Privacy-Preserving Efficient Federated-Learning Model Debugging

Li, Anran; Zhang, Lan; Wang, Junhao; Han, Feng; Li, Xiangyang

doi:10.1109/tpds.2021.3137321

Cited by 30 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its lightweight deployment scheme, FL has become the mainstream solution and product choice in many privacy computing application scenarios. FL techniques can achieve multiple federated agencies to build a unified machine learning model among the safe and efficient multi-source data systems [18]. However, with the explosive increase in privacy computing platforms, the number of FL devices put into practical application gradually increases, the main bottleneck for the current FL technique is the huge communication overhead in optimizing and deploying the FL framework [19].…”

Section: Review Of the Typical Icac Techniquementioning

confidence: 99%

Integrated Communication, Sensing, and Computation Framework for 6G Networks

Chen,

Feng,

Zhang

et al. 2024

Sensors

View full text Add to dashboard Cite

In the sixth generation (6G) era, intelligent machine network (IMN) applications, such as intelligent transportation, require collaborative machines with communication, sensing, and computation (CSC) capabilities. This article proposes an integrated communication, sensing, and computation (ICSAC) framework for 6G to achieve the reciprocity among CSC functions to enhance the reliability and latency of communication, accuracy and timeliness of sensing information acquisition, and privacy and security of computing to realize the IMN applications. Specifically, the sensing and communication functions can merge into unified platforms using the same transmit signals, and the acquired real-time sensing information can be exploited as prior information for intelligent algorithms to enhance the performance of communication networks. This is called the computing-empowered integrated sensing and communications (ISAC) reciprocity. Such reciprocity can further improve the performance of distributed computation with the assistance of networked sensing capability, which is named the sensing-empowered integrated communications and computation (ICAC) reciprocity. The above ISAC and ICAC reciprocities can enhance each other iteratively and finally lead to the ICSAC reciprocity. To achieve these reciprocities, we explore the potential enabling technologies for the ICSAC framework. Finally, we present the evaluation results of crucial enabling technologies to show the feasibility of the ICSAC framework.

show abstract

Section: Review Of the Typical Icac Techniquementioning

confidence: 99%

Integrated Communication, Sensing, and Computation Framework for 6G Networks

Chen,

Feng,

Zhang

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…To enhance the traditional FL inference performance, many FL optimization methods have been presented. Specifically, these methods can be classified into three categories, i.e., global variable-based FL methods (Li et al 2020;Karimireddy et al 2020), device grouping-based FL methods (Fraboni et al 2021;Chen et al 2020;Li et al 2021b), and knowledge distillation-based FL methods (Sattler et al 2021;Lin et al 2020;Zhu, Hong, and Zhou 2021).…”

Section: Related Workmentioning

confidence: 99%

FedMut: Generalized Federated Learning via Stochastic Mutation

Hu,

Cao,

et al. 2024

AAAI

View full text Add to dashboard Cite

Although Federated Learning (FL) enables collaborative model training without sharing the raw data of clients, it encounters low-performance problems caused by various heterogeneous scenarios. Due to the limitation of dispatching the same global model to clients for local training, traditional Federated Average (FedAvg)-based FL models face the problem of easily getting stuck into a sharp solution, which results in training a low-performance global model. To address this problem, this paper presents a novel FL approach named FedMut, which mutates the global model according to the gradient change to generate several intermediate models for the next round of training. Each intermediate model will be dispatched to a client for local training. Eventually, the global model converges into a flat area within the range of mutated models and has a well-generalization compared with the global model trained by FedAvg. Experimental results on well-known datasets demonstrate the effectiveness of our FedMut approach in various data heterogeneity scenarios.

show abstract

“…This can also include adversarial sample attacks. There are many studies on attack prevention in federated learning [16][17][18]. The literature [16] proposes a federated learning framework, where the server learns to use a powerful detection model to detect and remove malicious model updates, thereby enabling targeted defense.…”

Section: Related Workmentioning

confidence: 99%