REVIEW 4 cited by
A Temporal Kolmogorov-Arnold Transformer for 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
read the original abstract
Capturing complex temporal patterns and relationships within multivariate data streams is a difficult task. We propose the Temporal Kolmogorov-Arnold Transformer (TKAT), a novel attention-based architecture designed to address this task using Temporal Kolmogorov-Arnold Networks (TKANs). Inspired by the Temporal Fusion Transformer (TFT), TKAT emerges as a powerful encoder-decoder model tailored to handle tasks in which the observed part of the features is more important than the a priori known part. This new architecture combined the theoretical foundation of the Kolmogorov-Arnold representation with the power of transformers. TKAT aims to simplify the complex dependencies inherent in time series, making them more "interpretable". The use of transformer architecture in this framework allows us to capture long-range dependencies through self-attention mechanisms.
Forward citations
Cited by 4 Pith papers
-
LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration
A learned, stage-segmented KAN predictor for feature caching accelerates diffusion transformers by 5-6.25x while preserving more image/video fidelity than prior training-free forecasters.
-
Toroidal area-preserving parameterizations of genus-one closed surfaces
Four Riemannian optimization algorithms (projected/Riemannian gradient and conjugate gradient) are proposed to compute toroidal area-preserving parameterizations by minimizing stretch energy on a power manifold of ring tori.
-
SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions
SechKAN combines sech basis functions with a 1D linear projection to build a KAN-style model whose parameter count matches MLPs and which is competitive or better than several KAN variants on tested benchmarks.
-
SigGate: Enhancing Recurrent Neural Networks with Signature-Based Gating Mechanisms
A signature-based forget/reset gate that ignores the hidden state yields small and task-dependent R2 changes on two crypto forecasting tasks, not the consistent improvement claimed.
Discussion (0). Continue with ORCID to comment.