← Search

Chihiro Ono

2 accepted papers

2023

Parameter-Level Soft-Masking for Continual Learning

ICML 2023poster

Existing research on task incremental learning in continual learning has primarily focused on preventing catastrophic forgetting (CF). Although several techniques have achieved learning with no CF, they attain it by letting each task monopolize a sub-network in a shared network, which seriously limi…

2022

Physics-Informed Long-Sequence Forecasting From Multi-Resolution Spatiotemporal Data

IJCAI 2022poster

Spatiotemporal data aggregated over regions or time windows at various resolutions demonstrate heterogeneous patterns and dynamics in each resolution. Meanwhile, the multi-resolution characteristic provides rich contextual information, which is critical for effective long-sequence forecasting. The i…