federated learning

Decentralized Federated Reinforcement Learning with Multi-Agent Credit Assignment

This paper presents a novel approach to decentralized federated reinforcement learning (DFRL) that tackles the critical challenge of multi-agent credit assignment. Traditional multi-agent reinforcement learning (MARL) struggles to scale effectively in decentralized settings due to the difficulty in determining which agents are responsible for the overall reward. Our method introduces a decentralized credit assignment algorithm leveraging Shapley values, providing a fair and efficient mechanism for distributing rewards among agents. Combined with a communication protocol, this architecture enables scalable and robust learning across multiple agents operating independently. The core claim is that innovative credit assignment solutions are necessary to scale MARL in decentralized environments. This work offers a foundational framework for developing more practical and effective DFRL systems.

Machine Learning - Based Classification Framework for Intelligent 5G Resource Allocation and Network Optimization

Communication-Efficient Federated Frank-Wolfe Algorithm

Distributed Knowledge Graph Embedding with Federated Learning for Privacy Preservation

Knowledge graph embedding techniques have gained significant traction in representing complex relationships within knowledge graphs, enabling applications such as link prediction, entity recommendation, and semantic search. However, the training of these embeddings often relies on consolidating vast amounts of data from disparate sources, leading to substantial privacy risks. This paper proposes a novel approach to distributed knowledge graph embedding using federated learning, designed to mitigate these privacy concerns. We introduce a framework where multiple data sources independently train local knowledge graph embeddings. These local models are then aggregated using federated learning algorithms, resulting in a global knowledge graph embedding model without direct data sharing. The proposed method aims to balance embedding quality with robust privacy protection. We detail the technical aspects of the framework, including the selection of appropriate federated learning algorithms and strategies for addressing potential heterogeneity in data distributions. Experimental considerations and future research directions are also discussed.

FedBound a boundary aware optimization strategy for federated medical image segmentation under non IID data

Abstract Medical image segmentation is essential for computer-aided diagnosis and treatment planning. Privacy constraints impede centralized training using medical images from diverse healthcare organizations. Federated learning (FL) is developed to facilitate collaborative model training without sharing patient information. However, the statistical heterogeneity of data (non-IID distribution) among clients adversely impacts the segmentation task, particularly the quality of segmentation at object borders, which remains insufficiently explored. This paper presents a systematic analysis of boundary-sensitive medical image segmentation under heterogeneous federated learning conditions. We propose FedBound , a lightweight boundary-aware optimization technique that emphasizes contour areas during local training without increasing communication overhead. Additionally, we examine the impact of multiscale feature representations using an ASPP-based federated framework termed FedASPP . Experiments were conducted on the ISIC 2018 dataset for skin lesion segmentation, employing a Dirichlet non-IID distribution across 100 federated clients. The findings indicate that FedBound enhances boundary quality, reduces the HD95 score, and maintains high Dice and IoU coefficients across various segmentation architectures. Furthermore, FedBound reduces performance variability among clients, demonstrating improved stability in heterogeneous federated environments.

Decentralized Federated Learning with Differential Privacy via Lagrangian Relaxation

Federated learning (FL) offers a promising paradigm for training machine learning models on decentralized data sources without directly exchanging data. However, achieving robust privacy guarantees alongside high model accuracy remains a significant challenge. This paper introduces a novel approach to decentralized federated learning leveraging Lagrangian relaxation and differential privacy. Our method allows for a more nuanced and adaptive trade-off between privacy and accuracy by optimizing a Lagrangian function at each participating node. This decentralized optimization process enables a flexible solution to the inherent tension between privacy preservation and model performance. We demonstrate the effectiveness of this approach through a theoretical analysis and outline a potential implementation strategy. The key innovation lies in the localized optimization of the Lagrangian, mitigating the communication bottlenecks often encountered in centralized FL and offering a pathway towards truly decentralized privacy-preserving learning.

A Device-Agnostic Framework for Personalized Anomaly Detection in Wearable and Mobile Ecosystems: Applications in Personal Safety and Respiratory Health Surveillance

Abstract—This paper presents a reformulated, device-agnostic architectural framework for two interrelated applications: (i) personalized audio-based personal safety threat detection, and (ii) respiratory pattern anomaly detection for early-stage epidemiological screening. Originating from an ideation dialogue, the proposed concepts are critically re-examined against fundamental constraints in machine learning, embedded systems, privacy engineering, and sensor heterogeneity. We propose a generalized abstraction layer that decouples sensing modality from inference logic, enabling deployment across heterogeneous smart devices (wearables, smartphones, IoT nodes) without hardware-specific dependencies. We address the zero-positive-example training problem through a reformulation as one-class classification and temporal anomaly detection. Privacy is preserved via on-device federated feature extraction with no raw data transmission. We further analyze the practical limitations identified by domain experts and propose mitigations grounded in current literature. The framework is positioned as a foundational architecture rather than a deployable product, inviting interdisciplinary validation. Impact Statement—By introducing a sensing abstraction layer and reformulating personal safety and respiratory monitoring as one-class anomaly detection problems, this work provides a portable, privacy-preserving architecture that can operate across heterogeneous consumer devices without hardware-specific redesign. The framework addresses the zero-positive-example constraint inherent to rare-event detection and offers a structured research agenda for empirical validation, potentially accelerating the development of reliable, edge-deployed health and safety monitoring systems. Index Terms—Anomaly detection, one-class classification, device-agnostic computing, respiratory pattern analysis, personal safety systems, federated learning, wearable computing, edge inference.

