mohamad-ansarimehr/F-ACVAE: Second release of F-ACVAE implementation

Second release of F-ACVAE implementation. This repository contains the complete source code for the proposed F-ACVAE framework: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks}. Key features: Custom Constrained Momentum Gaussian Aggregation (CMGA) strategy in Flower framework Selective parameter aggregation for 62% communication reduction Evaluation on N-BaIoT dataset with highly non-IID clients PyTorch 2.1 and Flower 1.8 implementation For details, see the accompanying paper (under review/submission): "F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks" by Mohammad Ansarimehr et al. README.md includes installation instructions, requirements, and steps to reproduce the experiments.