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 [1].
FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation
Authors: Haozhao Wang, Haoran Xu, Yichen Li, Yuan Xu, Ruixuan Li, Tianwei Zhang
ICLR 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments conducted on various models and datasets reveal our approach outperforms state-of-the-art aggregation methods. and 6 EVALUATION |
| Researcher Affiliation | Academia | 1S-Lab, Nanyang Technological University 2Zhejiang University 3Department of Computer Science, Huazhong University of Science and Technology 4Nanyang Technological University |
| Pseudocode | Yes | Algorithm 1 Fed CDA Algorithm |
| Open Source Code | No | The paper does not contain an explicit statement about releasing the source code or a link to a code repository for the methodology described. |
| Open Datasets | Yes | Datasets and Models: We consider three popular datasets in experiments: Fashion-MNIST (Xiao et al., 2017), CIFAR-10 (Krizhevsky et al., 2009) and CIFAR-100 (Krizhevsky et al., 2009) |
| Dataset Splits | No | The paper describes data partitioning for federated learning among clients (Shards and Dirichlet distribution) but does not specify explicit training, validation, and test dataset splits (e.g., 80/10/10 percentages or counts) or mention a separate validation set. |
| Hardware Specification | Yes | We implement the whole experiment in a simulation environment based on Py Torch 2.0 and 8 NVIDIA Ge Force RTX 3090 GPUs. |
| Software Dependencies | Yes | We implement the whole experiment in a simulation environment based on Py Torch 2.0 and 8 NVIDIA Ge Force RTX 3090 GPUs. |
| Experiment Setup | Yes | We set the local epoch to 20, batch size to 64, and learning rate to 1e 3. We employ SGD optimizer with momentum of 1e 4 and weight decay of 1e 5 for all methods and datasets. |