← Back to all news
arXiv AI By Ali Mohammadi Ruzbahani, Abbas Yazdinejad, Hadis Karimipour

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

Read the original on arXiv AI →

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.

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 AI.

Related stories

arXiv Machine Learning
Oct 16

Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning

The paper investigates privacy and integrity risks in federated fine‑tuning of a pretrained MobileNetV4 model on Quick, Draw! data. It shows that a single client update can reveal private labels, that label‑count recovery degrades with more clients, and that backdoor and label‑flipping attacks can succeed under FedAvg but are mitigated by FLTrust. The study also demonstrates a live poisoning session using Indigma’s FedMaestro orchestrator.

By Vasileios Perifanis, Nikolaos Pavlidis
fine-tuningmultimodalsafety
More like this →
arXiv Machine Learning
Aug 20

FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs

FedLNS is a server‑side framework that screens federated learning updates by representing each client’s contribution through changes in trainable normalization‑layer parameters, creating lightweight signatures that can be compared against a history‑aware cross‑client reference. The method requires no extra client‑to‑server communication, raw data, or labeled attack examples, and after screening, the remaining full‑model updates are aggregated with standard federated learning rules. Experiments on GPT‑style, BERT‑style, and LLaMA‑style models with 200 clients demonstrate that FedLNS achieves lower test perplexity than six baselines even when 40% of the population performs target manipulation under both IID and non‑IID data partitions.

By Kai Li, Jong-Ik Park, Carlee Joe-Wong, Wei Ni, Falko Dressler
llmsroboticssafety
More like this →
arXiv Machine Learning
Sep 16

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

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.

By Saranraj S, Saranya M S, Alex David S, Ajay Kumar A
More like this →