论文标题
倾向于无回归的神经网络，用于不同的计算平台
Towards Regression-Free Neural Networks for Diverse Compute Platforms
论文作者
论文摘要
随着向设备深度学习的转变，确保在各种计算平台上的AI服务的一致行为变得非常重要。我们的工作解决了降低视力流动的预测不一致的紧急问题：由较少准确的模型正确预测但错误地预测的样本，但更准确。我们介绍了回归约束的神经体系结构搜索（Reg-NAS），以设计一个高度准确的模型家庭，这些模型会造成更少的负面流量。 Reg-NAS由两个组成部分组成：（1）一种新型的体系结构约束，使较大的模型包含较小的权重，从而最大化重量共享。这个想法源于我们观察到的，网络之间的重量较大会导致相似的样本预测，并导致负面量较少。 （2）一种新颖的搜索奖励，在体系结构搜索指标中均包含了TOP-1准确性和负面翻转。我们证明，\ regnas可以在三个流行的架构搜索空间中成功找到具有很少负面额的理想体系结构。与现有的最新方法相比，Reg-NAS可实现33-48％的负面流量相对减少。
With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important. Our work tackles the emergent problem of reducing predictive inconsistencies arising as negative flips: test samples that are correctly predicted by a less accurate model, but incorrectly by a more accurate one. We introduce REGression constrained Neural Architecture Search (REG-NAS) to design a family of highly accurate models that engender fewer negative flips. REG-NAS consists of two components: (1) A novel architecture constraint that enables a larger model to contain all the weights of the smaller one thus maximizing weight sharing. This idea stems from our observation that larger weight sharing among networks leads to similar sample-wise predictions and results in fewer negative flips; (2) A novel search reward that incorporates both Top-1 accuracy and negative flips in the architecture search metric. We demonstrate that \regnas can successfully find desirable architectures with few negative flips in three popular architecture search spaces. Compared to the existing state-of-the-art approach, REG-NAS enables 33-48% relative reduction of negative flips.
