IEEE

Federated Aggregation With Interlayer Personalized Contribution: Preference-Based Optimization Between Performance and Privacy

Abstract: Currently, due to the different distribution of data for each user, many personalized federated learning (PFL) methods have emerged to meet the personalized needs of different users. However ...
InfoWorld

JDK 26: The new features in Java 26

Java Development Kit (JDK) 26, a planned update to standard Java due March 17, 2026, has reached its second release candidate (RC) stage. The RC is open for critical bug fixes, with the feature set ...
IEEE

CPFedAvg: Enhancing Hierarchical Federated Learning via Optimized Local Aggregation and Parameter Mixing

Abstract: Hierarchical federated learning (HFL) improves the scalability and efficiency of traditional federated learning (FL) by incorporating a hierarchical topology into the FL framework. In a ...
IEEE

Multistage Particle Swarm Optimization for Heterogeneous Multipoint Dynamic Aggregation

Abstract: Multipoint dynamic aggregation (MPDA) is a multirobot task allocation problem, which requires the collaborative scheduling of multiple robots to complete time-varying tasks distributed on a ...
IEEE

Cellular Aggregation Graph Convolutional Network for Point Cloud Quality Assessment

Abstract: Point cloud quality assessment (PCQA) is a challenging task due to the inherently disordered nature of points. Existing point-based methods, such as sparse convolution and PointNet, are ...
IEEE

Cross-modality Feature Aggregation for Cross-domain Point Cloud Representation Learning

Abstract: Existing methods for learning 3D point cloud representation often use a single dataset-specific training and testing approach, leading to performance drops due to significant domain shifts ...
IEEE

Towards Privacy-Preserving and Error-Tolerant Wireless Federated Learning: Fixed-Point Model Aggregation with Differential Privacy Guarantees

Abstract: This paper presents a novel approach for wireless federated learning (WFL) that, for the first time, enables the aggregation of local models with mild to moderate errors under practical ...
GitHub

A data aggregation hub for QR Scout.

This project uses Apache Maven to build. You will need a JDK Java 21 or later) and Maven 3.6 or later installed to build. $ mvn package This should build a platform ...
IEEE

Revisiting the In-Network Aggregation in Distributed Machine Learning

Abstract: Distributed Machine Learning (DML) is proposed to accelerate machine learning model training by utilizing multiple training nodes to train models in parallel. Recent studies apply emerging ...