Youngjun Kwak
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Youngjun Kwak has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Chanyeol Choi
LinqAlpha, New York, USA
1 shared publication - Daehee Han
KakaoBank, Seongnam, Republic of Korea
1 shared publication - Daekyung Park
LinqAlpha, New York, USA
1 shared publication - Hyunkyu Kim
KakaoBank, Financial Tech Lab, Seongnam-si, Republic of Korea
1 shared publication - Junhyeong Lee
UNIST, Ulsan, Republic of Korea
1 shared publication - Kangmin Kim
UNIST, Ulsan, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 13 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 973-981
From Hindsight to Foresight: Adapting Reusable Reasoning Structures from Recurring Financial Events
- 13 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 973-981
Open AccessFrom Hindsight to Foresight: Adapting Reusable Reasoning Structures from Recurring Financial Events
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 141-149
Query Generation Pipeline with Enhanced Answerability Assessment for Financial Information Retrieval
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 141-149
Open AccessQuery Generation Pipeline with Enhanced Answerability Assessment for Financial Information Retrieval
- Open Access
- 23 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 133208-133217
FedDAR: Federated Learning With Data-Quantity Aware Regularization for Heterogeneous Distributed Data
Federated learning (FL) has emerged as a promising approach for collaboratively training global models and classifiers without sharing private data. However, existing studies primarily focus on distinct methodologies for typical and personalized FL (tFL and pFL), representing a challenge in exploring cross-applicable training methods. Moreover, previous approaches often rely on data and feature augmentation branches, overlooking data-quantity considerations, leading to suboptimal performance and inefficient communication costs, particularly in multi-class classification tasks. To address these challenges, we propose a novel add-on regularization technique for existing FL methods, named Data-quantity Aware Regularization (FedDAR), seamlessly integrating with existing tFL and pFL frameworks. This network-agnostic methodology reformulates the local training procedure by incorporating two crucial components: (1) enriched-feature augmentation, where features of the local model are coordinated with pre-initialized features to ensure unbiased-representations with efficient global communication rounds for unbalanced data distribution, and (2) data-quantity aware branch, which associates with local data size to improve the optimization of the local model using both supervised and self-supervised labels. We demonstrate significant performance improvements in tFL and pFL, achieving state-of-the-art results across MNIST, F-MNIST, CIFAR-10/100, and Tiny-ImageNet benchmarks.
- 23 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 133208-133217
Open AccessFedDAR: Federated Learning With Data-Quantity Aware Regularization for Heterogeneous Distributed Data
Federated learning (FL) has emerged as a promising approach for collaboratively training global models and classifiers without sharing private data. However, existing studies primarily focus on distinct methodologies for typical and personalized FL (tFL and pFL), representing a challenge in exploring cross-applicable training methods. Moreover, previous approaches often rely on data and feature augmentation branches, overlooking data-quantity considerations, leading to suboptimal performance and inefficient communication costs, particularly in multi-class classification tasks. To address these challenges, we propose a novel add-on regularization technique for existing FL methods, named Data-quantity Aware Regularization (FedDAR), seamlessly integrating with existing tFL and pFL frameworks. This network-agnostic methodology reformulates the local training procedure by incorporating two crucial components: (1) enriched-feature augmentation, where features of the local model are coordinated with pre-initialized features to ensure unbiased-representations with efficient global communication rounds for unbalanced data distribution, and (2) data-quantity aware branch, which associates with local data size to improve the optimization of the local model using both supervised and self-supervised labels. We demonstrate significant performance improvements in tFL and pFL, achieving state-of-the-art results across MNIST, F-MNIST, CIFAR-10/100, and Tiny-ImageNet benchmarks.