Bidirectional domain transfer knowledge distillation for catastrophic forgetting in federated learning with heterogeneous data
Authors:
- Qi MinQMQi Min
- Fei LuoFLFei Luo
- Wenbo DongWDWenbo Dong
- Chunhua GuCGChunhua Gu
- Weichao DingWDWeichao Ding
- 22 January 2025
- journal article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Shanghai Municipality (23ZR1414900, 22ZR1416500)
- National Natural Science Foundation of China (62403201)
This publication has 33 references indexed in Scilit:
- Learning adaptive shift and task decoupling for discriminative one-step person searchKnowledge-Based Systems, 2024
- Attentive multi-granularity perception network for person searchInformation Sciences, 2024
- Multimodal federated learning: Concept, methods, applications and future directionsInformation Fusion, 2024
- Communication-efficient federated learning via personalized filter pruningInformation Sciences, 2024
- Trust-aware conditional adversarial domain adaptation with feature norm alignmentNeural Networks, 2023
- Federated learning in smart cities: Privacy and security surveyInformation Sciences, 2023
- HOMDA: High-Order Moment-Based Domain Alignment for unsupervised domain adaptationKnowledge-Based Systems, 2022
- FedX: Unsupervised Federated Learning with Cross Knowledge Distillation2022
- Communication-efficient federated learning via knowledge distillationNature Communications, 2022
- Memory Aware Synapses: Learning What (not) to Forget2018