Publications

HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction

• Under review at Experts systems with applications
• Raehyun Kim, Chan Ho So, Minbyul Jeong, Sanghoon Lee, Jinkyu Kim, Jaewoo Kang
• Hierarchical graph attention network to incorporate relationship between companies to predict stock price movement.

[Paper] [Code]

Global Stock Market Prediction Based on Stock Chart Images Using Deep Q-Network

• IEEE Access
• Jinho Lee, Raehyun Kim, Yookyung Koh, and Jaewoo Kang
• Train DQN agent in US market and evaluate it on global market (31 countries).

[Paper]

Graph Transformer Networks

• NeurIPS 2019
• Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim
• Graph Transformer Networks (GTNs) that are capable identifying useful connections between unconnected nodes on the original graph

[Paper] [Code]

SAIN: Self-Attentive Integration Network for Recommendation

• SIGIR 2019
• Seoungjun Yun* , Raehyun Kim* , Miyoung Ko, Jaewoo Kang
• Self-Attentive Integration Network (SAIN) which is a model that effectively combines user-item feedback information and auxiliary information.

[Paper] [Code]

Predicting Multiple Demographic Attributes with Task Specific Embedding Transformation and Attention Network

• SDM 2019
• Raehyun Kim∗ Hyunjae Kim∗ Janghyuk Lee, Jaewoo Kang
• Embedding Transformation Network with Attention, multi-task learning approach for demographic prediction.

[Paper] [Code]