Seunghan Yang

Seunghan Yang

Auto-generated profile, based on publicly available information

Seunghan Yang

Qualcomm AI Research

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 February 2022 in IEEE Intelligent Systems
Verified
Journal Article
Closed access
SYSeunghan Yang
Seunghan Yang
HPHyoungseob Park
Hyoungseob Park
JBJunyoung Byun
Junyoung Byun
CKChangick Kim
Changick Kim
Federated learning enables local devices to jointly train the server model while keeping the data decentralized and private. In federated learning, all local data should be annotated by alternative labeling techniques since the annotator in the server cannot access the data. Therefore, it is hardly guaranteed that they are correctly annotated. Under this noisy label setting, local models form inconsistent class decision boundaries with one another, and their weights severely diverge, which are serious problems in federated learning. To solve these problems, we introduce a novel federated learning scheme that allows the server to cooperate with local models by interchanging class-wise centroids. The server aligns the class-wise centroids, which are central features of local data on each device, and broadcasts aligned centroids to selected clients every communication round. Updating local models with the aligned centroids helps to form consistent class decision boundaries among local models, although the noise distributions in clients' data are different from each other. Furthermore, we introduce a sample selection approach to filter out data with noisy labels and a label correction method to adjust the labels of noisy instances. Our experimental results show that our approach is noticeably effective in federated learning with noisy labels.


24 December 2019
Verified
Book Chapter
Closed access
PDF file
SYSeunghan Yang
Seunghan Yang
SJSeungjun Jung
Seungjun Jung
HKHeekwang Kang
Heekwang Kang
CKChangick Kim
Changick Kim

1 January 2024
Verified
Conference Paper
Open access
PDF file
JBJihwan Bang
Jihwan Bang
JLJuntae Lee
Juntae Lee
KSKyuhong Shim
Kyuhong Shim
SYSeunghan Yang
Seunghan Yang
SCSimyung Chang
Simyung Chang
Jihwan Bang, Juntae Lee, Kyuhong Shim, Seunghan Yang, Simyung Chang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

1 January 2025
Verified
Conference Paper
Open access
PDF file
JLJuntae Lee
Juntae Lee
JBJihwan Bang
Jihwan Bang
KSKyuhong Shim
Kyuhong Shim
SYSeunghan Yang
Seunghan Yang
SCSimyung Chang
Simyung Chang
Juntae Lee, Jihwan Bang, Kyuhong Shim, Seunghan Yang, Simyung Chang. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.

3 November 2024
Verified
Book Chapter
Closed access
PDF file
SYSeunghan Yang
Seunghan Yang
SCSeokeon Choi
Seokeon Choi
HPHyunsin Park
Hyunsin Park
SCSungha Choi
Sungha Choi
SCSimyung Chang
Simyung Chang
SYSungrack Yun
Sungrack Yun