humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems
This work provides a practical tool for researchers and practitioners in machine learning, particularly for applications like fairness and safety, but it is incremental as it builds on existing constrained training methods.
The authors tackled the lack of an industry standard toolkit for training deep neural networks with stochastic constraints by introducing humancompatible.train, an extendable PyTorch-based package that implements multiple previously unimplemented algorithms and demonstrates their use in a fairness-constrained deep learning task.
There has been a considerable interest in constrained training of deep neural networks (DNNs) recently for applications such as fairness and safety. Several toolkits have been proposed for this task, yet there is still no industry standard. We present humancompatible.train (https://github.com/humancompatible/train), an easily-extendable PyTorch-based Python package for training DNNs with stochastic constraints. We implement multiple previously unimplemented algorithms for stochastically constrained stochastic optimization. We demonstrate the toolkit use by comparing two algorithms on a deep learning task with fairness constraints.