SeesawNet dynamically balances common and instance-specific dependencies via ASNA in temporal and channel dimensions, outperforming prior methods on non-stationary forecasting benchmarks.
Fits: Modeling time series with 10 k parameters
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
In this paper, we introduce FITS, a lightweight yet powerful model for time series analysis. Unlike existing models that directly process raw time-domain data, FITS operates on the principle that time series can be manipulated through interpolation in the complex frequency domain. By discarding high-frequency components with negligible impact on time series data, FITS achieves performance comparable to state-of-the-art models for time series forecasting and anomaly detection tasks, while having a remarkably compact size of only approximately $10k$ parameters. Such a lightweight model can be easily trained and deployed in edge devices, creating opportunities for various applications. The code is available in: \url{https://github.com/VEWOXIC/FITS}
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Super-Linear introduces a pretrained MoE architecture using frequency-specialized linear experts and spectral gating for efficient general time series forecasting.
This survey and benchmark of deep time series models using the released TSLib library finds that models with specific structures perform well only on distinct analysis tasks.
TimeSynth supplies a generator and fidelity diagnostics that reveal pointwise metrics miss up to 53° phase errors across 11 architectures and show architecture determines temporal fidelity in health signals.
GenHAR generalizes cross-domain human activity recognition by 9.97% accuracy and 6.4x lower FLOPs via tokenized sensor data, frequency channel correlations, selective masking, and efficient attention, with deployment detecting 2.15 billion activities.
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.
Knowledge distillation most benefits intermediate-complexity students for time series classification, cutting parameters sharply while matching teacher accuracy across FCN, Inception, and ConvTran on UCR.
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.
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.
-
Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
Super-Linear introduces a pretrained MoE architecture using frequency-specialized linear experts and spectral gating for efficient general time series forecasting.
-
Deep Time Series Models: A Comprehensive Survey and Benchmark
This survey and benchmark of deep time series models using the released TSLib library finds that models with specific structures perform well only on distinct analysis tasks.
-
Timesynth: A Temporal Fidelity Framework for Health Signal Digital Twins
TimeSynth supplies a generator and fidelity diagnostics that reveal pointwise metrics miss up to 53° phase errors across 11 architectures and show architecture determines temporal fidelity in health signals.
-
GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery
GenHAR generalizes cross-domain human activity recognition by 9.97% accuracy and 6.4x lower FLOPs via tokenized sensor data, frequency channel correlations, selective masking, and efficient attention, with deployment detecting 2.15 billion activities.
-
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.
-
Enhancing deep learning models for time series classification via knowledge distillation
Knowledge distillation most benefits intermediate-complexity students for time series classification, cutting parameters sharply while matching teacher accuracy across FCN, Inception, and ConvTran on UCR.
-
Time Series Forecasting Through the Lens of Dynamics
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.