MillGNN learns delayed (lead-lag) influences between time series and between groups of series at multiple grouping scales, reporting state-of-the-art forecast errors on 11 benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting
MillGNN learns delayed (lead-lag) influences between time series and between groups of series at multiple grouping scales, reporting state-of-the-art forecast errors on 11 benchmarks.