporate domain adaptation techniques in the second stage of training. We further apply our method to neural architecture search. Extensive experiments on various datasets demonstrate our method's effectiveness and performance improvements in both fairness and accuracy. Our proposed Learning by Grouping can reduce overfitting and achieve state-of-the-art performances with fixed human-designed network architectures and searchable network architectures on various datasets.


page 1

page 2

page 3

page 4


Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML

Machine learning (ML) is increasingly being used in critical decision-ma...

Two-stage Algorithm for Fairness-aware Machine Learning

Algorithmic decision making process now affects many aspects of our live...

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization

Many existing group fairness-aware training methods aim to achieve the g...

Small-Group Learning, with Application to Neural Architecture Search

Small-group learning is a broadly used methodology in human learning and...

Joint Fairness Model with Applications to Risk Predictions for Under-represented Populations

Under-representation of certain populations, based on gender, race/ethni...

Interleaving Learning, with Application to Neural Architecture Search

Interleaving learning is a human learning technique where a learner inte...

Learning by Examples Based on Multi-level Optimization

Learning by examples, which learns to solve a new problem by looking int...

Please sign up or login with your details

Forgot password? Click here to reset