GNN2GNN: Graph Neural Networks to Generate Neural Networks


pagemagnifierBibTeX_logo.pngmagnifierpage_white_acrobatmagnifier

Andrea Agiollo, Andrea Omicini

James Cussens, Kun Zhang (eds.)
“Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022)”, pages 32-42
Proceedings of Machine Learning Research 180
ML Research Press
August 2022

The success of neural networks (NNs) is tightly linked with their architectural design—a complex problem by itself. We here introduce a novel framework leveraging Graph Neural Networks to Generate Neural Networks (GNN2GNN) where powerful NN architectures can be learned out of a set of available architecture-performance pairs. GNN2GNN relies on a three-way adversarial training of GNN, to optimise a generator model capable of producing predictions about powerful NN architectures. Unlike Neural Architecture Search (NAS) techniques proposing efficient searching algorithms over a set of NN architectures, GNN2GNN relies on learning NN architectural design criteria. GNN2GNN learns to propose NN architectures in a single step – i.e., training of the generator –, overcoming the recursive approach characterising NAS. Therefore, GNN2GNN avoids the expensive and inflexible search of efficient structures typical of NAS approaches. Extensive experiments over two state-of-the-art datasets prove the strength of our framework, showing that it can generate powerful architectures with high probability. Moreover, GNN2GNN outperforms possible counterparts for generating NN architectures, and shows flexibility against dataset quality degradation. Finally, GNN2GNN paves the way towards generalisation between datasets.

(keywords) Graph Neural Networks, Neural Architecture Search, Generative Adversarial Networks

Talks

Journals & Series

Events

  • 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022) — 01/08/2022–05/08/2022

Tags:

Publication

— authors

— editors

James Cussens, Kun Zhang

— status

published

— sort

paper in proceedings

— publication date

August 2022

— volume

Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022)

— series

Proceedings of Machine Learning Research

— volume

180

— pages

32-42

— number of pages

11

URLs

original page  |  open access PDF

identifiers

— DBLP

conf/uai/AgiolloO22

— IRIS

11585/899465

— Scholar

3643983533846865361

— print ISSN

2640-3498

files

Open Access PDF

Partita IVA: 01131710376 — Copyright © 2008–2023 APICe@DISI – PRIVACY