SeesawNet dynamically balances common and instance-specific dependencies via ASNA in temporal and channel dimensions, outperforming prior methods on non-stationary forecasting benchmarks.
arXiv preprint arXiv:2410.04442 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
LatentTSF improves time series forecasting accuracy and representation quality by shifting prediction from observation space to a learned latent state space via autoencoding.
SARAF is a new retrieval-augmented framework for time series forecasting that uses temporal similarity followed by stationarity-modulated diversity selection and aggregation to improve accuracy under non-stationarity.
MS-FLOW uses a capacity-limited sparse routing mechanism to model only critical inter-variable dependencies in time series data, achieving state-of-the-art accuracy on 12 benchmarks with fewer but more reliable connections.
ReNF proposes Boosted Direct Output (BDO) and parameter smoothing so a basic temporal MLP outperforms complex state-of-the-art models on long-term time series forecasting benchmarks by implicitly combining forecasts to reduce uncertainty.
A two-stage residual-aware framework adds a meta-corrector after a base transformer to model structured errors and reports state-of-the-art results on eight time-series benchmarks.
L-Drive adds a latent-context representation and gating mechanism to handle distribution shifts in multivariate time series forecasting beyond direct mapping approaches.
citing papers explorer
-
SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies
SeesawNet dynamically balances common and instance-specific dependencies via ASNA in temporal and channel dimensions, outperforming prior methods on non-stationary forecasting benchmarks.
-
From Observations to States: Latent Time Series Forecasting
LatentTSF improves time series forecasting accuracy and representation quality by shifting prediction from observation space to a learned latent state space via autoencoding.
-
Stationarity-Aware Retrieval-Augmented Time Series Forecasting
SARAF is a new retrieval-augmented framework for time series forecasting that uses temporal similarity followed by stationarity-modulated diversity selection and aggregation to improve accuracy under non-stationarity.
-
What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
MS-FLOW uses a capacity-limited sparse routing mechanism to model only critical inter-variable dependencies in time series data, achieving state-of-the-art accuracy on 12 benchmarks with fewer but more reliable connections.
-
ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters
ReNF proposes Boosted Direct Output (BDO) and parameter smoothing so a basic temporal MLP outperforms complex state-of-the-art models on long-term time series forecasting benchmarks by implicitly combining forecasts to reduce uncertainty.
-
One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data
A two-stage residual-aware framework adds a meta-corrector after a base transformer to model structured errors and reports state-of-the-art results on eight time-series benchmarks.
-
L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting
L-Drive adds a latent-context representation and gating mechanism to handle distribution shifts in multivariate time series forecasting beyond direct mapping approaches.
- FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting