A low-rank fast graph computation plus a dynamic spatio-temporal convolution kernel gives FasterSTS competitive traffic forecasts at a fraction of the compute, though not the universal state-of-the-art the paper claims.
Long short-term memory,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FasterSTS: A Faster Spatio-Temporal Synchronous Graph Convolutional Networks for Traffic flow Forecasting
A low-rank fast graph computation plus a dynamic spatio-temporal convolution kernel gives FasterSTS competitive traffic forecasts at a fraction of the compute, though not the universal state-of-the-art the paper claims.