• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.742-756
• /
• 2022

A flood of information has occurred with the rise of the internet and digital devices in the fourth industrial revolution era. Every millisecond, massive amounts of structured and unstructured data are generated; smartphones, wearable devices, sensors, and self-driving cars are just a few examples of devices that currently generate massive amounts of data in our daily. Machine learning has been considered an approach to support and recognize patterns in data in many areas to provide a convenient way to other sectors, including the healthcare sector, government sector, banks, military sector, and more. However, the conventional machine learning model requires the data owner to upload their information to train the model in one central location to perform the model training. This classical model has caused data owners to worry about the risks of transferring private information because traditional machine learning is required to push their data to the cloud to process the model training. Furthermore, the training of machine learning and deep learning models requires massive computing resources. Thus, many researchers have jumped to a new model known as "Federated Learning". Federated learning is emerging to train Artificial Intelligence models over distributed clients, and it provides secure privacy information to the data owner. Hence, this paper implements Federated Averaging with a Deep Neural Network to classify the handwriting image and protect the sensitive data. Moreover, we compare the centralized machine learning model with federated averaging. The result shows the centralized machine learning model outperforms federated learning in terms of accuracy, but this classical model produces another risk, like privacy concern, due to the data being stored in the data center. The MNIST dataset was used in this experiment.

• Annual Conference of KIPS
• /
• 2024.10a
• /
• pp.678-681
• /
• 2024

Fine-tuning is critical to enhance the model's ability to operate effectively in resource-constrained environments by incorporating domain-specific data, improving reliability, fairness, and accuracy. Large language models (LLMs) traditionally prefer centralized training due to the ease of managing vast computational resources and having direct access to large, aggregated datasets, which simplifies the optimization process. However, centralized training presents significant drawbacks, including significant delay, substantial communication costs, and slow convergence, particularly when deploying models to devices with limited resources. Our proposed framework addresses these challenges by employing a federated fine-tuning strategy with Whisper-tiny model for keyword recognition system (KWR). Federated learning allows edge devices to perform local updates without the need for constant data transmission to a central server. By selecting a cluster of clients and aggregating their updates each round based on federated averaging, this strategy accelerates convergence, reduces communication overhead, and achieves higher accuracy in comparatively less time, making it more suitable than centralized approach. By the tenth round of federated updates, the fine-tuned model demonstrates notable improvements, achieving over 95.48% test accuracy. We compare the FL-finetuning method with and centralized strategy. Our framework shows significant improvement in accuracy in fewer training rounds.