arXiv subjects

Rene Glitza

Publications and source records attributed to Rene Glitza.

4 recordsLinked to original sources

arXiv2026

autowerkstatt4null: An Off-Board-Diagnostics Ecosystem for Car-Workshops

This paper presents autowerkstatt4null, a three-year initiative to empower independent automotive workshops with AI-driven, federated diagnostics. The project was funded by the German Federal Ministry for Economic Affairs and Climate Action. The project enhanced the initial diagnostic workflow through newly developed technologies and architectural concepts, incorporating real user feedback. The resulting demonstrator showcases key outcomes: a modular measurement platform enabling flexible hardware integration, a secure data exchange hub for trusted collaboration, asynchronous online diagnostics that decouples analysis from workshop constraints, and a digital academy supporting technician upskilling. Together, these innovations demonstrate how independent workshops can access advanced diagnostic capabilities previously limited to manufacturer tools, strengthening competitiveness and sustainability in the sector. The project repository is available at: https://github.com/nabla-B/paper_aw4null-overview.

eess.SP↗

arXiv2026

Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data

Federated Learning (FL) enables distributed training of machine learning models while preserving data privacy. However, FL struggles with heterogeneous, non-IID client data distributions, resulting in sub-optimal and biased global models. In this paper, we propose pFedMARL, a novel approach leveraging Multi-Agent Reinforcement Learning (MARL) with Twin Delayed Deep Deterministic Policy Gradient (TD3) to dynamically adapt aggregation strategies in FL settings. Our method employs a server-side agent adjusting client contributions to optimize global model robustness and client-side agents balancing global and local updates to personalize models effectively without pre-training. We demonstrate superior performance of pFedMARL for training a semi-supervised audio spectrogram transformer, matching or outperforming FedAvg, Ditto, and local training approaches across multiple non-IID scenarios and in the presence of adversarial clients. Our results indicate that pFedMARL actively improves accuracy, robustness, and fairness, making it suitable for real-world deployments.

cs.LG↗

arXiv2021

Unsupervised Clustered Federated Learning in Complex Multi-source Acoustic Environments

In this paper we introduce a realistic and challenging, multi-source and multi-room acoustic environment and an improved algorithm for the estimation of source-dominated microphone clusters in acoustic sensor networks. Our proposed clustering method is based on a single microphone per node and on unsupervised clustered federated learning which employs a light-weight autoencoder model. We present an improved clustering control strategy that takes into account the variability of the acoustic scene and allows the estimation of a dynamic range of clusters using reduced amounts of training data. The proposed approach is optimized using clustering-based measures and validated via a network-wide classification task.

eess.AS↗

arXiv2021

Estimation of Microphone Clusters in Acoustic Sensor Networks using Unsupervised Federated Learning

In this paper we present a privacy-aware method for estimating source-dominated microphone clusters in the context of acoustic sensor networks (ASNs). The approach is based on clustered federated learning which we adapt to unsupervised scenarios by employing a light-weight autoencoder model. The model is further optimized for training on very scarce data. In order to best harness the benefits of clustered microphone nodes in ASN applications, a method for the computation of cluster membership values is introduced. We validate the performance of the proposed approach using clustering-based measures and a network-wide classification task.

eess.AS↗