Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Personalized Subgraph Federated Learning
Authors: Jinheon Baek, Wonyong Jeong, Jiongdao Jin, Jaehong Yoon, Sung Ju Hwang
ICML 2023 | Venue PDF | 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 <EMAIL>. |
| 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). |