Pattern Recognition Tasks with Personalized Federated Learning
Recent research in federated learning (FL) addresses critical challenges in privacy and data drift. One paper introduces TADI and Fulcrum to protect against topology-aware inference attacks by optimally allocating noise, showing privacy gains without utility loss. Another study proposes FlashbackCL, an extension to existing methods, which mitigates temporal forgetting in FL by using decayed label counts and a device-aware replay buffer, achieving significant improvements over prior work. Additional research explores personalized Bayesian FL approaches like pFedBayes, sFedBayes, and cFedbayes to handle data heterogeneity, alongside FedSAP for stable federated representation learning and FedMChain for multimodal FL by optimizing modalities sequentially. Finally, IntraShuffler is presented as a defense against privacy inference attacks in heterogeneous DP FL by shuffling client updates within privacy-compatible buckets. AI
IMPACT Advances in federated learning address key challenges in privacy, data drift, and heterogeneity, potentially enabling more robust and secure distributed AI systems.
- Hugging Face
- APPLE
- arXiv
- Yiwei Li
- Qiyuan Chen
- Fabio Turazza
- MS-PAFL
- Kaoru Otsuka
- HO-SFL
- FedNMap
- PGFedSplit
- GH-OFL
- Longtao Xu
- FedTSV
- FedProto
- Jaeyoung Song
- Kun Huang
- SPECIAL
- MIMIC-IV
- CIFAR-10
- Federated Learning
- Differential Privacy
- Flashback
- TADI
- FedSAP
- cFedbayes
- FlashbackCL
- IntraShuffler
- FedMChain
- pFedBayes
- sFedBayes