Meta-Learning for Adaptive Model Selection in Federated Learning

Federated Learning (FL) has emerged as a promising approach for training machine learning models across decentralized devices while preserving data privacy. However, a significant limitation of traditional FL is the static nature of model selection. Typically, all clients are trained with the same base model, regardless of the heterogeneity in their local data distributions. This static approach often leads to suboptimal performance, particularly in scenarios with diverse client datasets. This paper proposes a novel meta-learning framework to address this limitation. The framework learns a central model that dynamically selects the most appropriate base model for each client based on its local data characteristics. This adaptive model selection process aims to improve the overall system performance and efficiency of federated learning. The key contributions are the introduction of adaptability into the model selection stage and the development of a meta-learning approach for achieving this adaptation.

Digital Twins for Sustainable Groundwater Resources Management: From Monitoring and Prediction to Governance and Resilience—A Review

This article presents a scoping review of the literature on digital twins (DTs) for sustainable groundwater resources management, which constitutes a very recent and rapidly expanding research field, with literature moving quickly from conceptual frameworks to application-oriented systems. The literature, selected through the PRISMA 2020 methodology, is organized into seven sub-topics: AI and ML foundations, digital twin architectures and frameworks, aquifer-scale DT applications, agricultural and water–energy–food (WEF) nexus DTs, basin and urban water DTs, sensing, monitoring and IoT infrastructures, and governance, resilience and socio-hydrology. This structure shows how the field is shifting from monitoring and prediction toward integrated decision support, where process-based models, machine learning surrogates, real-time sensing and optimization are combined to support drought mitigation, saltwater intrusion control, irrigation management, climate adaptation and basin-scale planning. Across the reviewed studies, the most recurrent contributions are the construction of hybrid model architectures, the use of DTs to close the loop between observation and control, and the growing recognition that groundwater management must incorporate governance, stakeholder decision-making and socio-hydrological feedbacks. At the same time, the literature still faces key limitations, especially uncertainty quantification, interoperability between models and data streams, transferability to data-scarce settings and limited validation under real operational conditions. Future research should therefore focus on physics-informed and explainable AI, federated and scalable DT architectures, stronger coupling with socio-hydrological and governance frameworks, and more field-tested implementations that can demonstrate robust performance across diverse hydrogeological and institutional contexts.

Decentralized Learning with Federated Bayesian Networks

This paper proposes a novel decentralized learning algorithm for Bayesian networks, termed Federated Bayesian Networks (FBNs). The core idea is to enable nodes within a network to learn independently and collaboratively, mirroring the principles of federated learning. Each node maintains its own Bayesian network and updates its parameters based on probabilistic information received from its neighbors. This approach avoids the need for centralized data aggregation, addressing key challenges associated with privacy and scalability in traditional Bayesian network learning. The algorithm iteratively refines both the network structure and its parameters, leading to a more accurate and robust global model. Mathematical formulations are presented to detail the update rules and convergence properties of the FBN algorithm. The key contribution lies in establishing a framework for distributed Bayesian network learning, particularly well-suited for scenarios with heterogeneous data and limited communication bandwidth. This work lays the foundation for applying FBNs to diverse applications, including healthcare, smart cities, and anomaly detection.

Blockchain-Based Federated Learning with Differential Privacy

Federated learning (FL) offers a promising approach to training machine learning models on decentralized data sources without direct data sharing. However, traditional FL systems remain vulnerable to privacy breaches and data manipulation. This paper proposes a novel blockchain-based architecture that addresses these concerns by integrating data provenance tracking, integrity verification, and differential privacy mechanisms. The system leverages blockchain technology to create an immutable record of model updates and data contributions, ensuring transparency and accountability. Simultaneously, differential privacy techniques are applied during the training process to protect the privacy of individual data contributors. This combined approach significantly enhances the security and trustworthiness of FL systems, enabling secure and collaborative model training across diverse data sources. The proposed system utilizes cryptographic hashing and Merkle trees to guarantee data integrity and employs noise injection strategies within differential privacy mechanisms to protect user data. The core contribution is a secure and verifiable FL framework with enhanced privacy guarantees.

DIGITAL TWINS AND FEDERATED LEARNING IN CARDIOMETABOLIC HEALTH: A SYSTEMATIC REVIEW AND A NOVEL PUBLIC HEALTH FRAMEWORK FOR OBESITY, TYPE 2 DIABETES, AND CARDIOVASCULAR DISEASE INTEGRATION