Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID and long-tail data distributions. We propose \textbf{FedSM}, a novel client-centric framework that mitigates this bias through semantics-guided feature mixup and lightweight classifier retraining. FedSM uses a pretrained image-text-aligned model to compute category-level semantic relevance, guiding the category selection of local features to mix-up with global prototypes to generate class-consistent pseudo-features. These features correct classifier bias, especially when data are heavily skewed. To address the concern of potential domain shift between the pretrained model and the data, we propose probabilistic category selection, enhancing feature diversity to effectively mitigate biases. All computations are performed locally, requiring minimal server overhead. Extensive experiments on long-tail datasets with various imbalanced levels demonstrate that FedSM consistently outperforms state-of-the-art methods in accuracy, with high robustness to domain shift and computational efficiency.
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
Federated learning has made an important contribution to data privacy-preserving. Many previous works are based on the assumption that the data are independently identically distributed (IID). As a result, the model performance on non-identically independently distributed (non-IID) data is beyond expectation, which is the concrete situation. Some existing methods of ensuring the model robustness on non-IID data, like the data-sharing strategy or pretraining, may lead to privacy leaking. In addition, there exist some participants who try to poison the model with low-quality data. In this paper,…
Yonsei University（延世大学）；Deakin University（迪肯大学）；Samsung Research, Samsung Electronics（三星电子三星研究院）；University of Oulu（奥卢大学）
This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federated learning (FL). This requires a model output-to-parameter conversion at the server, after collecting additional data samples from devices. To preserve privacy while not compromising accuracy, linearly mixed-up local samples are uploaded, and inverse…
Korea Advanced Institute of Science and Technology (KAIST)（韩国高等科学技术研究院（KAIST））
Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device, thus preserving privacy and eliminating the need to store data globally. While there are promising results under the assumption of independent and identically distributed (iid) local data, current state-of-the-art algorithms suffer from performance degradation as the heterogeneity of local data across clients increases. To resolve this issue, we propose a simple framework, Mean Augmented Federated Learning (MAFL), where clients send and receive averaged local data, subjec…
Tencent AI Lab（腾讯人工智能实验室）；Hong Kong University of Science and Technology（香港科技大学）
Recently, federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. Nevertheless, directly applying federated learning to real-world tasks faces two challenges: (1) heterogeneity in the data among different organizations; and (2) data noises inside individual organizations. In this paper, we propose a general framework to solve the above two challenges simultaneously. Specifically, we propose using distributionally robust optimization to mitigate the negative effects caused by data heterogeneity par…
Seoul National University Hospital（首尔国立大学医院）；Chung-Ang University（中央大学）；Korea University（高丽大学）；Deakin University（迪肯大学）；University of Oulu（奥卢大学）；Yonsei University（延世大学）
User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and identically distributed (non-IID) data problem, in this work we develop a privacy-preserving XOR based mixup data augmentation technique, coined XorMixup, and thereby propose a novel one-shot FL framework, termed XorMixFL. The core idea is to collect other devices' encoded data samples that are decoded only using each device's own data samples. The decoding provides synthetic-but-realistic samples until inducing an IID dat…
Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients
The Future Network of Intelligence Institute（未来网络智能研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Zhejiang University（浙江大学）；Peng Cheng Laboratory（鹏城实验室）
Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes
Department of Computer Science and Engineering, School of Computing, Kyung Hee University（计算机科学与工程系，计算学院，庆熙大学）；Department of Artificial Intelligence, School of Computing, Kyung Hee University（人工智能系，计算学院，庆熙大学）；Digital Science and Technology Institute, The University of Danang—Vietnam-Korea University of Information and Communication Technology（数字科学与技术研究所，丹那大学—越南-韩国信息与通信技术大学）
Vicinal Feature Statistics Augmentation for Federated 3D Medical Volume Segmentation
Harvard Medical School（哈佛医学院）；Harvard University（哈佛大学）；Graduate School of Engineering, Tohoku University（东北大学工学研究生院）；School of Biomedical Engineering, Anhui Medical University（安徽医科大学生物医学工程学院）；Washington University in St. Louis（圣路易斯华盛顿大学）；The Hong Kong Polytechnic University（香港理工大学）
Yonsei University（延世大学）；Deakin University（迪肯大学）；Massachusetts Institute of Technology（麻省理工学院）；University of Oulu（奥卢大学）
Recently, vision transformer (ViT) has started to outpace the conventional CNN in computer vision tasks. Considering privacy-preserving distributed learning with ViT, federated learning (FL) communicates models, which becomes ill-suited due to ViT' s large model size and computing costs. Split learning (SL) detours this by communicating smashed data at a cut-layer, yet suffers from data privacy leakage and large communication costs caused by high similarity between ViT' s smashed data and input data. Motivated by this problem, we propose DP-CutMixSL, a differentially private (DP) SL framework …
Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）
As special information carriers containing both structure and feature information, graphs are widely used in graph mining, e.g., Graph Neural Networks (GNNs). However, in some practical scenarios, graph data are stored separately in multiple distributed parties, which may not be directly shared due to conflicts of interest. Hence, federated graph neural networks are proposed to address such data silo problems while preserving the privacy of each party (or client). Nevertheless, different graph data distributions among various parties, which is known as the statistical heterogeneity, may degrad…
