Now 3797 visitors
Today:0 Yesterday:0
Total: 140064 215S 51P 5R
2026-10-21, Week 43
Member Login
TACT Journal Homepage
Call for Paper
Committee
Find My Paper
Author Homepage
Statistics & History
Welcome Message
Paper Procedure
FAQ
Paper Archives
Outstanding Papers
Program & Proceedings
Presentation Platform
Hotel & Travel Info
Photo Gallery
Scheduler Login
Seminar
Archives Login
Sponsors


















Online Q&A Session
Paper Number Author:
Paper Title
Keyword
Q&A Number **Select your question number !!
Questioner eMail:
Question
Answer
by
Author
Save Q&A

* Edit or answer any Q&A by selecting Q&A number Hyper Link below + Write button (Save)
ICACT20230276 Question.1
Questioner: nvlinh@cs.ccu.edu.tw    2023-02-10 오후 6:34:49 		ICACT20230276 Answer.1
Answer by Auhor haodp@dau.edu.vn   2023-02-10 오후 6:34:49
Chrome Click!!
How did you implement FL, given the difficulty of maintaining fast convergence speed over many local models? Thanks for your question. The implementation of federated learning model follows these steps: + Step 1, collect data from different devices. + Step 2, train local models The model will be trained on each device + Step 3, Aggregate local models After the local models have been trained, they are aggregated to form a global model. The aggregation method can be adjusted to ensure that the global model converges quickly and accurately + Step 4, Update blobal model The global model is updated with the latest local models, and the process is repeated until convergence is achieved In the experimental implementation we use FedAvg And it is a method for aggregating models trained on decentralized data across multiple devices + Step 5, Evaluate the model The final step is to evaluate the performance of the global model, using metrics such as accuracy, precision, and recall The difficulty of maintaining fast convergence speed over many local models? + First, Data heterogeneity (data heterogeneity) This data heterogeneity can cause the local models to converge to different solutions, leading to slow convergence or divergence of the global model. + Second, Communication overhead (communication overhead) Federated learning requires communication between devices and the central server, which can be slow and expensive. + Third, Limited computational resources (limited computational resources) Many devices used in federated learning, such as mobile devices or Internet of Things (IoT) devices, have limited computational resources, which can impact the convergence speed of the local models. + Fourth, Data privacy (data privacy) Protecting the privacy of the data used in federated learning is a key concern, which can limit the amount of information that can be shared between devices and the central server. This can make it more difficult to achieve fast convergence. + Fifth, model complexity (complexity of models) The models used in federated learning can be very large and complex, which can slow down the convergence process. To address these challenges, various optimization techniques, such as model compression, data sampling, regularization, and communication optimization, have been developed and applied in federated learning algorithms.
ICACT20230276 Question.2
Questioner: nvlinh@cs.ccu.edu.tw    2023-02-10 오후 6:35:13 		ICACT20230276 Answer.2
Answer by Auhor haodp@dau.edu.vn   2023-02-10 오후 6:35:13
Chrome Click!!
Why do you use the centralized model for FL, which is supposed for distributed environments? Thanks for your question. In this paper, I am trying to compare the results of implementing the FL (federated learning) model with the CL (centralize learning) model. In the case of implementing the CL model, I would aggregate all the data from the different devices into the a common data set. From there deploy deep learning models (CNN, LSTM, GRU) The results show that using FL has the same results as CL. However, in FL data pricacy is guaranteed.
ICACT20230276 Question.3
Questioner: nvlinh@cs.ccu.edu.tw    2023-02-10 오후 6:35:31 		ICACT20230276 Answer.3
Answer by Auhor haodp@dau.edu.vn   2023-02-10 오후 6:35:31
Chrome Click!!
How to maintain FL in IoT networks in which many devices are constrained-energy/computation Thanks for your question. (FL) in IoT (Internet of Things) networks can be challenging, especially when dealing with devices that are constrained in terms of energy and computation. Here are some techniques that can be used to address these constraints: + Model compression: One of the ways to address limited computational resources is to use model compression techniques to reduce the size and complexity of the local models. + Data subsampling: Another way to address limited computational resources is to use data subsampling + Asynchronous updates: In some cases, it may not be possible for all devices to participate in each FL round. + Energy-efficient communication: To address the energy constraints of IoT devices, energy-efficient communication protocols can be used, such as rate-limited or power-limited communication. + Task-specific models: In some cases, it may be possible to train task-specific models on each device, rather than a single universal model.