IEEE

3D point cloud robust sampling method based on aggregation rate

Abstract: Effective sampling plays a critical role in the preprocessing of 3D point cloud data, directly impacting the performance of downstream models. Traditional Farthest Point Sampling (FPS) ...
IEEE

Joint Adaptive Aggregation and Resource Allocation for Hierarchical Federated Learning Systems Based on Edge-Cloud Collaboration

Abstract: Hierarchical federated learning shows excellent potential for communication-computation trade-offs and reliable data privacy protection by introducing edge-cloud collaboration. Considering ...
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

FedAWA: Aggregation Weight Adjustment in Federated Domain Generalization

Abstract: Domain Generalization (DG) in the setting of federated learning (i.e. Federated Domain Generalization, FDG) is gaining increasing attention. FDG aims to learn a global model generalizing ...
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

Byzantine Robust Aggregation in Federated Distillation with Adversaries

Abstract: Federated learning empowers privacy-preserving, multi-party secure model training without the necessity of sharing raw data. In recent years, knowledge distillation has emerged as a ...
IEEE

Point Cloud Registration via Reconstruction with Local Geometry Information Aggregation

Abstract: Point cloud registration is a fundamental yet challenging task in computer vision and robotics. While framing it as a reconstruction problem has shown promise, traditional reconstruction ...
IEEE

DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis

Abstract: Due to the irregular and disordered data structure in 3D point clouds, prior works have focused on designing more sophisticated local representation methods to capture these complex local ...
IEEE

Host-driven In-Network Aggregation on RDMA

Abstract: Large-scale datacenter networks are increasingly using in-network aggregation (INA) and remote direct memory access (RDMA) techniques to accelerate deep neural network (DNN) training.