Research map / Time series / Foundation models for time series
Adaptive Time Encoding for Irregular Multivariate Time-Series Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an adaptive time encoding for irregularly sampled multivariate time-series classification to handle misaligned observations and varying observation counts across variables.
Problem
Irregularly sampled multivariate time series cause misaligned observations across variables and varying observation counts, which degrades deep learning classification performance.
Approach
An adaptive time encoding that embeds irregular timestamps so that observations are represented in a common, learnable time representation, mitigating cross-variable misalignment and varying counts.
Closest papers by meaning
- TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (ICML 2024 · similarity 0.86)
- TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis (AAAI 2025 · similarity 0.86)
- T-Rep: Representation Learning for Time Series using Time-Embeddings (ICLR 2024 · similarity 0.85)
- Learning under Temporal Label Noise (ICLR 2025 · similarity 0.84)
- Time Series Representations with Hard-Coded Invariances (ICML 2025 · similarity 0.84)
- Hi-Patch: Hierarchical Patch GNN for Irregular Multivariate Time Series (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.