Skip to content
GCC AI Research

Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancing

arXiv · · Significant research

Research Time-Series Representation Learning Classification Anomaly Detection

Summary

The paper introduces TimeHUT, a new method for learning time-series representations using hierarchical uniformity-tolerance balancing of contrastive representations. TimeHUT employs a hierarchical setup to learn both instance-wise and temporal information, along with a temperature scheduler to balance uniformity and tolerance. The method was evaluated on UCR, UAE, Yahoo, and KPI datasets, demonstrating superior performance in classification tasks and competitive results in anomaly detection.

Keywords

Time-Series · Representation Learning · Contrastive Learning · Uniformity · Tolerance

Read original article →

Get the weekly digest

Top AI stories from the GCC region, every week.

Related

Distribution-Free Conformal Joint Prediction Regions for Neural Marked Temporal Point Processes

MBZUAI ·

A presentation will demonstrate the construction of well-calibrated, distribution-free neural Temporal Point Process (TPP) models from multiple event sequences using conformal prediction. The method builds a distribution-free joint prediction region for event arrival time and type with a finite-sample coverage guarantee. The refined method is based on the highest density regions, derived from the joint predictive density of event arrival time and type to address the challenge of creating a joint prediction region for a bivariate response that includes both continuous and discrete data types. Why it matters: This research from a KAUST postdoc improves uncertainty quantification in neural TPPs, which are crucial for modeling continuous-time event sequences, with applications in various fields, by providing more reliable prediction regions.