Efficient Architecture Search under Leave-One-Subject-Out Evaluation

Deep neural architectures are widely used for signal processing in automated pain assessment systems. However, architecture design has remained largely a manual task despite the potential efficiency benefits of Neural Architecture Search (NAS). Embedding NAS in a Leave-One-Subject-Out (LOSO) evaluation is computationally demanding because a fully nested implementation requires N independent architecture searches and, assuming approximately linear training cost, scales as O(N 2). We propose a block-based, leakage-controlled approach that shares NAS runs between subjects, reducing the number of searches from N to B, where B N, dubbed PainNAS. On the BioVid Heat Pain dataset, PainNAS yields comparable subject-level accuracy with substantially fewer parameters and FLOPs.