no code implementations • 20 Feb 2023 • Yoonhyuk Choi, Jiho Choi, Taewook Ko, Chong-Kwon Kim
Graph Neural Networks (GNNs) have proven to be powerful in many graph-based applications.
no code implementations • 21 Jan 2023 • Yoonhyuk Choi, Jiho Choi, Taewook Ko, Chong-Kwon Kim
This paper provides a new understanding of signed propagation for multi-class scenarios and points out two drawbacks in terms of message-passing and parameter update: (1) Message-passing: if two nodes belong to different classes but have a high similarity, signed propagation can decrease the separability.
no code implementations • 28 Nov 2022 • Yoonhyuk Choi, Jiho Choi, Taewook Ko, Chong-Kwon Kim
To the best of our knowledge, this is the first attempt to mitigate the overfitting caused by the initial features.
no code implementations • 16 Nov 2022 • Jiho Choi, Junghoon Park, Woocheol Kim, Jin-Hyeok Park, Yumin Suh, Minchang Sung
The recent advent of play-to-earn (P2E) systems in massively multiplayer online role-playing games (MMORPGs) has made in-game goods interchangeable with real-world values more than ever before.
no code implementations • 25 Oct 2021 • Yoonhyuk Choi, Jiho Choi, Taewook Ko, Hyungho Byun, Chong-Kwon Kim
A cross-domain recommendation has shown promising results in solving data-sparsity and cold-start problems.