← Back to all news
arXiv Machine Learning By Saranraj S, Saranya M S, Alex David S, Ajay Kumar A

SWB-DM: A Calibrated Sliced-Wasserstein-Barycenter Aggregator with Delayed-Momentum Caching for Byzantine-Robust Federated Learning under Partial Participation

Read the original on arXiv Machine Learning →

The paper introduces SWB-DM, a Byzantine‑robust federated learning aggregator that treats each slice of a client update as a one‑dimensional distribution, computes a trimmed Wasserstein barycenter across clients, and uses a medoid‑based gauge‑fixing step to recover coordinate identity. It further incorporates delayed‑momentum caching to decouple robustness from the specific clients sampled each round. Extensive experiments on CIFAR‑10, CIFAR‑100, FEMNIST, and a 500‑client scalability run reveal distinct failure modes of existing defenses and demonstrate that SWB‑DM achieves significant gains, especially when compared under equal round budgets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 15

A Byzantine-Robust Federated Learning with Nesterov Momentum

The paper introduces Byrd-NAFL, a Byzantine‑robust federated learning algorithm that incorporates Nesterov momentum at the server while keeping workers stateless. It applies any soft γ‑Byzantine resilient aggregation rule and provides finite‑time convergence guarantees for smooth non‑convex losses across all momentum factors β∈[0,1). Experiments on MNIST, CIFAR‑10, and Sentiment140 demonstrate faster convergence and higher accuracy than existing benchmarks under various attacks.

By Lihan Xu, Xiaoyi Fan, Gang Wang, Runhao Zeng, Xiping Hu, Yanjie Dong
agentsbenchmarks
More like this →
arXiv AI
1d ago

FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning

FedReason introduces a large language model (LLM) that dynamically selects aggregation rules for federated learning by inspecting client model weights in a sandboxed environment. The LLM evaluates candidate rules on a small proxy dataset and submits a Python program that the server executes until the next call, defaulting to FedAvg if the output is invalid. Experiments on CIFAR-10 and CIFAR-100 with ResNet-18 under various heterogeneity and Byzantine scenarios show FedReason outperforming FedAvg by an average of 1.26 percentage points and matching the best server‑side rule on CIFAR‑100, while incurring modest API costs.

By Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour
llms
More like this →