对比3种新算法在公平性约束下的深度学习训练效果。
Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks
- 基于美国人口普查数据构建大规模公平性约束训练基准
- 实测3个未实现的新算法，验证其优化与公平性提升能力
- 开源代码工具包，支持公平性机器学习研究
训练具备约束条件的深度神经网络对提升现代机器学习模型的公平性至关重要。近年来虽有多种算法被提出，但尚无统一认可的约束训练方法。本文基于美国人口普查数据（Folktables）构建了具有挑战性的大规模真实世界公平性约束学习基准。我们指出了此类任务的理论难点，并回顾了随机逼近算法的主要方法。最后，通过实现并比较三种近期提出但尚未实现的算法，评估其在优化性能和公平性改进方面的表现。相关基准代码以Python包形式开源，地址为https://github.com/humancompatible/train。
原文摘要 · Abstract (English)
The ability to train Deep Neural Networks (DNNs) with constraints is instrumental in improving the fairness of modern machine-learning models. Many algorithms have been analysed in recent years, and yet there is no standard, widely accepted method for the constrained training of DNNs. In this paper, we provide a challenging benchmark of real-world large-scale fairness-constrained learning tasks, built on top of the US Census (Folktables). We point out the theoretical challenges of such tasks and review the main approaches in stochastic approximation algorithms. Finally, we demonstrate the use of the benchmark by implementing and comparing three recently proposed, but as-of-yet unimplemented, algorithms both in terms of optimization performance, and fairness improvement. We release the code of the benchmark as a Python package at https://github.com/humancompatible/train.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。