E2EG: End-to-End Node Classification Using Graph Topology and Text-based Node Attributes

Tu Anh Dinh, Jeroen Den Boef, Joran Cornelisse, Paul Groth

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Node classification utilizing text-based node attributes has many real-world applications, ranging from prediction of paper topics in academic citation graphs to classification of user characteristics in social media networks. State-of-the-art node classification frameworks, such as GIANT, use a two-stage pipeline: first embedding the text attributes of graph nodes then feeding the resulting embeddings into a node classification model. In this paper, we eliminate these two stages and develop an end-to-end node classification model that builds upon GIANT, called End-to-End-GIANT (E2EG). The tandem utilization of a main and an auxiliary classification objectives in our approach results in a more robust model, enabling the BERT backbone to be switched out for a distilled encoder with a 25% - 40% reduction in the number of parameters. Moreover, the model's end-to-end nature increases ease of use, as it avoids the need of chaining multiple models for node classification. Compared to a GIANT+MLP baseline on the ogbn-arxiv and ogbn-products datasets, E2EG obtains slightly better accuracy in the transductive setting (+0.5%), while reducing model training time by up to 40%. Our model is also applicable in the inductive setting, outperforming GIANT+MLP by up to +2.23%.

Original languageEnglish
Title of host publicationProceedings - 23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
EditorsJihe Wang, Yi He, Thang N. Dinh, Christan Grant, Meikang Qiu, Witold Pedrycz
PublisherIEEE Computer Society
Pages1084-1091
Number of pages8
ISBN (Electronic)9798350381641
DOIs
StatePublished - 2023
Externally publishedYes
Event23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023 - Shanghai, China
Duration: Dec 1 2023Dec 4 2023

Publication series

NameIEEE International Conference on Data Mining Workshops, ICDMW
ISSN (Print)2375-9232
ISSN (Electronic)2375-9259

Conference

Conference23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
Country/TerritoryChina
CityShanghai
Period12/1/2312/4/23

Keywords

  • end-to-end
  • multi-task learning
  • node classification
  • transfer learning

Fingerprint

Dive into the research topics of 'E2EG: End-to-End Node Classification Using Graph Topology and Text-based Node Attributes'. Together they form a unique fingerprint.

Cite this