FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 6962-6971
Abstract
No abstract availableFunding Information
- The National Natural Science Foundation of China (62472047)
- The National Natural Science Foundation of China (62572068)
- The National Natural Science Foundation of China (62502042)
- The National Natural Science Foundation of China (62572073)
- the 111 Project (B21049)
This publication has 38 references indexed in Scilit:
- FL-QNNs: Memory Efficient and Privacy Preserving Framework for Peripheral Blood Cell ClassificationIEEE Access, 2025
- GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting2023
- DaFKD: Domain-aware Federated Knowledge Distillation2023
- MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classificationScientific Data, 2023
- Clustering-based Curriculum Construction for Sample-Balanced Federated Learning2022
- Improving Generalization in Federated Learning by Seeking Flat Minima2022
- Learn from Others and Be Yourself in Heterogeneous Federated Learning2022
- Federated learning on non-IID data: A surveyNeurocomputing, 2021
- Model-Contrastive Federated Learning2021
- The Exponentially Weighted Moving AverageJournal of Quality Technology, 1986