Innovation
Methods, ideas, or system contributions that make the work stand out.
leakage-free
block-based approach
shared NAS runs
Efficient Leakage-Free Neural Architecture Search under Leave-One-Subject-Out Evaluation
🤖 AI Summary
为解决LOSO评估下NAS计算成本高问题，提出一种无泄漏、基于块的方法共享跨主体NAS运行，提高准确率并大幅减少参数。
📝 Abstract
Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS) computationally expensive because a fully nested implementation requires N independent architecture searches and, assuming approximately linear training cost, scales as O(N^2). We propose a leakage-free, block-based approach that shares NAS runs across subjects. On the BioVid Heat Pain dataset, our approach increased the mean accuracy from 82.79% to 83.39% while reducing the number of parameters by up to 99.2%.
🔎 Similar Papers
2024-05-02arXiv.orgCitations: 1
Optimizing Time Series Forecasting Architectures: A Hierarchical Neural Architecture Search Approach
2024-06-07arXiv.orgCitations: 0
