KSC 2021 Top Conference 특별세션 초청

본 연구실의 이연창 연구원이 KSC 2021 Top Conference 특별세션(2021. 12. 20)의 발표자로 초청되었습니다.
KSC 2021 Top Conference 특별세션은 2020-2021년 최우수 학술대회에서 발표된 논문의 저자를 초청하여, 연구 내용 소개 및 질의응답을 통해 연구원 간의 식견을 교류하는 장입니다.
[발표논문]
Title: Look Before You Leap: Confirming Edge Signs in Random Walk with Restart for Personalized Node Ranking in Signed Networks
Author: Wonchang Lee, Yeon-Chang Lee, Dongwon Lee, and Sang-Wook Kim (*co-first authors with equal contribution) Abstract
In this paper, we address the personalized node ranking (PNR) problem for signed networks, which aims to rank nodes in an order most relevant to a given seed node in a signed network. The recently-proposed PNR methods introduce the concept of the signed random surfer, denoted as SRSurfer, that performs the score propagation between nodes using the balance theory. However, in real settings of signed networks, edge relationships often do not strictly follow the rules of the balance theory. Therefore, SRSurfer-based PNR methods frequently perform incorrect score propagation to nodes, thereby degrading the accuracy of PNR. To address this limitation, we propose a novel random-walk based PNR approach with sign verification, named as OBOE (lOok Before yOu lEap). Specifically, OBOE carefully verifies the score propagation of SRSurfer by using the topological features of nodes. Then, OBOE corrects all incorrect score propagation cases by exploiting the statistics of a given network. The experiments on 3 real-world signed networks show that OBOE consistently and significantly outperforms 5 competing methods with improvement up to 13%, 95%, and 249% in top-k PNR, bottom-k PNR, and troll identification tasks, respectively. All OBOE codes and datasets are available at: http://github.com/wonchang24/OBOE.