DRAGON maps discretized multivariate time series onto a de Bruijn graph with cross-dimension connections and uses graph attention to add global pattern memory to a CNN-based forecaster, improving short-context forecasts on ETT benchmarks.
5 Submission and Formatting Instructions for ICML 2025 A
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
-
Multivariate de Bruijn Graphs: A Symbolic Graph Framework for Time Series Forecasting
DRAGON maps discretized multivariate time series onto a de Bruijn graph with cross-dimension connections and uses graph attention to add global pattern memory to a CNN-based forecaster, improving short-context forecasts on ETT benchmarks.