S
Se-eun Yoon
Researcher at KAIST
Publications - 8
Citations - 130
Se-eun Yoon is an academic researcher from KAIST. The author has contributed to research in topics: Constraint graph & Pairwise comparison. The author has an hindex of 3, co-authored 7 publications receiving 41 citations.
Papers
More filters
Proceedings ArticleDOI
Structural Patterns and Generative Models of Real-world Hypergraphs
TL;DR: This work empirically finds that at each decomposition level, the investigated hypergraphs obey five structural properties, which serve as criteria for evaluating how realistic a hypergraph is, and establish a foundation for the hypergraph generation problem.
Proceedings ArticleDOI
How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction
TL;DR: In this article, the authors propose a method of incrementally representing group interactions using a notion of n-projected graph whose accumulation contains information on up to n-way interactions, and quantify the accuracy of solving a task as n grows for various datasets.
Proceedings ArticleDOI
How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Prediction
TL;DR: In this article, the authors propose a method of incrementally representing group interactions using a notion of n-projected graph whose accumulation contains information on up to n-way interactions, and quantify the accuracy of solving a task as n grows for various datasets.
Proceedings ArticleDOI
Solving Continual Combinatorial Selection via Deep Reinforcement Learning
Hyungseok Song,Hyeryung Jang,Hai H. Tran,Se-eun Yoon,Kyunghwan Son,Donggyu Yun,Hyoju Chung,Yung Yi +7 more
TL;DR: A deep RL algorithm is presented to solve the intractable problem of selecting a subset of items at each step of the Markov Decision Process by exploiting a special symmetry in IS-MDPs with novel weight shared Q-networks, which prov-ably maintain sufficient expressive power.
Proceedings ArticleDOI
Structural Patterns and Generative Models of Real-world Hypergraphs
TL;DR: In this paper, a multi-level decomposition method is proposed to represent each hypergraph by a set of pairwise graphs, which capture the interactions between pairs of subsets of k nodes.