DynLMC creates synthetic time series data with dynamic inter-channel correlations that improve zero-shot forecasting in foundation models across multiple benchmarks.
Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
Extending the forecasting time is a critical demand for real applications, such as extreme weather early warning and long-term energy consumption planning. This paper studies the long-term forecasting problem of time series. Prior Transformer-based models adopt various self-attention mechanisms to discover the long-range dependencies. However, intricate temporal patterns of the long-term future prohibit the model from finding reliable dependencies. Also, Transformers have to adopt the sparse versions of point-wise self-attentions for long series efficiency, resulting in the information utilization bottleneck. Going beyond Transformers, we design Autoformer as a novel decomposition architecture with an Auto-Correlation mechanism. We break with the pre-processing convention of series decomposition and renovate it as a basic inner block of deep models. This design empowers Autoformer with progressive decomposition capacities for complex time series. Further, inspired by the stochastic process theory, we design the Auto-Correlation mechanism based on the series periodicity, which conducts the dependencies discovery and representation aggregation at the sub-series level. Auto-Correlation outperforms self-attention in both efficiency and accuracy. In long-term forecasting, Autoformer yields state-of-the-art accuracy, with a 38% relative improvement on six benchmarks, covering five practical applications: energy, traffic, economics, weather and disease. Code is available at this repository: \url{https://github.com/thuml/Autoformer}.
representative citing papers
Neural CDEs serve as correctors that reduce error accumulation in multi-step forecasts from learned time-series models across synthetic, physics, and real-world data.
TelecomTS is a de-anonymized 5G observability benchmark with scale information, anomalies, and multi-modal QA tasks, on which current foundation models perform poorly.
RhyMix reaches state-of-the-art long-term multivariate forecasting on 10 of 12 public benchmarks with a ~40K-parameter dual-path adaptive architecture of linear complexity.
Characteristic roots govern dynamics in linear forecasting models but noise induces spurious roots; rank reduction and Root Purge regularization mitigate this for more robust predictions.
MR-CDM uses hierarchical multi-resolution decomposition and multi-scale conditional diffusion to generate forecasts that reduce MAE and RMSE by 6-10% versus baselines like CSDI and Informer on four datasets.
MSTN claims SOTA across time-series tasks with early temporal pooling, but internal inconsistencies in parameter counts, benchmark tables, and implausible error reductions undermine the central claims.
Signed Dual Attention is a parameter-free attention module that models signed dependencies in time series via dual message passing to achieve two-head expressiveness in one block.
citing papers explorer
-
Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series
DynLMC creates synthetic time series data with dynamic inter-channel correlations that improve zero-shot forecasting in foundation models across multiple benchmarks.
-
Neural CDEs as Correctors for Learned Time Series Models
Neural CDEs serve as correctors that reduce error accumulation in multi-step forecasts from learned time-series models across synthetic, physics, and real-world data.
-
TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis
TelecomTS is a de-anonymized 5G observability benchmark with scale information, anomalies, and multi-modal QA tasks, on which current foundation models perform poorly.
-
RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting
RhyMix reaches state-of-the-art long-term multivariate forecasting on 10 of 12 public benchmarks with a ~40K-parameter dual-path adaptive architecture of linear complexity.
-
Characteristic Root Analysis and Regularization for Linear Time Series Forecasting
Characteristic roots govern dynamics in linear forecasting models but noise induces spurious roots; rank reduction and Root Purge regularization mitigate this for more robust predictions.
-
MR-ImagenTime: Multi-Resolution Time Series Generation through Dual Image Representations
MR-CDM uses hierarchical multi-resolution decomposition and multi-scale conditional diffusion to generate forecasts that reduce MAE and RMSE by 6-10% versus baselines like CSDI and Informer on four datasets.
-
MSTN: A Lightweight and Fast Model for General TimeSeries Analysis
MSTN claims SOTA across time-series tasks with early temporal pooling, but internal inconsistencies in parameter counts, benchmark tables, and implausible error reductions undermine the central claims.
-
Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting
Signed Dual Attention is a parameter-free attention module that models signed dependencies in time series via dual message passing to achieve two-head expressiveness in one block.