Multi-conditioned Graph Diffusion for Neural Architecture Search

TL;DR

This paper introduces a differentiable graph diffusion-based neural architecture search method that efficiently generates high-performance architectures with constraints like low latency, demonstrating fast speed and strong results on multiple benchmarks.

Contribution

The paper proposes a novel, fully differentiable graph diffusion approach for neural architecture search that requires only one training process and effectively incorporates multiple constraints.

Findings

Achieves high-quality architectures in less than 0.2 seconds per architecture.

Demonstrates strong performance on six standard benchmarks.

Shows good generalizability and efficiency on ImageNet.

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, our method is completely differentiable and requires only a single model training. In our evaluations, we show promising results on six standard benchmarks, yielding novel and unique architectures at a fast speed, i.e. less than 0.2 seconds per architecture. Furthermore, we demonstrate the generalisability and efficiency of our method through experiments on ImageNet dataset.