JeremyChou28 / Awesome-irregular-incomplete-time-series

Awesome: Irregular Time Series, Incomplete Time Series • Awesome: Irregular Time Series, Incomplete Time Series• What are Irregular Time Series and Incomplete Time Series?• Related Surveys \& Benchmark• Paper List• Year 2026• Year 2025• Year 2024• Year 2023• Year 2022• Year 2021• Year 2020• Year 2019• Others What are Irregular Time Series and Incomplete Time Series? An irregular time series can be represented as |n=1,\cdots,N},>) where ]_{i=1}^{L_n}},x_i\in\mathbb{R}^d>), is the number of samples, is the number of variables, is the length of observations. For each variable, the time point list of observations is irregular. An incomplete time series can be represented as |_{t=1}^T},>) where \in\mathbb{R}^C>) denotes the incomplete values of $C$ features at the timestamp $t$, \in{0,1}^C>) is the mask matrix. $m_t^i=1$ indicates $x_t^i$ is observed, and $m_t^i=0$ indicates $x_t^i$ is missing. **Irregular time series** vs **incomplete time series**: Irregular time series usually refers to the irregular intervals between observation time points, while incomplete time series usually refers to the presence of missing values in the observed regular time series.• : irregular time series: observation/sampling timestamps are irregular.• : incomplete time series: regular time series with missing values. **Task**: , , , , , , , Related Surveys & Benchmark | Year | Venue | Title | Type | Link | | :--: | :--------------------------------------------: | :---------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------: | | 2026 | ICLR | PYRREGULAR: A Unified Framework for Irregular Time Series, with Classification Benchmarks | | [paper] [code] | | 2025 | Arxiv | Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series | | [paper] [code] | | 2025 | IJCAI | Deep Learning for Multivariate Time Series Imputation: A Survey | | [paper] [code] | | 2024 | Arxiv | An Experimental Evaluation of Imputation Models for Spatial-Temporal Traffic Data | | [paper] [code] | | 2024 | Arxiv | TSI-Bench: Benchmarking Time Series Imputation | | [paper] [code] | | 2024 | Arxiv | ITI-IQA: a Toolbox for Heterogeneous Univariate and Multivariate Missing Data Imputation Quality Assessment | | [paper] | | 2024 | Arxiv | Benchmarking with MIMIC-IV, an irregular, spare clinical time series dataset | | [paper] | | 2024 | Arxiv | How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation | | [paper] | | 2023 | Arxiv | Deep Imputation of Missing Values in Time Series Health Data: A Review with Benchmarking | | [paper] | | 2023 | TKDE | An Experimental Survey of Missing Data Imputation Algorithms | | [paper] | | 2023 | IEEE Access | Generative Adversarial Networks Assist Missing Data Imputation: A Comprehensive Survey and Evaluation | | [paper] | | 2022 | ACM Computing Surveys | A Comprehensive Survey on Imputation of Missing Data in Internet of Things | | [paper] | | 2022 | Research in Social and Administrative Pharmacy | Missing data in surveys: Key concepts, approaches, and applications | | [paper] | | 2020 | VLDB | Mind the gap: an experimental evaluation of imputation of missing values techniques in time series | | [paper] [code] | | 2020 | NeurIPS Workshop | A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series | | [paper] | | 2020 | Arxiv | Time series data imputation: A survey on deep learning approaches | | [paper] | Paper List Year 2026 | Venue | Title | Type | Task | Link | | :---: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | | ICLR | ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting | | | [paper] | | ICLR | DeNOTS: Stable Deep Neural ODEs for Time Series | | | [paper] | | ICLR | GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care | | | [paper] [code] | | ICLR | Reliable Probabilistic Forecasting of Irregular Time Series through Marginalization-Consistent Flows | | | [paper] [code] | | ICLR | Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting | | | [paper] [code] | | ICLR |Can we generate portable representations for clinical time series data using LLMs? | | | [paper] [code] | | ICLR | T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation | | | [paper] [code] | | ICLR | Time-Gated Multi-Scale Flow Matching for Time-Series Imputation | | | [paper] | | ICLR | Time-Gated Multi-Scale Flow Matching for Time-Series Imputation | | | [paper] | | AAAI | Beyond Missing Data Imputation: Information-Theoretic Coupling of Missingness and Class Imbalance for Optimal Irregular Time Series Classification | | | [paper] | | AAAI | Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputation | | | [paper] | | AAAI | Generalising Traffic Forecasting to Regions Without Traffic Observations | | | [paper] | | AAAI | WaveDiST: A Wavelet Diffusion Transformer for Spatio-Temporal Estimation on Unobserved Locations | | | [paper] [code] | | AAAI | Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learning | | | [paper] | | AAAI | Revitalizing Canonical Pre-Alignment for Irregular Multivariate Time Series Forecasting| | | [paper] [code] | | AAAI | Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline | | | [paper] | | AAAI | FlowPath: Learning Data-Driven Manifolds with Invertibl…