Fairness warnings and fair-MAML: learning fairly with minimal data
Fairness warnings and fair-MAML: learning fairly with minimal data
复制标题
DOI：
10.1145/3351095.3372839
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Dylan Slack;Sorelle A. Friedler;Emile Givental
中科院分区：
文献类型：
--
作者：
Dylan Slack;Sorelle A. Friedler;Emile Givental
出于对共享和转移公平机器学习工具的公平性影响的担忧，我们提出了两种算法：公平警告和 Fair-MAML。第一个是与模型无关的算法，当训练有素的模型在给定域内的类似但略有不同的任务上可能表现不佳时，它提供可解释的边界条件。第二个是公平的元学习方法来训练模型，可以仅从少量样本实例快速微调到特定任务，同时平衡公平性和准确性。我们使用相关基线通过实验证明了每个模型的单独效用，并为我们对 K-shot 公平性的了解提供了第一个实验，即仅使用 K 个数据点在新任务上训练公平模型。然后，我们说明了这两种算法作为从新任务的一些数据点训练模型的组合方法的有用性，同时使用公平警告作为可解释的边界条件，在该边界条件下新训练的模型可能不公平。
Motivated by concerns surrounding the fairness effects of sharing and transferring fair machine learning tools, we propose two algorithms: Fairness Warnings and Fair-MAML. The first is a model-agnostic algorithm that provides interpretable boundary conditions for when a fairly trained model may not behave fairly on similar but slightly different tasks within a given domain. The second is a fair meta-learning approach to train models that can be quickly fine-tuned to specific tasks from only a few number of sample instances while balancing fairness and accuracy. We demonstrate experimentally the individual utility of each model using relevant baselines and provide the first experiment to our knowledge of K-shot fairness, i.e. training a fair model on a new task with only K data points. Then, we illustrate the usefulness of both algorithms as a combined method for training models from a few data points on new tasks while using Fairness Warnings as interpretable boundary conditions under which the newly trained model may not be fair.