SiGeo: Sub-One-Shot NAS via Geometry of Loss Landscape

Neural Architecture Search (NAS) has become a widely used tool for automating neural network design. While one-shot NAS methods have successfully reduced computational requirements, they often require extensive training. On the other hand, zero-shot NAS utilizes training-free proxies to evaluate a candidate architecture's test performance but has two limitations: (1) inability to use the information gained as a network improves with training and (2) unreliable performance, particularly in complex domains like RecSys, due to the multi-modal data inputs and complex architecture configurations. To synthesize the benefits of both methods, we introduce a "sub-one-shot" paradigm that serves as a bridge between zero-shot and one-shot NAS. In sub-one-shot NAS, the supernet is trained using only a small subset of the training data, a phase we refer to as "warm-up." Within this framework, we present SiGeo, a proxy founded on a novel theoretical framework that connects the supernet warm-up with the efficacy of the proxy. Extensive experiments have consistently shown that SiGeo, when properly warmed up, surpasses state-of-the-art NAS proxies in many established NAS benchmarks in the computer vision domain. Furthermore, when tested on recommendation system benchmarks, SiGeo demonstrates its ability to match the performance of state-of-the-art weight-sharing one-shot NAS methods while significantly reducing computational costs by approximately 60%.