arXiv Machine Learning
Jun 19
Reversible Residual Normalization Alleviates Spatio-Temporal Distribution Shift
arXiv:2604. 15838v2 Announce Type: replace Abstract: Distribution shift severely degrades the performance of deep forecasting models.
Synthetic Time Series Generation via Complex Networks
arXiv:2601. 22879v2 Announce Type: replace Abstract: Time series data are essential for a wide range of applications, yet access to high-quality datasets is often constrained by privacy concerns, acquisition costs, and labelling challenges.
Related stories
arXiv Machine Learning
Jun 11
Efficient Time Series Clustering from Multiscale Reservoir Dynamics with Granular-Ball Anchoring Graph Optimization
arXiv:2606. 12077v1 Announce Type: new Abstract: Time-series clustering remains challenging due to the inherent trade-off between clustering effectiveness and computational efficiency.
arXiv AI
Jun 3
QuITE: Query-Based Irregular Time Series Embedding
arXiv:2605. 28166v3 Announce Type: replace-cross Abstract: Irregular Multivariate Time Series (IMTS) are common in practice, yet their irregular sampling complicates effective modeling.
arXiv Machine Learning
Aug 24
A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Baselines
arXiv:2608.20980v1 Announce Type: new Abstract: Graph neural networks (GNNs) are routinely employed for short-range forecasting on multivariate time series with a spatial graph structure. Despite the...
arXiv AI
Jul 7
Signal or Noise? Understanding Generative Models for Real-World Sensor Time Series
arXiv:2607. 04245v1 Announce Type: cross Abstract: Generative models have changed how machine learning represents complex data distributions, especially in language and vision, yet many real-world systems are observed instead as continuous, high-dimensional, and noisy sensor time series.
arXiv AI
Sep 18
QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization
QUALS is a large‑scale time‑series corpus equilibrium framework designed to improve data efficiency for zero‑shot forecasting. It uses pattern quantization to decode heterogeneous patterns from mixed corpora and a learnability synchronization mechanism to calibrate sampling weights, bridging the optimization gap between simple and complex motifs. Benchmarks show that pre‑training on QUALS yields superior zero‑shot performance even with reduced training budgets.
arXiv Machine Learning
Jun 18
TimeLAVA: Learning-Agnostic Data Valuation for Time Series
arXiv:2606. 18729v1 Announce Type: cross Abstract: Data valuation quantifies the intrinsic quality of individual samples to enable principled data curation, quality control, and robust learning.
arXiv Machine Learning
Aug 10
When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series
arXiv:2608. 07333v1 Announce Type: new Abstract: Modeling multivariate time series by representing them as graphs, where individual series act as nodes and pairwise temporal corre- lations serve as edges, has gained significant traction.
Hugging Face Trending Papers
Aug 7
When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series
Modeling multivariate time series by representing them as graphs, where individual series act as nodes and pairwise temporal corre- lations serve as edges, has gained significant traction. Recent advances in Graph Neural Networks (GNNs) have demonstrated strong perfor- mance by assuming a static graph topology and aggregating information from neighboring series.
arXiv AI
3d ago
WinoTS: Wavelet-based Self-Distillation for Time Series Models
WinoTS introduces a wavelet‑based self‑distillation framework for time‑series models that uses time‑frequency augmentations to create multi‑scale structural views, avoiding distortion of signal dynamics. The method outperforms state‑of‑the‑art baselines in long‑term forecasting, cross‑domain zero‑shot transfer, and unsupervised anomaly detection, and linear probing on frozen representations often beats fully supervised training from scratch. Ablation studies show WinoTS is architecture‑agnostic and demonstrates that time‑frequency transformations offer a principled alternative to vision‑style spatial augmentations.
arXiv Machine Learning
Jul 7
Deep Learning Network-Temporal Models For Traffic Prediction
arXiv:2603. 11475v2 Announce Type: replace Abstract: Accurate prediction of multivariate time series is essential for emerging network intelligent control, observability, and management functions.
arXiv Machine Learning
Jun 16
Towards a Unified Generative Model for Scarce Time Series with Domain Experts
arXiv:2606. 15172v1 Announce Type: new Abstract: Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios.