REVIEW 5 cited by
TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation
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
Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively capture both long-term dynamic evolution and subtle local patterns in a unified manner. In this work, we propose \textbf{TimeDART}, a novel self-supervised time series pre-training framework that unifies two powerful generative paradigms to learn more transferable representations. Specifically, we first employ a causal Transformer encoder, accompanied by a patch-based embedding strategy, to model the evolving trends from left to right. Building on this global modeling, we further introduce a denoising diffusion process to capture fine-grained local patterns through forward diffusion and reverse denoising. Finally, we optimize the model in an autoregressive manner. As a result, TimeDART effectively accounts for both global and local sequence features in a coherent way. We conduct extensive experiments on public datasets for time series forecasting and classification. The experimental results demonstrate that TimeDART consistently outperforms previous compared methods, validating the effectiveness of our approach. Our code is available at https://github.com/Melmaphother/TimeDART.
Forward citations
Cited by 5 Pith papers
-
Domain-Informed Multi-View Self-Distillation for Astronomical Light-Curve Representation Learning with JEPA
A JEPA-based model with domain-informed multi-view self-distillation learns light-curve representations that outperform hand-crafted features on 15 of 16 StarEmbed metrics and adapts competitively to other irregular t...
-
Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach
A bi-level federated learning framework trains time series foundation models on heterogeneous data by enforcing domain-invariant representations locally and improving cross-domain collaboration through aware aggregation.
-
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.
-
Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models
Self-supervised pre-training delivers large gains up to 375% on time series anomaly detection and classification but only marginal benefits for forecasting, driven by a precision-invariance trade-off in the learned re...
-
CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting
CoGenCast couples a Qwen-based encoder-decoder with flow matching and reports strong MSE/MAE on ten time-series benchmarks.
Discussion (0). Sign in to comment.