FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning

Authors: Yinlin Zhu, Xunkai Li, Zhengyu Wu, Di Wu, Miao Hu, Rong-Hua Li

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on six public datasets consistently demonstrate the superiority of Fed TAD over state-of-the-art baselines. In this section, we conduct experiments to verify the effectiveness of Fed TAD.
Researcher Affiliation Academia 1Sun Yat-sen University, Guangzhou, China 2Beijing Institute of Technology, Beijing, China
Pseudocode Yes The complete algorithm of Fed TAD is presented in Algorithm 1.
Open Source Code No The paper does not provide an explicit statement about releasing source code or a link to a code repository.
Open Datasets Yes We perform experiments on six widely used public benchmark datasets in graph learning: three small-scale citation network datasets (Cora, Cite Seer, Pub Med [Yang et al., 2016]), two medium-scale co-author datasets (CS, Physics [Shchur et al., 2018]), and one large-scale OGB dataset (ogbn-arxiv [Hu et al., 2020]).
Dataset Splits No The paper mentions 'We perform the hyperparameter search for Fed TAD using the Optuna framework [Akiba et al., 2019]' but does not specify the training, validation, and test splits (e.g., percentages or exact counts) for the datasets used in the main experiments, which are necessary for reproducibility.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory specifications) used for running the experiments.
Software Dependencies No The paper mentions 'we perform the hyperparameter search for Fed TAD using the Optuna framework [Akiba et al., 2019]' but does not provide specific version numbers for Optuna or any other software dependencies crucial for replication.
Experiment Setup Yes The dimension of the hidden layer is set to 64 or 128. The local training epoch and round are set to 3 and 100, respectively. The learning rate of GNN is set to 1e-2, the weight decay is set to 5e-4, and the dropout is set to 0.5. Based on this, we perform the hyperparameter search for Fed TAD using the Optuna framework [Akiba et al., 2019] on λ1 and λ2 within {10 1, 10 2, 10 3}, and I, Ig, Id within {1, 3, 5, 10}.