no code implementations • 15 Apr 2024 • Jongmin Park, SeungHoon Han, Soohwan Jeong, Sungsu Lim
Most previous heterogeneous graph embedding models represent elements in a heterogeneous graph as vector representations in a low-dimensional Euclidean space.
2 code implementations • 21 Aug 2023 • Hwan Kim, JungHoon Kim, Byung Suk Lee, Sungsu Lim
To further efficiently exploit context information from metapath-based anomaly subgraph, we present a new framework, Metapath-based Graph Anomaly Detection (MGAD), incorporating GCN layers in both the dual-encoders and decoders to efficiently propagate context information between abnormal and normal nodes.
Graph Anomaly Detection Semi-supervised Anomaly Detection +1
no code implementations • 2 Apr 2023 • Bo-Kyeong Kim, Jaemin Kang, Daeun Seo, Hancheol Park, Shinkook Choi, Hyoung-Kyu Song, Hyungshin Kim, Sungsu Lim
Virtual humans have gained considerable attention in numerous industries, e. g., entertainment and e-commerce.
no code implementations • 29 Sep 2022 • Hwan Kim, Byung Suk Lee, Won-Yong Shin, Sungsu Lim
Graphs are used widely to model complex systems, and detecting anomalies in a graph is an important task in the analysis of complex systems.
1 code implementation • 19 Aug 2021 • Changwon Seo, Kyeong-Joong Jeong, Sungsu Lim, Won-Yong Shin
In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy.
no code implementations • 17 Jul 2021 • Alan Chan, Hugo Silva, Sungsu Lim, Tadashi Kozuno, A. Rupam Mahmood, Martha White
Approximate Policy Iteration (API) algorithms alternate between (approximate) policy evaluation and (approximate) greedification.
no code implementations • 6 Dec 2020 • Jin-woo Lee, Jaehoon Oh, Sungsu Lim, Se-Young Yun, Jae-Gil Lee
Federated learning has emerged as a new paradigm of collaborative machine learning; however, many prior studies have used global aggregation along a star topology without much consideration of the communication scalability or the diurnal property relied on clients' local time variety.
2 code implementations • 1 Jun 2020 • Kyuhan Lee, Hyeonsoo Jo, Jihoon Ko, Sungsu Lim, Kijung Shin
SSumM not only merges nodes together but also sparsifies the summary graph, and the two strategies are carefully balanced based on the minimum description length principle.
Databases Social and Information Networks H.2.8
no code implementations • 11 May 2020 • Yash Satsangi, Sungsu Lim, Shimon Whiteson, Frans Oliehoek, Martha White
Information gathering in a partially observable environment can be formulated as a reinforcement learning (RL), problem where the reward depends on the agent's uncertainty.
1 code implementation • 22 Oct 2018 • Samuel Neumann, Sungsu Lim, Ajin Joseph, Yangchen Pan, Adam White, Martha White
We first provide a policy improvement result in an idealized setting, and then prove that our conditional CEM (CCEM) strategy tracks a CEM update per state, even with changing action-values.