GSNF combines graph structures with one-step neural flows and auxiliary self-supervision to improve interaction modeling and classification of irregular multivariate time series.
We used the processed data provided by Raindrop (Zhang et al., 2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification
GSNF combines graph structures with one-step neural flows and auxiliary self-supervision to improve interaction modeling and classification of irregular multivariate time series.