Node-wise Diffusion for Scalable Graph Learning

Keke Huang, Jing Tang, Juncheng Liu, Renchi Yang, Xiaokui Xiao

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

2 Citations (Scopus)

Abstract

Graph Neural Networks (GNNs) have shown superior performance for semi-supervised learning of numerous web applications, such as classification on web services and pages, analysis of online social networks, and recommendation in e-commerce. The state of the art derives representations for all nodes in graphs following the same diffusion (message passing) model without discriminating their uniqueness. However, (i) labeled nodes involved in model training usually account for a small portion of graphs in the semi-supervised setting, and (ii) different nodes locate at different graph local contexts and it inevitably degrades the representation qualities if treating them undistinguishedly in diffusion. To address the above issues, we develop NDM, a universal node-wise diffusion model, to capture the unique characteristics of each node in diffusion, by which NDM is able to yield high-quality node representations. In what follows, we customize NDM for semi-supervised learning and design the NIGCN model. In particular, NIGCN advances the efficiency significantly since it (i) produces representations for labeled nodes only and (ii) adopts well-designed neighbor sampling techniques tailored for node representation generation. Extensive experimental results on various types of web datasets, including citation, social and co-purchasing graphs, not only verify the state-of-the-art effectiveness of NIGCN but also strongly support the remarkable scalability of NIGCN. In particular, NIGCN completes representation generation and training within 10 seconds on the dataset with hundreds of millions of nodes and billions of edges, up to orders of magnitude speedups over the baselines, while achieving the highest F1-scores on classification.

Original languageEnglish
Title of host publicationWWW '23
Subtitle of host publicationProceedings of the ACM Web Conference 2023
EditorsYing Ding, Jie Tang, Juan Sequeda, Lora Aroyo, Carlos Castillo, Geert-Jan Houben
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Pages1723-1733
Number of pages11
Edition1st
ISBN (Print)9781450394161
DOIs
Publication statusPublished - 30 Apr 2023
Event2023 World Wide Web Conference, WWW 2023 - AT&T Hotel and Conference Center at The University of Texas at Austin, Austin, United States
Duration: 30 Apr 20234 May 2023
https://www2023.thewebconf.org/program/detailed-program/
https://dl.acm.org/doi/proceedings/10.1145/3543507

Publication series

NameProceedings of the International World Wide Web Conference
PublisherAssociation for Computing Machinery

Conference

Conference2023 World Wide Web Conference, WWW 2023
Country/TerritoryUnited States
CityAustin
Period30/04/234/05/23
Internet address

Scopus Subject Areas

  • Computer Networks and Communications
  • Software

User-Defined Keywords

  • graph neural networks
  • scalability
  • semi-supervised classifcation

Fingerprint

Dive into the research topics of 'Node-wise Diffusion for Scalable Graph Learning'. Together they form a unique fingerprint.

Cite this