Research map / Federated learning and privacy / Privacy attacks and secure learning
Byzantine-Robust Federated Learning with Learnable Aggregation Weights
Javad Parsa, Amir Hossein Daghestani, André M. H. Teixeira, Mikael Johansson
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| learn aggregation weights jointly with the model instead of uniform weights after filtering | FedLAW · CIFAR10 label flipping (q=0.6, 40% malicious) | test accuracy (%): 62.2 -> 70.5 | Improved |
| learn aggregation weights jointly with the model | FedLAW · CIFAR10 inverse gradient (q=0.9, 40% malicious) | test accuracy (%): 56.24 -> 59.38 | Improved |
| use nested weight objective with gradient alignment rather than BSUM loss-only weight update (ablation) | FedLAW · MNIST four attacks (10 clients, q=0.9, 40% malicious) | test accuracy / speed of suppressing attackers | Improved |
| FedLAW vs best baseline on MNIST inverse-gradient attack with 40% malicious | FedLAW · MNIST inverse gradient (40% malicious) | test accuracy: 3.6% higher than next-best | Improved |
Closest papers by meaning
- Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients (NeurIPS 2025 · similarity 0.92)
- Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning (ICML 2024 · similarity 0.92)
- A Huber Loss Minimization Approach to Byzantine Robust Federated Learning (AAAI 2024 · similarity 0.91)
- Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates (ICML 2024 · similarity 0.90)
- FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors (CVPR 2025 · similarity 0.90)
- On the Byzantine-Resilience of Distillation-Based Federated Learning (ICLR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
