Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision

TL;DR

This paper introduces DSGAS, an unsupervised method for discovering optimal graph neural network architectures by disentangling latent graph factors using self-supervision, without relying on labeled data.

Contribution

The paper proposes a novel disentangled self-supervised framework for GNAS that captures multiple latent factors and performs architecture search without supervision.

Findings

Achieves state-of-the-art results on 11 datasets

Effectively disentangles graph factors in architecture search

Operates without labeled supervision

Abstract

The existing graph neural architecture search (GNAS) methods heavily rely on supervised labels during the search process, failing to handle ubiquitous scenarios where supervisions are not available. In this paper, we study the problem of unsupervised graph neural architecture search, which remains unexplored in the literature. The key problem is to discover the latent graph factors that drive the formation of graph data as well as the underlying relations between the factors and the optimal neural architectures. Handling this problem is challenging given that the latent graph factors together with architectures are highly entangled due to the nature of the graph and the complexity of the neural architecture search process. To address the challenge, we propose a novel Disentangled Self-supervised Graph Neural Architecture Search (DSGAS) model, which is able to discover the optimal architectures capturing various latent graph factors in a self-supervised fashion based on unlabeled graph data. Specifically, we first design a disentangled graph super-network capable of incorporating multiple architectures with factor-wise disentanglement, which are optimized simultaneously. Then, we estimate the performance of architectures under different factors by our proposed self-supervised training with joint architecture-graph disentanglement. Finally, we propose a contrastive search with architecture augmentations to discover architectures with factor-specific expertise. Extensive experiments on 11 real-world datasets demonstrate that the proposed model is able to achieve state-of-the-art performance against several baseline methods in an unsupervised manner.