Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach
Authors: Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we numerically study the role of personalization when the data distributions are heterogeneous. In particular, we consider the multi-class classification problem over MNIST [43] and CIFAR-10 [44] datasets and distribute the training data between n users as follows: ... The test accuracy results along with the 95% confidence intervals are reported in Table 1. |
| Researcher Affiliation | Academia | Alireza Fallah EECS Department Massachusetts Institute of Technology Cambridge, MA 02139 afallah@mit.edu Aryan Mokhtari ECE Department University of Texas at Austin Austin, TX 78712 mokhtari@austin.utexas.edu Asuman Ozdaglar EECS Department Massachusetts Institute of Technology Cambridge, MA 02139 asuman@mit.edu |
| Pseudocode | Yes | Algorithm 1: The proposed Personalized Fed Avg (Per-Fed Avg) Algorithm |
| Open Source Code | No | The paper states |
| Open Datasets | Yes | In particular, we consider the multi-class classification problem over MNIST [43] and CIFAR-10 [44] datasets |
| Dataset Splits | No | The paper mentions distributing training data and dividing test data, but it does not specify a distinct validation set or its split percentage for hyperparameter tuning or model selection. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions |
| Experiment Setup | Yes | We use a neural network with two hidden layers with sizes 80 and 60, and we use Exponential Linear Unit (ELU) activation function. We take n = 50 users in the network, and run all three algorithms for K = 1000 rounds. At each round, we assume rn agents with r = 0.2 are chosen to run τ local updates. The batch sizes are D = D = 40 and the learning rate is β = 0.001. |