Sukwon Yun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Sukwon Yun has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Chanyoung Park
KAIST, Daejeon, Republic of Korea
6 shared publications - Tianlong Chen
University of North Carolina at Chapel Hill
3 shared publications - Tsuyoshi Murata
Institute of Science Tokyo, Tokyo, Japan
3 shared publications - Xin Liu
National Institute of Advanced Industrial Science and Technology, Tokyo, Japan
3 shared publications - Alexandro E. Trevino
Enable Medicine, Menlo Park, USA
2 shared publications - Dongmin Hyun
POSTECH, Pohang, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3704-3715
Oldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3704-3715
Open AccessOldie but Goodie: Re-illuminating Label Propagation on Graphs with Partially Observed Features
- 27 November 2024
- Published by Springer Nature
- p. 127-144
Mew: Multiplexed Immunofluorescence Image Analysis Through an Efficient Multiplex Network
- 27 November 2024
- Published by Springer Nature
- p. 127-144
Mew: Multiplexed Immunofluorescence Image Analysis Through an Efficient Multiplex Network
- Open Access
Mew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network
Recent advancements in graph-based approaches for multiplexed immunofluorescence (mIF) images have significantly propelled the field forward, offering deeper insights into patient-level phenotyping. However, current graph-based methodologies encounter two primary challenges: (1) Cellular Heterogeneity, where existing approaches fail to adequately address the inductive biases inherent in graphs, particularly the homophily characteristic observed in cellular connectivity and; (2) Scalability, where handling cellular graphs from high-dimensional images faces difficulties in managing a high number of cells. To overcome these limitations, we introduce Mew, a novel framework designed to efficiently process mIF images through the lens of multiplex network. Mew innovatively constructs a multiplex network comprising two distinct layers: a Voronoi network for geometric information and a Cell-type network for capturing cell-wise homogeneity. This framework equips a scalable and efficient Graph Neural Network (GNN), capable of processing the entire graph during training. Furthermore, Mew integrates an interpretable attention module that autonomously identifies relevant layers for image classification. Extensive experiments on a real-world patient dataset from various institutions highlight Mew's remarkable efficacy and efficiency, marking a significant advancement in mIF image analysis. The source code of Mew can be found here: \url{https://github.com/UNITES-Lab/Mew}
Open AccessMew: Multiplexed Immunofluorescence Image Analysis through an Efficient Multiplex Network
Recent advancements in graph-based approaches for multiplexed immunofluorescence (mIF) images have significantly propelled the field forward, offering deeper insights into patient-level phenotyping. However, current graph-based methodologies encounter two primary challenges: (1) Cellular Heterogeneity, where existing approaches fail to adequately address the inductive biases inherent in graphs, particularly the homophily characteristic observed in cellular connectivity and; (2) Scalability, where handling cellular graphs from high-dimensional images faces difficulties in managing a high number of cells. To overcome these limitations, we introduce Mew, a novel framework designed to efficiently process mIF images through the lens of multiplex network. Mew innovatively constructs a multiplex network comprising two distinct layers: a Voronoi network for geometric information and a Cell-type network for capturing cell-wise homogeneity. This framework equips a scalable and efficient Graph Neural Network (GNN), capable of processing the entire graph during training. Furthermore, Mew integrates an interpretable attention module that autonomously identifies relevant layers for image classification. Extensive experiments on a real-world patient dataset from various institutions highlight Mew's remarkable efficacy and efficiency, marking a significant advancement in mIF image analysis. The source code of Mew can be found here: \url{https://github.com/UNITES-Lab/Mew}
- 25 April 2024
- Published by Springer Nature
- p. 376-389
DEGNN: Dual Experts Graph Neural Network Handling both Edge and Node Feature Noise
- 25 April 2024
- Published by Springer Nature
- p. 376-389
DEGNN: Dual Experts Graph Neural Network Handling both Edge and Node Feature Noise
- Open Access
DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
Graph Neural Networks (GNNs) have achieved notable success in various applications over graph data. However, recent research has revealed that real-world graphs often contain noise, and GNNs are susceptible to noise in the graph. To address this issue, several Graph Structure Learning (GSL) models have been introduced. While GSL models are tailored to enhance robustness against edge noise through edge reconstruction, a significant limitation surfaces: their high reliance on node features. This inherent dependence amplifies their susceptibility to noise within node features. Recognizing this vulnerability, we present DEGNN, a novel GNN model designed to adeptly mitigate noise in both edges and node features. The core idea of DEGNN is to design two separate experts: an edge expert and a node feature expert. These experts utilize self-supervised learning techniques to produce modified edges and node features. Leveraging these modified representations, DEGNN subsequently addresses downstream tasks, ensuring robustness against noise present in both edges and node features of real-world graphs. Notably, the modification process can be trained end-to-end, empowering DEGNN to adjust dynamically and achieves optimal edge and node representations for specific tasks. Comprehensive experiments demonstrate DEGNN's efficacy in managing noise, both in original real-world graphs and in graphs with synthetic noise.
