Machine learning models implemented in hardware on physical devices may be deployed for a long time. The computational abilities of the device may be limited and become outdated with respect to newer improvements. Because of the size of ML models, offloading some computation (e.g. to an edge cloud) can help such legacy devices. We cast this problem in the framework of learning with abstention (LWA) in which the expert (edge) must be trained to assist the client (device). Prior work on LWA trains the client assuming the edge is either an oracle or a human expert. In this work, we formalize the reverse problem of training the expert for a fixed (legacy) client. As in LWA, the client uses a rejection rule to decide when to offload inference to the expert (at a cost). We find the Bayes-optimal rule, prove a generalization bound, and find a consistent surrogate loss function. Empirical results show that our framework outperforms confidence-based rejection rules.

翻译：在物理设备上以硬件形式实现的机器学习模型可能长期部署。设备的计算能力可能有限，并随着新技术的改进而逐渐过时。由于机器学习模型的规模较大，将部分计算任务卸载（例如到边缘云）可以帮助此类遗留设备。我们将此问题置于带弃权学习框架中，其中专家（边缘）必须经过训练以协助客户端（设备）。先前关于带弃权学习的研究假设边缘为预言机或人类专家，并基于此训练客户端。在本工作中，我们形式化了针对固定（遗留）客户端训练专家的反向问题。与带弃权学习类似，客户端使用拒绝规则来决定何时将推理任务卸载给专家（需付出一定代价）。我们推导了贝叶斯最优规则，证明了泛化界，并找到了一个一致的代理损失函数。实证结果表明，我们的框架优于基于置信度的拒绝规则。