U Kang

6.4k total citations · 1 hit paper
161 papers, 3.8k citations indexed

About

U Kang is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Statistical and Nonlinear Physics. According to data from OpenAlex, U Kang has authored 161 papers receiving a total of 3.8k indexed citations (citations by other indexed papers that have themselves been cited), including 83 papers in Artificial Intelligence, 73 papers in Computer Vision and Pattern Recognition and 44 papers in Statistical and Nonlinear Physics. Recurrent topics in U Kang's work include Graph Theory and Algorithms (47 papers), Advanced Graph Neural Networks (44 papers) and Complex Network Analysis Techniques (44 papers). U Kang is often cited by papers focused on Graph Theory and Algorithms (47 papers), Advanced Graph Neural Networks (44 papers) and Complex Network Analysis Techniques (44 papers). U Kang collaborates with scholars based in South Korea, United States and Italy. U Kang's co-authors include Christos Faloutsos, Charalampos E. Tsourakakis, K.D. Wise, Yongsub Lim, Evangelos E. Papalexakis, Lee Sael, Jinhong Jung, Hanghang Tong, Jimeng Sun and Jaemin Yoo and has published in prestigious journals such as PLoS ONE, IEEE Access and BMC Bioinformatics.

In The Last Decade

U Kang

151 papers receiving 3.7k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

PEGASUS: A Peta-Scale Graph Mining System Implementation and Observations

2009 426 citations U Kang et al. profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
U Kang South Korea	32	1.9k	1.5k	1.0k	827	772	161	3.8k
James Cheng Hong Kong	38	2.2k 1.2×	2.1k 1.4×	1.2k 1.1×	1.1k 1.3×	1.5k 1.9×	137	4.7k
Spiros Papadimitriou United States	23	1.5k 0.8×	456 0.3×	603 0.6×	547 0.7×	773 1.0×	53	2.7k
Evangelos E. Papalexakis United States	23	1.1k 0.6×	423 0.3×	330 0.3×	228 0.3×	326 0.4×	112	2.9k
Hong Cheng Hong Kong	39	3.3k 1.8×	1.2k 0.8×	1.8k 1.8×	2.6k 3.1×	1.4k 1.8×	145	6.3k
Christopher Ré United States	38	3.1k 1.7×	1.1k 0.7×	131 0.1×	1.1k 1.3×	1.7k 2.2×	153	5.3k
Quanquan Gu United States	32	2.3k 1.2×	900 0.6×	399 0.4×	894 1.1×	530 0.7×	142	3.8k
Matthew Roughan Australia	34	1.9k 1.0×	207 0.1×	617 0.6×	376 0.5×	4.5k 5.9×	139	5.9k
Nina Taft United States	33	1.9k 1.0×	248 0.2×	230 0.2×	526 0.6×	2.3k 3.0×	83	3.9k
Danai Koutra United States	22	2.0k 1.1×	592 0.4×	1.2k 1.2×	516 0.6×	793 1.0×	93	3.0k
Anukool Lakhina United States	19	2.6k 1.4×	172 0.1×	558 0.5×	372 0.4×	4.1k 5.3×	25	4.8k

Countries citing papers authored by U Kang

Since Specialization

Citations

This map shows the geographic impact of U Kang's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by U Kang with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites U Kang more than expected).

Fields of papers citing papers by U Kang

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by U Kang. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by U Kang. The network helps show where U Kang may publish in the future.

Co-authorship network of co-authors of U Kang

This figure shows the co-authorship network connecting the top 25 collaborators of U Kang. A scholar is included among the top collaborators of U Kang based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with U Kang. U Kang is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

1.

Kang, U, et al.. (2025). Mitigating Distribution Shift in Stock Price Data via Return-Volatility Normalization for Accurate Prediction. 1458–1467.

2.

Kang, U, et al.. (2025). PuzzleTensor: A Method-Agnostic Data Transformation for Compact Tensor Factorization. 2234–2244.

3.

Lee, Wookey, et al.. (2024). DDC3N: Doppler-Driven Convolutional 3D Network for Human Action Recognition. IEEE Access. 12. 93546–93567. 6 indexed citations

4.

Kang, U, et al.. (2024). Fast and Accurate PARAFAC2 Decomposition for Time Range Queries on Irregular Tensors. 962–972. 2 indexed citations

5.

Kang, U, et al.. (2023). Accurate Open-Set Recognition for Memory Workload. ACM Transactions on Knowledge Discovery from Data. 17(9). 1–14. 4 indexed citations

6.

Kang, U, et al.. (2023). PET: Parameter-efficient Knowledge Distillation on Transformer. PLoS ONE. 18(7). e0288060–e0288060. 5 indexed citations

7.

Kang, U, et al.. (2023). Fast and accurate interpretation of workload classification model. PLoS ONE. 18(3). e0282595–e0282595. 2 indexed citations

8.

Yoo, Jaemin, et al.. (2022). Accurate Stock Movement Prediction with Self-supervised Learning from Sparse Noisy Tweets. 2022 IEEE International Conference on Big Data (Big Data). 1691–1700. 14 indexed citations

9.

Yoo, Jaemin, et al.. (2021). Accurate Graph-Based PU Learning without Class Prior. 827–836. 3 indexed citations

10.

Kim, Junghun, Jinhong Jung, & U Kang. (2021). Compressing deep graph convolution network with multi-staged knowledge distillation. PLoS ONE. 16(8). e0256187–e0256187. 11 indexed citations

11.

Kang, U, et al.. (2020). D-Tucker: Fast and Memory-Efficient Tucker Decomposition for Dense Tensors. 1850–1853. 17 indexed citations

12.

Park, Namyong, et al.. (2020). PACC: Large scale connected component computation on Hadoop and Spark. PLoS ONE. 15(3). e0229936–e0229936. 4 indexed citations

13.

Lim, Yongsub, et al.. (2019). PS-MCL: parallel shotgun coarsened Markov clustering of protein interaction networks. BMC Bioinformatics. 20(S13). 381–381. 7 indexed citations

14.

Jin, Woojeong, Jinhong Jung, & U Kang. (2019). Supervised and extended restart in random walks for ranking and link prediction in networks. PLoS ONE. 14(3). e0213857–e0213857. 29 indexed citations

15.

Yu, Seok Jong, et al.. (2016). Efficient Subgraph Matching on Large Networks. 275–276. 1 indexed citations

16.

Lee, Jungwoo, et al.. (2016). TeT: Distributed Tera-Scale Tensor Generator. Journal of KIISE. 43(8). 910–918. 1 indexed citations

17.

Kang, U, Hanghang Tong, & Jimeng Sun. (2012). Fast Random Walk Graph Kernel. 828–838. 64 indexed citations

18.

Kang, U, et al.. (2012). Design and Implementation of a Real-time Automatic Disaster and Information Broadcasting System. Journal of Digital Convergence. 10(7). 141–152. 2 indexed citations

19.

Lee, Young Ho, et al.. (2009). Development of Mining model through reproducibility assessment in Adverse drug event surveillance system. Journal of the Korea Society of Computer and Information. 14(3). 183–192. 2 indexed citations

20.

Yoon, Youngmi & U Kang. (2005). Recovery techniques for Main-Memory database system. 한국정보기술학회논문지. 3(5). 73–88. 2 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact