论文标题
依赖阶级的置信度在物联网节点上的节能自适应机器学习
Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence
论文作者
论文摘要
可以直接在边缘设备上运行的节能机器学习模型对物联网应用非常感兴趣，因为它们可以减少网络压力和响应延迟，并提高隐私。以较小的精度降低获得省力效率的一种有效方法是依次执行一组日益复杂的模型，并在“简易”输入的过程中暂停了可以通过最小模型对“易于”输入的过程。作为停止标准，当前方法对每个模型产生的输出概率采用单个阈值。在这项工作中，我们表明，此类标准对于包括不同复杂性类别的数据集来说是最佳的，并且我们基于每个级别的阈值演示了一种更通用的方法。通过对低功率端节点进行的实验，我们表明我们的方法可以显着减少与单阈值方法相比的能源消耗。
Energy-efficient machine learning models that can run directly on edge devices are of great interest in IoT applications, as they can reduce network pressure and response latency, and improve privacy. An effective way to obtain energy-efficiency with small accuracy drops is to sequentially execute a set of increasingly complex models, early-stopping the procedure for "easy" inputs that can be confidently classified by the smallest models. As a stopping criterion, current methods employ a single threshold on the output probabilities produced by each model. In this work, we show that such a criterion is sub-optimal for datasets that include classes of different complexity, and we demonstrate a more general approach based on per-classes thresholds. With experiments on a low-power end-node, we show that our method can significantly reduce the energy consumption compared to the single-threshold approach.
