A graph-free MLP-Mixer with independent patch-wise MLP masked pretraining matches or beats complex spatiotemporal models on large-scale traffic forecasting at a fraction of the compute.
Deep learning for short-term traffic flow prediction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PreMixer: MLP-Based Pre-training Enhanced MLP-Mixers for Large-scale Traffic Forecasting
A graph-free MLP-Mixer with independent patch-wise MLP masked pretraining matches or beats complex spatiotemporal models on large-scale traffic forecasting at a fraction of the compute.