Publications

[ Google Scholar | DBLP | Research Gate ]

2023 and Forthcoming

[T2]

Mining of Real-world Hypergraphs: Patterns, Tools, and Generators

Geon Lee, Jaemin Yoo, and Kijung Shin
KDD 2023 & WWW 2023 (Tutorial) [ slides ]

[C57]

How Transitive Are Real-World Group Interactions? - Measurement and Reproduction

[C56]

On Improving the Cohesiveness of Graphs by Merging Nodes: Formulation, Analysis, and Algorithms

[C55]

Classification of Edge-dependent Labels of Nodes in Hypergraphs

[C54]

Towards Deep Attention in Graph Neural Networks: Problems and Remedies

Soo Yong Lee, Fanchen Bu, Jaemin Yoo, and Kijung Shin
ICML 2023 [ paper | video | slides | code and datasets | bib ]

[C53]

NeuKron: Constant-Size Lossy Compression of Sparse Reorderable Matrices and Tensors

[C52]

Characterization of Simplicial Complexes Using Simplets Beyond Four Nodes

[C51]

Disentangling Degree-related Biases and Interest for
Out-of-Distribution Generalized Directed Network Embedding

Hyunsik Yoo, Yeon-Chang Lee, Kijung Shin, and Sang-Wook Kim
WWW 2023 [ paper | slides | code | bib ]

[C50]

I'm Me, We're Us, and I'm Us: Tridirectional Contrastive Learning on Hypergraphs

Dongjin Lee and Kijung Shin
AAAI 2023 [ paper | video | slides | code and datasets | bib ]

[C49]

Robust and Efficient Alignment of Calcium Imaging Data through
Simultaneous Low Rank and Sparse Decomposition

Junmo Cho*, Seungjae Han*, Eun-Seo Cho, Kijung Shin, and Young-Gyu Yoon
WACV 2023 [ paper | code and dataset | bib ]

[J17]

Interplay between Topology and Edge Weights in Real-World Graphs:
Concepts, Patterns, and an Algorithm

Fanchen Bu, Shinhwan Kang, and Kijung Shin
Data Mining and Knowledge Discovery [ paper | slides | code and datasets | bib ]

[J16]

Temporal Hypergraph Motifs

Geon Lee and Kijung Shin
Knowledge and Information Systems [ paper | shorter ver. [C35] | code and datasets | bib ]

[J15]

Evaluation of Deep-Learning-Based Very Short-Term Rainfall Forecasts in South Korea

Seok-Geun Oh , Chanil Park, Seok-Woo Son, Jihoon Ko, Kijung Shin, Sunyoung Kim, and Junsang Park
Asia-Pacific Journal of Atmospheric Sciences [ paper | bib ]

[J14]

Two-Stage Training of Graph Neural Networks for Graph Classification

Manh Tuan Do, Noseng Park, and Kijung Shin
Neural Processing Letters [ paper | code and datasets | bib ]
A shorter version appeared at DLG-AAAI 2021

2022

[T1]

Mining of Real-world Hypergraphs: Patterns, Tools, and Generators

Geon Lee, Jaemin Yoo, and Kijung Shin
ICDM 2022 & CIKM 2022 (Tutorial) [ proposal | video | slides | bib ]

[C48]

Reciprocity in Directed Hypergraphs: Measures, Findings, and Generators

Sunwoo Kim, Minyoung Choe, Jaemin Yoo, and Kijung Shin
ICDM 2022 [ paper | longer ver. | slides | code and datasets | bib ]

[C47]

Set2Box: Similarity Preserving Representation Learning for Sets

Geon Lee, Chanyoung Park, and Kijung Shin
ICDM 2022 [ paper | longer ver. | slides | code and datasets | bib ]

[C46]

MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation

Taeri Kim*, Yeon-Chang Lee*, Kijung Shin, and Sang-Wook Kim
CIKM 2022 [ paper | slides | bib ]

[C45]

HashNWalk: Hash and Random Walk Based Anomaly Detection in Hyperedge Streams

[C44]

