Multi-conditioned Graph Diffusion for Neural Architecture Search

arXiv:2403.06020v1 Announce Type: new
Abstract: Neural architecture search automates the design of neural network architectures usually by exploring a large and thus complex architecture search space. To advance the architecture search, we present a graph diffusion-based NAS approach that uses discrete conditional graph diffusion processes to generate high-performing neural network architectures. We then propose a multi-conditioned classifier-free guidance approach applied to graph diffusion networks to jointly impose constraints such as high accuracy and low hardware latency. Unlike the related work, …

abstract advance architecture architectures arxiv cs.cv cs.lg design diffusion generate graph nas network neural architecture search neural network processes search space type