SCFormer, a channel-wise Transformer with triangular or convolutional temporal constraints and a HiPPO cumulative history state, improves forecasting on several benchmarks but not on Traffic.
IEEE Communications Magazine 57(6), 114–119 (2019)
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
-
SCFormer: Structured Channel-wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting
SCFormer, a channel-wise Transformer with triangular or convolutional temporal constraints and a HiPPO cumulative history state, improves forecasting on several benchmarks but not on Traffic.