Personalized Subgraph Federated Learning

Authors: Jinheon Baek, Wonyong Jeong, Jiongdao Jin, Jaehong Yoon, Sung Ju Hwang

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

Reproducibility Variable Result LLM Response
Research Type Experimental We validate our FED-PUB for its subgraph FL performance on six datasets, considering both non-overlapping and overlapping subgraphs, on which it significantly outperforms relevant baselines.
Researcher Affiliation Academia 1KAIST. Correspondence to: Jinheon Baek, and Sung Ju Hwang <{jinheon.baek, sjhwang82}@kaist.ac.kr>.
Pseudocode Yes Algorithm 1 FED-PUB Client Algorithm
Open Source Code Yes Our code is available at https://github.com/JinheonBaek/FED-PUB.
Open Datasets Yes Specifically, we use six datasets: Cora, Cite Seer, Pubmed and ogbn-arxiv for citation graphs (Sen et al., 2008; Hu et al., 2020); Computer and Photo for product graphs (Mc Auley et al., 2015; Shchur et al., 2018).
Dataset Splits Yes For dataset splits, we randomly sample 20% nodes for training, 35% for validation, and 35% for testing, for all datasets except for the arxiv dataset.
Hardware Specification Yes We use two types of GPUs: Ge Force RTX 2080 Ti and TITAN XP, for training models.
Software Dependencies No The paper mentions 'Py Torch (Paszke et al., 2019) and Py Torch Geometric (Fey & Lenssen, 2019)' but does not specify their version numbers or any other software dependencies with version numbers.
Experiment Setup Yes Regarding hyperparameters, the number of hidden dimensions is set to 128, and the learning rate is set to 0.001. All models are optimized with Adam optimizer (Kingma & Ba, 2015).