Patch-wise Structural Loss for Time Series Forecasting
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:F6LJLNEWrecord.jsonopen to challenge →
read the original abstract
Time-series forecasting has gained significant attention in machine learning due to its crucial role in various domains. However, most existing forecasting models rely heavily on point-wise loss functions like Mean Square Error, which treat each time step independently and neglect the structural dependencies inherent in time series data, making it challenging to capture complex temporal patterns accurately. To address these challenges, we propose a novel Patch-wise Structural (PS) loss, designed to enhance structural alignment by comparing time series at the patch level. Through leveraging local statistical properties, such as correlation, variance, and mean, PS loss captures nuanced structural discrepancies overlooked by traditional point-wise losses. Furthermore, it integrates seamlessly with point-wise loss, simultaneously addressing local structural inconsistencies and individual time-step errors. PS loss establishes a novel benchmark for accurately modeling complex time series data and provides a new perspective on time series loss function design. Extensive experiments demonstrate that PS loss significantly improves the performance of state-of-the-art models across diverse real-world datasets.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
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.
-
TopoCast: A Topological Fidelity Framework for Evaluating Transformer-Based Time Series Forecasting
A topological evaluation framework for transformer time series forecasts that derives fidelity scores from persistence diagrams of delay embeddings, including a phase-aware localized metric.
-
An Efficient and Effective Architecture for Large-Scale Traffic Prediction via Geometry-Adaptive Square Partitioning
SqLinear uses geometry-adaptive square partitioning with theoretical guarantees plus hierarchical linear interactions to cut MAE 2.3-5.8% and training time 13-31% on large traffic datasets versus 10 baselines.
-
STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergy
STaT is a Symbolic-Temporal-Textual Alignment model that integrates three modalities to reduce shape distortion in non-stationary time series forecasting, reporting up to 8.9% gains in magnitude metrics and 8.5% less ...
-
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 t...
-
VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting
VLBM learns a shared latent basis for stable ID dynamics and orthogonal OOD residuals via variational alignment of future-aware posterior with future-blind prior, reporting 15.08% MAE and 7.74% MSE gains on 12 OOD benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.