直接优化能耗，让表格数据模型更省电
Kernel-Level Energy-Efficient Neural Architecture Search for Tabular Dataset
- 不靠代理指标，直接搜索最低能耗的网络结构
- 在保持精度前提下，能耗最高降低92%
- 专为表格数据设计，适合低功耗应用场景
现有研究常通过内存占用、计算量（FLOPs）和推理延迟等代理指标估算能耗，假设降低这些指标即可减少实际能耗。本文提出一种面向表格数据的能耗感知神经架构搜索方法，不再依赖代理指标，而是直接优化能量消耗。与以往主要针对视觉和语言任务的方法不同，该方法专门适配表格数据。实验表明，所推荐的最佳架构相比传统NAS方法可降低高达92%的能耗，同时维持可接受的准确率。
原文摘要 · Abstract (English)
Many studies estimate energy consumption using proxy metrics like memory usage, FLOPs, and inference latency, with the assumption that reducing these metrics will also lower energy consumption in neural networks. This paper, however, takes a different approach by introducing an energy-efficient Neural Architecture Search (NAS) method that directly focuses on identifying architectures that minimize energy consumption while maintaining acceptable accuracy. Unlike previous methods that primarily target vision and language tasks, the approach proposed here specifically addresses tabular datasets. Remarkably, the optimal architecture suggested by this method can reduce energy consumption by up to 92% compared to architectures recommended by conventional NAS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。