PHI Lab Team
Maya Okawa
Scientist
Maya Okawa earned her B.S. in Physics in 2012, an M.S. in physics two years later, and a Ph.D. in computer science in 2022 from Kyoto University. Her research interest lies in developing machine learning methods for modeling and predicting time-series data. Her current work focuses on the integration of machine learning methods with the neurological and physiological sciences.
Awards
xxxFellow (2021)
xxxxInvestigator (2019)
xxxMurray Hopper Award (2015)
Presixxxdential Early Career Award for Scientists and Engineers (PECASE) (2011)
xxxFellowship (2011)
xxxxFaculty Fellowship (2011)
xxxxFellowship (2010)
Publications
- Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
By Maya Okawa, Ekdeep S Lubana, Robert Dick & Hidenori Tanaka
Advances in Neural Information Processing Systems (NeurIPS) 2023
- Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
- Predicting Opinion Dynamics via Sociologically-Informed Neural Networks
By Maya Okawa & Tomoharu Iwata
Proceedings of the 28th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2022
- Aggregated Multi-output Gaussian Processes with Knowledge Transfer Across Domains
By Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata, Takeshi Kurashima, Maya Okawa, Yasunori Akagi & Hiroyuki Toda
arXiv preprint arXiv 2022
- Spatio-temporal Event Prediction via Deep Point Processes
By Maya Okawa
Kyoto University 2022
- Context-aware Spatio-temporal Event Prediction via Convolutional Hawkes Processes
By Maya Okawa
Machine Learning Journal (ECML-PKDD Journal Track) 2022
- Predicting Opinion Dynamics via Sociologically-Informed Neural Networks
- Deep Mixture Point Processes
By Maya Okawa, Tomoharu Iwata, Takeshi Kurashima, Yusuke Tanaka, Hiroyuki Toda, Naonori Ueda & Hisashi Kashima
Transactions of the Japanese Society for Artificial Intelligence 2021
- Dynamic Hawkes Processes for Discovering Time-evolving Communities’ States behind Diffusion Processes
By Maya Okawa, Tomoharu Iwata, Yusuke Tanaka, Hiroyuki Toda, Takeshi Kurashima & Hisashi Kashima
Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2021
- Deep Mixture Point Processes
- Predicting Traffic Accidents with Event Recorder Data
By Yoshiaki Takimoto, Yusuke Tanaka, Takeshi Kurashima, Shuhei Yamamoto, Maya Okawa & Hiroyuki Toda
Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Prediction of Human Mobility 2019
- Marked Temporal Point Processes for Trip Demand Prediction in Bike Sharing Systems
By Maya Okawa, Yusuke Tanaka, Takeshi Kurashima, Hiroyuki Toda & Tomohiro Yamada
IEICE TRANSACTIONS on Information and Systems 2019
- Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Information
By Maya Okawa, Tomoharu Iwata, Takeshi Kurashima, Yusuke Tanaka, Hiroyuki Toda & Naonori Ueda
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2019
- Refining Coarse-grained Spatial Data Using Auxiliary Spatial Data Sets with Various Granularities
By Yusuke Tanaka, Tomoharu Iwata, Toshiyuki Tanaka, Takeshi Kurashima, Maya Okawa & Hiroyuki Toda
Proceedings of the AAAI Conference on Artificial Intelligence 2019
- Spatially Aggregated Gaussian Processes with Multivariate Areal Outputs
By Yusuke Tanaka, Toshiyuki Tanaka, Tomoharu Iwata, Takeshi Kurashima, Maya Okawa, Yasunori Akagi & Hiroyuki Toda
Advances in Neural Information Processing Systems 2019
- Online Traffic Flow Prediction Using Convolved Bilinear Poisson Regression
By Maya Okawa, Hideaki Kim & Hiroyuki Toda
- Visualization of Crowd Movements at Large-scale Events
By Hiroyuki Toda Maya Okawa, Aki Hayashi, Kim Hideaki & Takuya Nishimura