Optimal Device Selection for Federated Learning over Mobile Edge Networks

Ching, Cheng-Wei; Liu, Kao–Lang; Yang, Chung-Kai; Kuo, Jian-Jhih; Su, Feng-Ting

doi:10.1109/icdcs47774.2020.00168

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the loss function, we leverage the loss function in personalized federated optimization (PFO) [11,16] in order to retain the data characteristics in the different leaf nodes and use federated-based method to perform online model fine-tuning. Therefore, the loss function for the leaf node 𝑛 to perform online model fine-tuning is as follows:…”

Section: Online Model Fine-tuning and Ensemble-based Model Inferencementioning

confidence: 99%

Decaffe: DHT Tree-Based Online Federated Fake News Detection

Ching,

2024

2024 8th International Conference on Control Engineering and Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

The proliferation of mobile social networks (MSNs) has transformed information dissemination, leading to increased reliance on these platforms for news consumption. However, this shift has been accompanied by the widespread propagation of fake news, posing significant challenges in terms of public panic, political influence, and the obscuring of truth. Traditional data processing pipelines for fake news detection in MSNs suffer from lengthy response times and poor scalability, failing to address the unique characteristics of news in MSNs, such as prompt propagation, large-scale quantity, and rapid evolution. This paper introduces a novel system named Decaffe -a DHT Tree-Based Online Federated Fake News Detection system. Decaffe leverages distributed hash table (DHT)-based aggregation trees for scalability and real-time detection, and it employs two model fine-tuning methods for adapting to mobile network dynamics. The system's structure includes a root, branches, and leaves for effective dissemination of a pre-trained model and ensemblebased aggregation of predictive results. Decaffe uniquely combines centralized server-based and decentralized serverless model finetuning approaches with personalized model fine-tuning, addressing the challenges of real-time detection, scalability, and adaptability in the dynamic environment of MSNs. CCS Concepts• Computer systems organization → Peer-to-peer architectures.

show abstract

Section: Online Model Fine-tuning and Ensemble-based Model Inferencementioning

confidence: 99%

Decaffe: DHT Tree-Based Online Federated Fake News Detection

Ching,

2024

2024 8th International Conference on Control Engineering and Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

“…Remark that users can upload the gradients ∇ Θ t f k (D k ; Θ t ) to PS instead. Both of the methods are mathematically equivalent [1], [12], [25], [26].…”

Section: Federated Learning (Fl)mentioning

confidence: 99%

“…Ineq. (26), limit the total numbers of the reciprocal models for Personalized Labeling and uploading to B and K, respectively. The third constraint (30) indicates that only the uploaded reciprocal models can be used.…”

Section: Definition 4 (The Optimization Problem Of the Setmentioning

confidence: 99%

Dual-Objective Personalized Federated Service System With Partially-Labeled Data Over Wireless Networks

Ching

Chang

Kuo

et al. 2023

IEEE Trans. Serv. Comput.

View full text Add to dashboard Cite

Federated learning (FL) emerges to mitigate the privacy concerns in machine learning-based services and applications, and personalized federated learning (PFL) evolves to alleviate the issue of data heterogeneity. However, FL and PFL usually rest on two assumptions: the users' data is well-labeled, or the personalized goals align with sufficient local data. Unfortunately, the two assumptions may not hold in most cases, where data labeling is costly, or most users have no sufficient local data to satisfy their personalized needs. To this end, we first formulate the problem, DoLP, that studies the issue of insufficient and partially-labeled data on FL-based services. DoLP aims to maximize two service objectives: 1) personalized classification objective and 2) the personalized labeling objective for each user within the constraint of training time over wireless networks. Then, we propose a PFL-based service system DoFed-SPP to solve DoLP. The DoFed-SPP's novelty is two-fold. First, we devise an inference-based first-order approximation metric, similarity ratio, to identify the similarity between users' local data. Second, we design an approximation algorithm to determine the appropriate size and set of users for uploading in each round. Extensive experiments show DoFed-SPP outperforms the state-of-the-art in final accuracy and time-to-accuracy performance on CIFAR10/100 and DBPedia.

show abstract