AHP: Learning to Negative Sample for Hyperedge Prediction

Hyunjin Hwang*, Seungwoo Lee*, Chanyoung Park, and Kijung Shin
SIGIR 2022 (Short Paper) [ paper | video | slides | code and datasets | bib ]

[C43]

Are Edge Weights in Summary Graphs Useful? - A Comparative Study

Shinhwan Kang, Kyuhan Lee, and Kijung Shin
PAKDD 2022 [ paper | appendix | slides | code and datasets | bib ]

[C42]

Personalized Graph Summarization: Formulation, Scalable Algorithms, and Applications

[C41]

SLUGGER: Lossless Hierarchical Summarization of Massive Graphs

[C40]

MiDaS: Representative Sampling from Real-world Hypergraphs

[C39]

On the Persistence of Higher-Order Interactions in Real-World Hypergraphs

[C38]

Meta-Learning for Online Update of Recommender Systems

Minseok Kim, Hwanjun Song, Yooju Shin, Dongmin Park, Kijung Shin, and Jae-Gil Lee
AAAI 2022 [ paper | bib ]

[C37]

Finding a Concise, Precise, and Exhaustive Set of Near Bi-Cliques in Dynamic Graphs

[C36]

Directed Network Embedding with Virtual Negative Edges

Hyunsik Yoo*, Yeon-Chang Lee*, Kijung Shin, and Sang-Wook Kim
WSDM 2022 [ paper | slides | code and datasets | bib ]

[J13]

Growth Patterns and Models of Real-world Hypergraphs

Jihoon Ko*, Yunbum Kook*, and Kijung Shin
Knowledge and Information Systems [ paper | shorter ver. [C27] | code and datasets | bib ]

[J12]

Effective Training Strategies for Deep-Learning-Based Precipitation Nowcasting and Estimation

Jihoon Ko*, Kyuhan Lee*, Hyunjin Hwang*, Seok-Geun Oh, Seok-Woo Son, and Kijung Shin
Computers and Geosciences [ paper | code | bib ]

[J11]

Simple Epidemic Models with Segmentation Can Be Better than Complex Ones

Geon Lee, Se-eun Yoon, and Kijung Shin
PLOS ONE [ paper | appendix | slides | code and datasets | bib ]
A shorter version appeared at epiDAMIK-KDD 2021 (long oral)

[J10]

Real-Time Anomaly Detection in Edge Streams

Siddharth Bhatia, Rui Liu, Bryan Hooi, Minji Yoon, Kijung Shin, and Christos Faloutsos
ACM TKDD [ paper | shorter ver. [C20] | code and datasets | bib ]

2021

[C35]

THyMe+: Temporal Hypergraph Motifs and Fast Algorithms for Exact Counting

[C34]

Efficient Neural Network Approximation of Robust PCA for Automated Analysis of
Calcium Imaging Data

Seungjae Han, Eun-Seo Cho, Inkyu Park, Kijung Shin, and Young-Gyu Yoon
MICCAI 2021 [ paper | code and datasets | bib ]

[C33]

SliceNStitch: Continuous CP Decomposition of Sparse Tensor Streams

[C32]

Robust Factorization of Real-world Tensor Streams with Patterns, Missing Values, and Outliers

[C31]

How Do Hyperedges Overlap in Real-World Hypergraphs? - Patterns, Measures, and Generators

[C30]

PREMERE: Meta-Reweighting via Self-Ensembling for Point-of-Interest Recommendation

Minseok Kim, Hwanjun Song, Doyoung Kim, Kijung Shin, and Jae-Gil Lee
AAAI 2021 [ paper | bib ]

[C29]

DPGS: Degree-Preserving Graph Summarization

Houquan Zhou, Shenghua Liu, Kyuhan Lee, Kijung Shin, Huawei Shen, and Xueqi Cheng
SDM 2021 [ paper | code and datasets | bib ]

[J9]

CoCoS: Fast and Accurate Distributed Triangle Counting in Graph Streams

Kijung Shin, Euiwoong Lee, Jinoh Oh, Mohammad Hammoud, and Christos Faloutsos
ACM TKDD [ paper | shorter ver. [C13] | code and datasets | bib ]

2020

[C28]

MONSTOR: An Inductive Approach for Estimating and Maximizing Influence over Unseen Networks

Jihoon Ko, Kyuhan Lee, Kijung Shin, and Noseong Park
ASONAM 2020 [ paper | slides | code and datasets | bib ]
Selected for fast-track journal invitation

[C27]

Evolution of Real-world Hypergraphs: Patterns and Models without Oracles

[C26]

Hypergraph Motifs: Concepts, Algorithms, and Discoveries

[C25]

Incremental Lossless Graph Summarization

[C24]

SSumM: Sparse Summarization of Massive Graphs

[C23]

Structural Patterns and Generative Models of Real-world Hypergraphs

[C22]

How Much and When Do We Need Higher-order Information in Hypergraphs?
A Case Study on Hyperedge Prediction

[C21]

TellTail: Fast Scoring and Detection of Dense Subgraphs

Bryan Hooi, Kijung Shin, Hemank Lamba, and Christos Faloutsos
AAAI 2020 [ paper | appendix | code | bib ]
Oral Presentation

[C20]

MIDAS: Microcluster-Based Detector of Anomalies in Edge Streams

Siddharth Bhatia, Bryan Hooi, Minji Yoon, Kijung Shin, and Christos Faloutsos
AAAI 2020 [ paper | longer ver. [J10] | code and datasets | bib ]
Oral Presentation

[J8]

Temporal Locality-Aware Sampling for Accurate Triangle Counting in Real Graph Streams

Dongjin Lee, Kijung Shin, and Christos Faloutsos
The VLDB Journal [ paper | shorter ver. [C12] | code and datasets | bib ]

[J7]

Fast and Memory-Efficient Algorithms for High-Order Tucker Decomposition

Jiyuan Zhang, Jinoh Oh, Kijung Shin, Evangelos E. Papalexakis, Christos Faloutsos, and Hwanjo Yu
Knowledge and Information Systems [ paper | shorter ver. [C7] | code | bib ]

[J6]

Fast, Accurate and Provable Triangle Counting in Fully Dynamic Graph Streams

Kijung Shin, Sejoon Oh, Jisu Kim, Bryan Hooi, and Christos Faloutsos
ACM TKDD [ paper | shorter ver. [C16] | code and datasets | bib ]

2019

[C19]

Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach

Minji Yoon, Bryan Hooi, Kijung Shin, and Christos Faloutsos
KDD 2019 [ paper | video | code | bib ]

[C18]

SWeG: Lossless and Lossy Summarization of Web-Scale Graphs

Kijung Shin, Amol Ghoting, Myunghwan Kim, and Hema Raghavan
WWW 2019 [ paper | slides | poster | patent | bib ]

[C17]

SMF: Drift Aware Matrix Factorization with Seasonal Patterns

Bryan Hooi, Kijung Shin, Shenghua Liu, and Christos Faloutsos
SDM 2019 [ paper | code | bib ]

[D3]

Mining Large Dynamic Graphs and Tensors

Kijung Shin
Ph.D. Thesis, Carnegie Mellon University, 2019 [ paper | slides | code and datasets | bib ]

2018

[C16]

Think Before You Discard: Accurate Triangle Counting in Graph Streams with Deletions

[C15]

ONE-M: Modeling the Co-evolution of Opinions and Network Connections

Aastha Nigam, Kijung Shin, Ashwin Bahulkar, Bryan Hooi, David Hachen,
Boleslaw Szymanski, Christos Faloutsos, and Nitesh Chawla
PKDD 2018 [ paper | bib ]

[C14]

Discovering Progression Stages in Trillion-Scale Behavior Logs

Kijung Shin, Mahdi Shafiei, Myunghwan Kim, Aastha Jain, and Hema Raghavan
WWW 2018 (Industry Track) [ paper | slides | bib ]

[C13]

Tri-Fly: Distributed Estimation of Global and Local Triangle Counts in Graph Streams

[J5]

Fast, Accurate and Flexible Algorithms for Dense Subtensor Mining

Kijung Shin, Bryan Hooi, and Christos Faloutsos
ACM TKDD [ paper | shorter ver. [C5] | code and datasets | bib ]

[J4]

Patterns and Anomalies in k-Cores of Real-World Graphs with Applications

Kijung Shin, Tina Eliassi-Rad, and Christos Faloutsos
Knowledge and Information Systems [ paper | shorter ver. [C6] | code and datasets | bib ]
Taught in courses: MIT (6.886)

[D2]

Mining Large Dynamic Graphs and Tensors: Thesis Proposal

Kijung Shin
Ph.D. Thesis Proposal, Carnegie Mellon University, 2018 [ paper | slides | code and datasets ]

2017

[C12]

WRS: Waiting Room Sampling for Accurate Triangle Counting in Real Graph Streams

[C11]

ZooRank: Ranking Suspicious Entities in Time-Evolving Tensors

Hemank Lamba, Bryan Hooi, Kijung Shin, Christos Faloutsos, and Jürgen Pfeffer
PKDD 2017 [ paper | code and datasets | bib ]

[C10]

DenseAlert: Incremental Dense-Subtensor Detection in Tensor Streams

[C9]

Why You Should Charge Your Friends for Borrowing Your Stuff

Kijung Shin, Euiwoong Lee, Dhivya Eswaran, and Ariel D. Procaccia
IJCAI 2017 [ paper | slides (short) | slides (long) | bib ]
Media: New Scientist [link]

[C8]

D-Cube: Dense-Block Detection in Terabyte-Scale Tensors

[C7]

S-HOT: Scalable High-Order Tucker Decomposition

Jinoh Oh, Kijung Shin, Evangelos E. Papalexakis, Christos Faloutsos, and Hwanjo Yu
WSDM 2017 [ paper | longer ver. [J7] | code | bib ]

[J3]

Graph-Based Fraud Detection in the Face of Camouflage

Bryan Hooi, Kijung Shin, Hyun Ah Song, Alex Beutel, Neil Shah, and Christos Faloutsos
ACM TKDD [ paper | shorter ver. [C4] | code | bib ]

[J2]

Fully Scalable Methods for Distributed Tensor Factorization

Kijung Shin, Lee Sael, and U Kang
IEEE TKDE [ paper | appendix | shorter ver. [C2] | code and datasets | bib ]

2016

[C6]

CoreScope: Graph Mining Using k-Core Analysis - Patterns, Anomalies and Algorithms

[C5]

M-Zoom: Fast Dense-Block Detection in Tensors with Quality Guarantees

[C4]

FRAUDAR: Bounding Graph Fraud in the Face of Camouflage

Bryan Hooi, Hyun Ah Song, Alex Beutel, Neil Shah, Kijung Shin, and Christos Faloutsos
KDD 2016 [ paper | longer ver. [J3] | code | bib ]
KDD 2016 Best Paper Award [link], CogX 2017 Award for Best Student Paper in AI [link]
Media: NSF [link], WESA [link], TechXplore [link], Stanford Scholar [link], Crain's [link]

[J1]

Random Walk with Restart on Large Graphs Using Block Elimination

Jinhong Jung, Kijung Shin, Lee Sael, and U Kang
ACM TODS [ paper | shorter ver. [C3] | code and datasets | bib ]

2015

[D1]

Scalable Methods for Random Walk with Restart and Tensor Factorization

Kijung Shin
Senior Thesis, Seoul National University, 2015 [ paper ]
Best Thesis Award [link]

[C3]

BEAR: Block Elimination Approach for Random Walk with Restart on Large Graphs

Kijung Shin, Jinhong Jung, Lee Sael, and U Kang
SIGMOD 2015 [ paper | longer ver. [J1] | slides | code and datasets | bib ]
Samsung Humantech Paper Award (1st in Computer Science) [link],
Taught in courses: UMich (EECS 598)

2014

[C2]

Distributed Methods for High-dimensional and Large-scale Tensor Factorization

Kijung Shin and U Kang
ICDM 2014 [ paper | longer ver. [J2] | slides | code and datasets | bib ]

[C1]

Data/Feature Distributed Stochastic Coordinate Descent for Logistic Regression

Dongyeop Kang, Woosang Lim, Kijung Shin, Lee Sael, and U Kang
CIKM 2014 [ paper | appendix | bib ]

Kijung Shin (신기정)

About Me

Contact Details

Education

Carnegie Mellon University

Seoul National University

Positions

KAIST

LinkedIn

CYRAM

Teaching

KAIST AI607 Graph Mining and Social Network Analysis

KAIST AI506 Data Mining and Search

KAIST EE210 Probability and Introductory Random Processes

KAIST EE209(B) Programming Structure for Electrical Engineering

CMU 10-601 Introduction to Machine Learning

CMU 15-780 Graduate Artificial Intelligence

Publications

2023 and Forthcoming

[T2]

Mining of Real-world Hypergraphs: Patterns, Tools, and Generators

[C57]

How Transitive Are Real-World Group Interactions? - Measurement and Reproduction

[C56]

On Improving the Cohesiveness of Graphs by Merging Nodes: Formulation, Analysis, and Algorithms

[C55]

Classification of Edge-dependent Labels of Nodes in Hypergraphs

[C54]

Towards Deep Attention in Graph Neural Networks: Problems and Remedies

[C53]

NeuKron: Constant-Size Lossy Compression of Sparse Reorderable Matrices and Tensors

[C52]

Characterization of Simplicial Complexes Using Simplets Beyond Four Nodes

[C51]

Disentangling Degree-related Biases and Interest for Out-of-Distribution Generalized Directed Network Embedding

[C50]

I'm Me, We're Us, and I'm Us: Tridirectional Contrastive Learning on Hypergraphs

[C49]

Robust and Efficient Alignment of Calcium Imaging Data through Simultaneous Low Rank and Sparse Decomposition

[J17]

Interplay between Topology and Edge Weights in Real-World Graphs: Concepts, Patterns, and an Algorithm

[J16]

Temporal Hypergraph Motifs

[J15]

Evaluation of Deep-Learning-Based Very Short-Term Rainfall Forecasts in South Korea

[J14]

Two-Stage Training of Graph Neural Networks for Graph Classification

2022

[T1]

Mining of Real-world Hypergraphs: Patterns, Tools, and Generators

[C48]

Reciprocity in Directed Hypergraphs: Measures, Findings, and Generators

[C47]

Set2Box: Similarity Preserving Representation Learning for Sets

[C46]

MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation

[C45]

HashNWalk: Hash and Random Walk Based Anomaly Detection in Hyperedge Streams

[C44]

AHP: Learning to Negative Sample for Hyperedge Prediction

[C43]

Are Edge Weights in Summary Graphs Useful? - A Comparative Study

[C42]

Personalized Graph Summarization: Formulation, Scalable Algorithms, and Applications

[C41]

SLUGGER: Lossless Hierarchical Summarization of Massive Graphs

[C40]

MiDaS: Representative Sampling from Real-world Hypergraphs

[C39]

On the Persistence of Higher-Order Interactions in Real-World Hypergraphs

[C38]

Meta-Learning for Online Update of Recommender Systems

[C37]

Finding a Concise, Precise, and Exhaustive Set of Near Bi-Cliques in Dynamic Graphs

[C36]

Directed Network Embedding with Virtual Negative Edges

[J13]

Growth Patterns and Models of Real-world Hypergraphs

[J12]

Effective Training Strategies for Deep-Learning-Based Precipitation Nowcasting and Estimation

Disentangling Degree-related Biases and Interest for
Out-of-Distribution Generalized Directed Network Embedding

Robust and Efficient Alignment of Calcium Imaging Data through
Simultaneous Low Rank and Sparse Decomposition

Interplay between Topology and Edge Weights in Real-World Graphs:
Concepts, Patterns, and an Algorithm

Efficient Neural Network Approximation of Robust PCA for Automated Analysis of
Calcium Imaging Data

How Much and When Do We Need Higher-order Information in Hypergraphs?
A Case Study on Hyperedge Prediction