REVIEW 4 cited by
PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
read the original abstract
Although the Transformer has been the dominant architecture for time series forecasting tasks in recent years, a fundamental challenge remains: the permutation-invariant self-attention mechanism within Transformers leads to a loss of temporal information. To tackle these challenges, we propose PatchMixer, a novel CNN-based model. It introduces a permutation-variant convolutional structure to preserve temporal information. Diverging from conventional CNNs in this field, which often employ multiple scales or numerous branches, our method relies exclusively on depthwise separable convolutions. This allows us to extract both local features and global correlations using a single-scale architecture. Furthermore, we employ dual forecasting heads encompassing linear and nonlinear components to better model future curve trends and details. Our experimental results on seven time-series forecasting benchmarks indicate that compared with the state-of-the-art method and the best-performing CNN, PatchMixer yields $3.9\%$ and $21.2\%$ relative improvements, respectively, while being 2-3x faster than the most advanced method.
Forward citations
Cited by 4 Pith papers
-
QuITE: Query-Based Irregular Time Series Embedding
QuITE is a query-token embedding layer that aggregates irregular observations via self-attention to produce backbone-compatible latents without generating artificial values.
-
PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting
PMDformer uses patch-mean decoupling, trend restoration attention, and proximal variable attention to improve accuracy and stability in long-term time series forecasting benchmarks.
-
SinFormer: A Tailored Transformer for Robust Radio Frequency Fingerprint Identification
SinFormer is a tailored transformer that applies multi-scale self-attention and staged training to improve accuracy and robustness in radio frequency fingerprint identification on real-world data.
-
ITS-Mina: A Harris Hawks Optimization-Based All-MLP Framework with Iterative Refinement and External Attention for Multivariate Time Series Forecasting
ITS-Mina introduces an all-MLP model with iterative refinement, external attention via learnable memory units, and HHO-tuned dropout that reports state-of-the-art or competitive results on six multivariate time series...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.