Federated Learning for Internet of Things: Applications, Challenges, and Opportunities

Zhang, Tuo; Gao, Lei; He, Chuan; Zhang, Mi; Krishnamachari, Bhaskar; Avestimehr, Salman

doi:10.48550/arxiv.2111.07494

Cited by 5 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FedCV serves as one of the key components of FedML ecosystem. The other important applications include FedNLP [47], FedGraphNN [25], and FedIoT [88]. Google Landmarks Dataset 23k (GLD-23K) is a subset of Google Landmark Dataset 160k [78].…”

Section: Discussionmentioning

confidence: 99%

“…FL has the potential to rescue many interesting computer vision (CV) applications which centralized training cannot handle due to various issues such as privacy concerns (e.g. in medical settings), data transfer and maintenance costs (most notably in video analytic) [88,89], or sensitivity of proprietary data (e.g. facial recognition) [37].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks

He¹,

Shah²,

Tang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Federated Learning (FL) is a distributed learning paradigm that can learn a global or personalized model from decentralized datasets on edge devices. However, in the computer vision domain, model performance in FL is far behind centralized training due to the lack of exploration in diverse tasks with a unified FL framework. FL has rarely been demonstrated effectively in advanced computer vision tasks such as object detection and image segmentation. To bridge the gap and facilitate the development of FL for computer vision tasks, in this work, we propose a federated learning library and benchmarking framework, named FedCV, to evaluate FL on the three most representative computer vision tasks: image classification, image segmentation, and object detection. We provide non-I.I.D. benchmarking datasets, models, and various reference FL algorithms. Our benchmark study suggests that there are multiple challenges that deserve future exploration: centralized training tricks may not be directly applied to FL; the non-I.I.D. dataset actually downgrades the model accuracy to some degree in different tasks; improving the system efficiency of federated training is challenging given the huge number of parameters and the per-client memory cost. We believe that such a library and benchmark, along with comparable evaluation settings, is necessary to make meaningful progress in FL on computer vision tasks. FedCV is publicly available: https://github.com/FedML-AI/FedCV .

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks

He¹,

Shah²,

Tang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…We used horizontal data partitioning [23] for distributing to the workers. The two virtual workers are assigned slightly different positive and negative class distributions in the training data, to emulate such possibility in the real case [24]. That is, Anne had 35% positive and 65% negative classes distribution, while Bob had 28% positive and 72% negative classes 2 summarizes the distribution of the training data.…”

Section: Model Descriptionmentioning

confidence: 99%

Federated learning for scam classification in small Indonesian language dataset: an initial study

Chen

Halim

2023

IJEECS

View full text Add to dashboard Cite

Most digital phishing or scam trick users into fraudulent links and is more effective against users with low technology literacy, like in Indonesia. Machine learning is widely used for scam classification, but most require sending the messages to a centralized server. This induces privacy concern as messages might contain private data. Federated learning (FL) was proposed to allow user devices to train models locally without sending data to server. In this work, we examined the use of FL with gated recurrent unit (GRU) model for classifying scam messages in Indonesian language with small dataset. We provided two FL-based baseline models (FedAvg and daisy-chained algorithms) and a dataset for scam classification in Indonesian language. We examined the models based on these performance metrics; precision, recall, F1, selectivity, and balanced accuracy. Despite the performance, we pointed out characteristics of the FL algorithms and the hyperparameters for this use case as pointers towards fine-tuning these baseline models. Overall, the FL model with FedAvg algorithm performed better in all metrics except recall.

show abstract

“…The paper introduces a number of metrics, such as sparsification, robustness, quantization, scalability, security and privacy, to compare the analyzed proposals. A further review is presented in [17], which discusses the opportunities and challenges of federated learning in IoT platforms, as well as how federated learning can enable different IoT applications. The paper also identifies critical challenges of federated learning in IoT platforms, highlighting some recent promising approaches to address them.…”

Section: Related Workmentioning

confidence: 99%

FLaMAS: Federated Learning Based on a SPADE MAS

2022

View full text Add to dashboard Cite

In recent years federated learning has emerged as a new paradigm for training machine learning models oriented to distributed systems. The main idea is that each node of a distributed system independently trains a model and shares only model parameters, such as weights, and does not share the training data set, which favors aspects such as security and privacy. Subsequently, and in a centralized way, a collective model is built that gathers all the information provided by all of the participating nodes. Several federated learning framework proposals have been developed that seek to optimize any aspect of the learning process. However, a lack of flexibility and dynamism is evident in many cases. In this regard, this study aims to provide flexibility and dynamism to the federated learning process. The methodology used consists of designing a multi-agent system that can form a federated learning framework where the agents act as nodes that can be easily added to the system dynamically. The proposal has been evaluated with different experiments on the SPADE platform; the results obtained demonstrate the benefits of the federated system while facilitating flexibility and scalability.

show abstract

Federated Learning for Internet of Things: Applications, Challenges, and Opportunities

Cited by 5 publications

References 15 publications

FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks

FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks

Federated learning for scam classification in small Indonesian language dataset: an initial study

FLaMAS: Federated Learning Based on a SPADE MAS

Contact Info

Product

Resources

About