Is Averaging Always the Best? Improving Aggregation Method for Federated Knowledge Graph Embedding

  • Yuanyi Liu*
  • , Renyu Zhang
  • , Jia Chen
  • *Corresponding author for this work

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

Abstract

In recent years, along with the rapid development of big data and AI technologies, knowledge graphs have also experienced significant growth. The vectorized representation of entities and relations in knowledge graphs has proven beneficial for various knowledge graph-related applications. However, traditional knowledge graph embedding methods are designed for centralized graphs, which cannot effectively represent the distributed knowledge graphs in real-world while ensuring data security. In this paper, we improve the aggregation method for federated knowledge graph embedding and propose a Federated knowledge graph embedding model with CompGCN, which is called FedComp for short. FedComp is an innovative server-client framework which implement CompGCN for federated KGE, along with the design of three novel aggregation methods. We conduct link prediction experiments on two datasets to demonstrate the performance of our model.

Original languageEnglish
Title of host publicationICNSC 2023 - 20th IEEE International Conference on Networking, Sensing and Control
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350369502
DOIs
StatePublished - 2023
Event20th IEEE International Conference on Networking, Sensing and Control, ICNSC 2023 - Marseille, France
Duration: 25 Oct 202327 Oct 2023

Publication series

NameICNSC 2023 - 20th IEEE International Conference on Networking, Sensing and Control

Conference

Conference20th IEEE International Conference on Networking, Sensing and Control, ICNSC 2023
Country/TerritoryFrance
CityMarseille
Period25/10/2327/10/23

Keywords

  • Aggregation Algorithm
  • CompGCN
  • FedE
  • Federated Learning
  • Knowledge Graph Embedding (KGE)

Fingerprint

Dive into the research topics of 'Is Averaging Always the Best? Improving Aggregation Method for Federated Knowledge Graph Embedding'. Together they form a unique fingerprint.

Cite this