PaSca: A Graph Neural Architecture Search System under the Scalable Paradigm

33Citations
Citations of this article
34Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Graph neural networks (GNNs) have achieved state-of-the-art performance in various graph-based tasks. However, as mainstream GNNs are designed based on the neural message passing mechanism, they do not scale well to data size and message passing steps. Although there has been an emerging interest in the design of scalable GNNs, current researches focus on specific GNN design, rather than the general design space, limiting the discovery of potential scalable GNN models. This paper proposes PaSca, a new paradigm and system that offers a principled approach to systemically construct and explore the design space for scalable GNNs, rather than studying individual designs. Through deconstructing the message passing mechanism, PaSca presents a novel Scalable Graph Neural Architecture Paradigm (SGAP), together with a general architecture design space consisting of 150k different designs. Following the paradigm, we implement an auto-search engine that can automatically search well-performing and scalable GNN architectures to balance the trade-off between multiple criteria (e.g., accuracy and efficiency) via multi-objective optimization. Empirical studies on ten benchmark datasets demonstrate that the representative instances (i.e., PaSca-V1, V2, and V3) discovered by our system achieve consistent performance among competitive baselines. Concretely, PaSca-V3 outperforms the state-of-the-art GNN method JK-Net by 0.4% in terms of predictive accuracy on our large industry dataset while achieving up to 28.3 × training speedups.

Cite

CITATION STYLE

APA

Zhang, W., Shen, Y., Lin, Z., Li, Y., Li, X., Ouyang, W., … Cui, B. (2022). PaSca: A Graph Neural Architecture Search System under the Scalable Paradigm. In WWW 2022 - Proceedings of the ACM Web Conference 2022 (pp. 1817–1828). Association for Computing Machinery, Inc. https://doi.org/10.1145/3485447.3511986

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free