Federated Graph Semantic and Structural Learning

Authors: Wenke Huang, Guancheng Wan, Mang Ye, Bo Du

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results on three graph datasets manifest the superiority of the proposed method over counterparts. and 4 Experiments
Researcher Affiliation Academia 1School of Computer Science, Wuhan University, Wuhan, China 2 Hubei Luojia Laboratory, Wuhan, China {wenkehuang, guanchengwan, yemang, dubo}@whu.edu.cn
Pseudocode Yes Algorithm 1: The FGSSL Framework
Open Source Code No No explicit statement or link for open-source code release was found.
Open Datasets Yes Cora [Mc Callum et al., 2000] dataset consists of 2708 scientific publications classified into one of seven classes. ... Citeseer [Giles et al., 1998] dataset consists of 3312 scientific publications classified into one of six classes and 4732 edges. ... Pubmed [Sen et al., 2008] dataset consists of 19717 scientific papers on diabetes...
Dataset Splits Yes To conduct the experiments uniformly and fairly, we split the nodes into train/valid/test sets, where the ratio is 60% : 20% : 20% .
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory, cloud instance types) were mentioned for running experiments.
Software Dependencies No No specific software dependencies with version numbers were mentioned.
Experiment Setup Yes The hidden dimensions are 128 for all datasets, and classifier F maps the embedding from 128 dimensions to 7,6,3 dimensions, which is the number of classification classes for Cora, Citeseer, and Pubmed respectively. As for all networks, we use SGD [Robbins and Monro, 1951] as the selected optimizer with momentum 0.9 and weight decay 5e 4. The communication round is 200 and the local training epoch is 4 for all datasets.