Globally Consistent Federated Graph Autoencoder for Non-IID Graphs

Authors: Kun Guo, Yutong Fang, Qingqing Huang, Yuting Liang, Ziyao Zhang, Wenyu He, Liu Yang, Kai Chen, Ximeng Liu, Wenzhong Guo

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on real-world datasets demonstrate that GCFGAE achieves not only higher accuracy but also around 500 times lower communication overhead and 1000 times smaller space overhead than existing federated GNN models. ... We have conducted comprehensive experiments on privacy-preserving community detection, a typical unsupervised graph learning task, to evaluate the performance of GFGAE and baseline models.
Researcher Affiliation Academia 1College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China 2Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong 999077, China
Pseudocode No The paper describes the proposed model's framework and steps for forward and backward propagation but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes The source code of all models is written in Python 5. 5https://github.com/gcfgae/GCFGAE
Open Datasets Yes Five real-world networks are used in the experiments: (1) Cora: n=2708, m=5278, avgd=3.90, w=1433; (2) Citeseer: n=3264, m=4536, avgd=2.78, w=3703; (3) DBLP: n=1906, m=6644, avgd=6.97, w=45; (4) Amazon: n=2187, m=6413, avgd=5.86, w=480; (5) Lastfm: n=1215, m=5707, avgd=9.39, w=180, where n, m, avgd and w denote the number of vertices and links, the average degree and the dimension of attribute vectors of a network, respectively. We source Cora and Citeseer from LINQS 3 and DBLP, Amazon and Lastfm asia (abbreviated as Lastfm) from SNAP 4. 3https://linqs.soe.ucsc.edu/data 4http://snap.stanford.edu/data
Dataset Splits No The paper mentions splitting networks into 'overlapping subnetworks to simulate participants graphs' and using Kmeans for clustering evaluation with NMI and ARI metrics, but does not provide specific training/validation/test dataset splits or cross-validation details for model training and evaluation in the traditional supervised learning sense.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper states, 'The source code of all models is written in Python,' but it does not specify the version of Python or any other software libraries with their version numbers (e.g., PyTorch, TensorFlow, scikit-learn).
Experiment Setup No The paper describes the model architecture and training process but does not specify concrete experimental setup details such as hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings.