70 citations · 467 across the 48 of their papers we have counts for
50 papers
Robust Graph Clustering via Meta Weighting for Noisy Graphs
Hyeonsoo Jo, Fanchen Bu, Kijung Shin
How can we find meaningful clusters in a graph robustly against noise edges? Graph clustering (i.e., dividing nodes into groups of similar ones) is a fundamental problem in graph a…
Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs
Dongjin Lee, Juho Lee, Kijung Shin
Real-world graphs are dynamic, constantly evolving with new interactions, such as financial transactions in financial networks. Temporal Graph Neural Networks (TGNNs) have been dev…
Social network modeling and applications, a tutorial
Lisette Espín-Noboa, Tiago Peixoto, Fariba Karimi
Social networks have been widely studied over the last century from multiple disciplines to understand societal issues such as inequality in employment rates, managerial performanc…
On Improving the Cohesiveness of Graphs by Merging Nodes: Formulation, Analysis, and Algorithms
Fanchen Bu, Kijung Shin
Graphs are a powerful mathematical model, and they are used to represent real-world structures in various fields. In many applications, real-world structures with high connectivity…
Classification of Edge-dependent Labels of Nodes in Hypergraphs
Minyoung Choe, Sunwoo Kim, Jaemin Yoo +1
A hypergraph is a data structure composed of nodes and hyperedges, where each hyperedge is an any-sized subset of nodes. Due to the flexibility in hyperedge size, hypergraphs repre…
Towards Deep Attention in Graph Neural Networks: Problems and Remedies
Soo Yong Lee, Fanchen Bu, Jaemin Yoo +1
Graph neural networks (GNNs) learn the representation of graph-structured data, and their expressiveness can be further enhanced by inferring node relations for propagation. Attent…
How Transitive Are Real-World Group Interactions? -- Measurement and Reproduction
Sunwoo Kim, Fanchen Bu, Minyoung Choe +2
Many real-world interactions (e.g., researcher collaborations and email communication) occur among multiple entities. These group interactions are naturally modeled as hypergraphs.…
Interplay between Topology and Edge Weights in Real-World Graphs: Concepts, Patterns, and an Algorithm
Fanchen Bu, Shinhwan Kang, Kijung Shin
What are the relations between the edge weights and the topology in real-world graphs? Given only the topology of a graph, how can we assign realistic weights to its edges based on…
NeuKron: Constant-Size Lossy Compression of Sparse Reorderable Matrices and Tensors
Taehyung Kwon, Jihoon Ko, Jinhong Jung +1
Many real-world data are naturally represented as a sparse reorderable matrix, whose rows and columns can be arbitrarily ordered (e.g., the adjacency matrix of a bipartite graph).…
Characterization of Simplicial Complexes by Counting Simplets Beyond Four Nodes
Hyunju Kim, Jihoon Ko, Fanchen Bu +1
Simplicial complexes are higher-order combinatorial structures which have been used to represent real-world complex systems. In this paper, we concentrate on the local patterns in…
Graphlets over Time: A New Lens for Temporal Network Analysis
Deukryeol Yoon, Dongjin Lee, Minyoung Choe +1
Graphs are widely used for modeling various types of interactions, such as email communications and online discussions. Many of such real-world graphs are temporal, and specificall…
Hypercore Decomposition for Non-Fragile Hyperedges: Concepts, Algorithms, Observations, and Applications
Fanchen Bu, Geon Lee, Kijung Shin
Hypergraphs are a powerful abstraction for modeling high-order relations, which are ubiquitous in many fields. A hypergraph consists of nodes and hyperedges (i.e., subsets of nodes…
Region-Conditioned Orthogonal 3D U-Net for Weather4Cast Competition
Taehyeon Kim, Shinhwan Kang, Hyeonjeong Shin +4
The Weather4Cast competition (hosted by NeurIPS 2022) required competitors to predict super-resolution rain movies in various regions of Europe when low-resolution satellite contex…
BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning
Jihoon Ko, Shinhwan Kang, Taehyung Kwon +2
Continual Learning (CL) is the process of learning ceaselessly a sequence of tasks. Most existing CL methods deal with independent data (e.g., images and text) for which many bench…
Deep-Learning-Based Precipitation Nowcasting with Ground Weather Station Data and Radar Data
Jihoon Ko, Kyuhan Lee, Hyunjin Hwang +1
Recently, many deep-learning techniques have been applied to various weather-related prediction tasks, including precipitation nowcasting (i.e., predicting precipitation levels and…
Set2Box: Similarity Preserving Representation Learning of Sets
Geon Lee, Chanyoung Park, Kijung Shin
Sets have been used for modeling various types of objects (e.g., a document as the set of keywords in it and a customer as the set of the items that she has purchased). Measuring s…
Reciprocity in Directed Hypergraphs: Measures, Findings, and Generators
Sunwoo Kim, Minyoung Choe, Jaemin Yoo +1
Group interactions are prevalent in a variety of areas. Many of them, including email exchanges, chemical reactions, and bitcoin transactions, are directional, and thus they are na…
I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphs
Dongjin Lee, Kijung Shin
Although machine learning on hypergraphs has attracted considerable attention, most of the works have focused on (semi-)supervised learning, which may cause heavy labeling costs an…
AHP: Learning to Negative Sample for Hyperedge Prediction
Hyunjin Hwang, Seungwoo Lee, Chanyoung Park +1
Hypergraphs (i.e., sets of hyperedges) naturally represent group relations (e.g., researchers co-authoring a paper and ingredients used together in a recipe), each of which corresp…
HashNWalk: Hash and Random Walk Based Anomaly Detection in Hyperedge Streams
Geon Lee, Minyoung Choe, Kijung Shin
Sequences of group interactions, such as emails, online discussions, and co-authorships, are ubiquitous; and they are naturally represented as a stream of hyperedges. Despite their…
Personalized Graph Summarization: Formulation, Scalable Algorithms, and Applications
Shinhwan Kang, Kyuhan Lee, Kijung Shin
Are users of an online social network interested equally in all connections in the network? If not, how can we obtain a summary of the network personalized to specific users? Can w…
Meta-Learning for Online Update of Recommender Systems
Minseok Kim, Hwanjun Song, Yooju Shin +3
Online recommender systems should be always aligned with users' current interest to accurately suggest items that each user would like. Since user interest usually evolves over tim…
Are Edge Weights in Summary Graphs Useful? -- A Comparative Study
Shinhwan Kang, Kyuhan Lee, Kijung Shin
Which one is better between two representative graph summarization models with and without edge weights? From web graphs to online social networks, large graphs are everywhere. Gra…
Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation
Jihoon Ko, Kyuhan Lee, Hyunjin Hwang +3
Deep learning has been successfully applied to precipitation nowcasting. In this work, we propose a pre-training scheme and a new loss function for improving deep-learning-based no…