Open AccessDEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
Graph Neural Networks (GNNs) have achieved notable success in various applications over graph data. However, recent research has revealed that real-world graphs often contain noise, and GNNs are susceptible to noise in the graph. To address this issue, several Graph Structure Learning (GSL) models have been introduced. While GSL models are tailored to enhance robustness against edge noise through edge reconstruction, a significant limitation surfaces: their high reliance on node features. This inherent dependence amplifies their susceptibility to noise within node features. Recognizing this vulnerability, we present DEGNN, a novel GNN model designed to adeptly mitigate noise in both edges and node features. The core idea of DEGNN is to design two separate experts: an edge expert and a node feature expert. These experts utilize self-supervised learning techniques to produce modified edges and node features. Leveraging these modified representations, DEGNN subsequently addresses downstream tasks, ensuring robustness against noise present in both edges and node features of real-world graphs. Notably, the modification process can be trained end-to-end, empowering DEGNN to adjust dynamically and achieves optimal edge and node representations for specific tasks. Comprehensive experiments demonstrate DEGNN's efficacy in managing noise, both in original real-world graphs and in graphs with synthetic noise.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1928-1938
MUSE: Music Recommender System with Shuffle Play Recommendation Enhancement
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1928-1938
Open AccessMUSE: Music Recommender System with Shuffle Play Recommendation Enhancement
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4003-4007
S-Mixup: Structural Mixup for Graph Neural Networks
Existing studies for applying the mixup technique on graphs mainly focus on graph classification tasks, while the research in node classification is still under-explored. In this paper, we propose a novel mixup augmentation for node classification called Structural Mixup (S-Mixup). The core idea is to take into account the structural information while mixing nodes. Specifically, S-Mixup obtains pseudo-labels for unlabeled nodes in a graph along with their prediction confidence via a Graph Neural Network (GNN) classifier. These serve as the criteria for the composition of the mixup pool for both inter and intra-class mixups. Furthermore, we utilize the edge gradient obtained from the GNN training and propose a gradient-based edge selection strategy for selecting edges to be attached to the nodes generated by the mixup. Through extensive experiments on real-world benchmark datasets, we demonstrate the effectiveness of S-Mixup evaluated on the node classification task. We observe that S-Mixup enhances the robustness and generalization performance of GNNs, especially in heterophilous situations. The source code of S-Mixup can be found at https://github.com/SukwonYun/S-Mixup
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4003-4007
Open AccessS-Mixup: Structural Mixup for Graph Neural Networks
Existing studies for applying the mixup technique on graphs mainly focus on graph classification tasks, while the research in node classification is still under-explored. In this paper, we propose a novel mixup augmentation for node classification called Structural Mixup (S-Mixup). The core idea is to take into account the structural information while mixing nodes. Specifically, S-Mixup obtains pseudo-labels for unlabeled nodes in a graph along with their prediction confidence via a Graph Neural Network (GNN) classifier. These serve as the criteria for the composition of the mixup pool for both inter and intra-class mixups. Furthermore, we utilize the edge gradient obtained from the GNN training and propose a gradient-based edge selection strategy for selecting edges to be attached to the nodes generated by the mixup. Through extensive experiments on real-world benchmark datasets, we demonstrate the effectiveness of S-Mixup evaluated on the node classification task. We observe that S-Mixup enhances the robustness and generalization performance of GNNs, especially in heterophilous situations. The source code of S-Mixup can be found at https://github.com/SukwonYun/S-Mixup
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 68-77
MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation
The long-tailed problem is a long-standing challenge in Sequential Recommender Systems (SRS) in which the problem exists in terms of both users and items. While many existing studies address the long-tailed problem in SRS, they only focus on either the user or item perspective. However, we discover that the long-tailed user and item problems exist at the same time, and considering only either one of them leads to sub-optimal performance of the other one. In this paper, we propose a novel framework for SRS, called Mutual Enhancement of Long-Tailed user and item (MELT), that jointly alleviates the long-tailed problem in the perspectives of both users and items. MELT consists of bilateral branches each of which is responsible for long-tailed users and items, respectively, and the branches are trained to mutually enhance each other, which is trained effectively by a curriculum learning-based training. MELT is model-agnostic in that it can be seamlessly integrated with existing SRS models. Extensive experiments on eight datasets demonstrate the benefit of alleviating the long-tailed problems in terms of both users and items even without sacrificing the performance of head users and items, which has not been achieved by existing methods. To the best of our knowledge, MELT is the first work that jointly alleviates the long-tailed user and item problems in SRS.
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 68-77
Open AccessMELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation
The long-tailed problem is a long-standing challenge in Sequential Recommender Systems (SRS) in which the problem exists in terms of both users and items. While many existing studies address the long-tailed problem in SRS, they only focus on either the user or item perspective. However, we discover that the long-tailed user and item problems exist at the same time, and considering only either one of them leads to sub-optimal performance of the other one. In this paper, we propose a novel framework for SRS, called Mutual Enhancement of Long-Tailed user and item (MELT), that jointly alleviates the long-tailed problem in the perspectives of both users and items. MELT consists of bilateral branches each of which is responsible for long-tailed users and items, respectively, and the branches are trained to mutually enhance each other, which is trained effectively by a curriculum learning-based training. MELT is model-agnostic in that it can be seamlessly integrated with existing SRS models. Extensive experiments on eight datasets demonstrate the benefit of alleviating the long-tailed problems in terms of both users and items even without sacrificing the performance of head users and items, which has not been achieved by existing methods. To the best of our knowledge, MELT is the first work that jointly alleviates the long-tailed user and item problems in SRS.