Single-shot General Hyper-parameter Optimization for Federated Learning
Authors: Yi Zhou, Parikshit Ram, Theodoros Salonidis, Nathalie Baracaldo, Horst Samulowitz, Heiko Ludwig
ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our empirical evaluation of FLo RA for multiple FL algorithms on seven Open ML datasets demonstrates significant model accuracy improvements over the baselines, and robustness to increasing number of parties involved in FL-HPO training. |
| Researcher Affiliation | Industry | Y. Zhou, P. Ram, T. Salonidis, N. Baracaldo, H. Samulowitz, H. Ludwig IBM Research {yi.zhou, parikshit.ram}@ibm.com, {tsaloni, baracald, samulowitz, hludwig}@us.ibm.com |
| Pseudocode | Yes | Algorithm 1 FL-HPO with FLo RA |
| Open Source Code | Yes | The code and instructions to reproduce our numerical results can be found in supplemental materials. |
| Open Datasets | Yes | Our empirical evaluation of FLo RA for multiple FL algorithms on seven Open ML datasets demonstrates significant model accuracy improvements over the baselines, and robustness to increasing number of parties involved in FL-HPO training. |
| Dataset Splits | Yes | For the local per-party HPOs (as well as the centralized HPO we execute to compute the regret), we maximize the 10-fold cross-validated balanced accuracy. |
| Hardware Specification | No | The paper does not provide specific details on hardware used for running experiments, such as GPU/CPU models or cloud instance types. |
| Software Dependencies | No | The paper mentions software like "scikit-learn implementations", "IBM FL library", and "XGBoost" but does not provide specific version numbers for these software dependencies. |
| Experiment Setup | Yes | We use the search space definition used in the Neur IPS 2020 Black-box optimization challenge... For the Hist Gradient Boosting Classifier in scikit-learn: api_config = { "max_iter": {"type": "int", "space": "linear", "range": (10, 200)}, "learning_rate": {"type": "real", "space": "log", "range": (1e-3, 1.0)}, "min_samples_leaf": {"type": "int", "space": "linear", "range": (1, 40)}, "l2_regularization": {"type": "real", "space": "log", "range": (1e-4, 1.0)}, } |