Decomposable Submodular Maximization in Federated Setting
Authors: Akbar Rafiey
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We present FE DCG, the first algorithm for decomposable submodular maximization in federated setting under matroid constraints. FEDCG is based on the continuous greedy algorithm and achieves the best possible approximation factor i.e., 1 - 1/e under mild assumptions even faced with client selection and low communication rounds. Additionally, we introduce a new federated framework for discrete problems. |
| Researcher Affiliation | Academia | 1Halıcıo glu Data Science Institute, University of California, San Diego, USA. |
| Pseudocode | Yes | Algorithm 1 Federated Continuous Greedy (FE DCG); Algorithm 2 Practical Fed CG (FE DCG+); Algorithm 3 Federated Discrete Greedy; Algorithm 4 Computing importance factors for Facility Location; Algorithm 5 Computing importance factors for Max Coverage |
| Open Source Code | No | The paper does not provide any statement about releasing source code or links to a code repository. |
| Open Datasets | No | The paper is theoretical and does not describe actual training on a dataset. Examples like the 'Movie Lens dataset' are mentioned as applications, not as datasets used for experiments within the paper. |
| Dataset Splits | No | The paper is theoretical and does not describe experimental validation, thus no dataset splits for validation are provided. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental hardware used. |
| Software Dependencies | No | The paper is theoretical and does not mention any specific software dependencies with version numbers relevant for empirical experiments. |
| Experiment Setup | No | The paper is theoretical and does not describe any specific experimental setup details, hyperparameters, or training configurations. |