Towards Faster and Better Federated Learning: A Feature Fusion Approach

Yao, Xin; Huang, Tianchi; Wu, Chenglei; Zhang, Rui-Xiao; Sun, Lifeng

doi:10.1109/icip.2019.8803001

Cited by 70 publications

(35 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also due to the decentralized approach FL has, we do not need to worry about actively training the algorithms ourselves very much. The algorithms we use for FL train themselves directly on the devices and only transfer back the relevant data that is needed [148]. As a result, the need to use the user's data is remedied and the training process can be more streamlined.…”

Section: Benefits and Costs Of Federated Learningmentioning

confidence: 99%

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

et al. 2020

View full text Add to dashboard Cite

This paper provides a comprehensive study of Federated Learning (FL) with an emphasis on enabling software and hardware platforms, protocols, real-life applications and use-cases. FL can be applicable to multiple domains but applying it to different industries has its own set of obstacles. FL is known as collaborative learning, where algorithm(s) get trained across multiple devices or servers with decentralized data samples without having to exchange the actual data. This approach is radically different from other more established techniques such as getting the data samples uploaded to servers or having data in some form of distributed infrastructure. FL on the other hand generates more robust models without sharing data, leading to privacy-preserved solutions with higher security and access privileges to data. This paper starts by providing an overview of FL. Then, it gives an overview of technical details that pertain to FL enabling technologies, protocols, and applications. Compared to other survey papers in the field, our objective is to provide a more thorough summary of the most relevant protocols, platforms, and real-life use-cases of FL to enable data scientists to build better privacy-preserving solutions for industries in critical need of FL. We also provide an overview of key challenges presented in the recent literature and provide a summary of related research work. Moreover, we explore both the challenges and advantages of FL and present detailed service use-cases to illustrate how different architectures and protocols that use FL can fit together to deliver desired results.

show abstract

Section: Benefits and Costs Of Federated Learningmentioning

confidence: 99%

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Federated augmentation (FAug), a generative adversarial network (GAN) based data augmentation scheme is also introduced to solve the non-IID problem. In [16], the authors propose a feature fusion method to aggregate the features for both the local and global models. The aggregation is able to reduce the communication costs and stimulate the convergence.…”

Section: A Learning Efficiency Of Flmentioning

confidence: 99%

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Yoshinaga

et al. 2020

IEEE Open J. Comput. Soc.

239

106

View full text Add to dashboard Cite

show abstract

“…But the filtering is based on pre-trained models. Yao et al [15] proposed FedFusion, an approach that could improve the performance by fusing the two model features, although extra computation is needed for choosing the best fusion approach. FedMA [4] constructs the global model in a layer-wise manner, which appears to cause significant burden on the clients.…”

Section: Related Workmentioning

confidence: 99%

Fedns: Improving Federated Learning for Collaborative Image Classification on Mobile Clients

Zhuo

2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model collaboratively with the help of a centralized server. The most popular FL algorithm is Federated Averaging (FedAvg), which is based on taking weighted average of the client models, with the weights determined largely based on dataset sizes at the clients. In this paper, we propose a new approach, termed Federated Node Selection (FedNS), for the server's global model aggregation in the FL setting. FedNS filters and reweights the clients' models at the node/kernel level, hence leading to a potentially better global model by fusing the best components of the clients. Using collaborative image classification as an example, we show with experiments from multiple datasets and networks that FedNS can consistently achieve improved performance over FedAvg.

show abstract

Towards Faster and Better Federated Learning: A Feature Fusion Approach

Cited by 70 publications

References 1 publication

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues

Fedns: Improving Federated Learning for Collaborative Image Classification on Mobile Clients

Contact Info

Product

Resources

About