Skip to content

A professional list of Papers, Tutorials, and Surveys on AI for Time Series in top AI conferences and journals.

License

Notifications You must be signed in to change notification settings

DAMO-DI-ML/AI-for-Time-Series-Papers-Tutorials-Surveys

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 

Repository files navigation

AI for Time Series (AI4TS) Papers, Tutorials, and Surveys

Awesome PRs Welcome

A professionally curated list of papers (with available code), tutorials, and surveys on recent AI for Time Series Analysis (AI4TS), including Time Series, Spatio-Temporal Data, Event Data, Sequence Data, Temporal Point Processes, etc., at the Top AI Conferences and Journals, which is updated ASAP (the earliest time) once the accepted papers are announced in the corresponding top AI conferences/journals.

The top conferences including:

  • Machine Learning: NeurIPS, ICML, ICLR
  • Data Mining: KDD
  • Artificial Intelligence: AAAI, IJCAI
  • Data Management: SIGMOD, VLDB, ICDE
  • Misc (selected): WWW, AISTAT, CIKM, ICDM, WSDM, SIGIR, ICASSP, CVPR, ICCV, etc.

The top journals including (mainly for survey papers): CACM, PIEEE, TPAMI, TKDE, TNNLS, TITS, TIST, SPM, JMLR, JAIR, CSUR, DMKD, KAIS, IJF, arXiv(selected), etc.

This list is also simultaneously updated in the Repo AI4TS Paper.

Most Recent Update Note

  • [2022-06-02] Add papers accepted by ICML'22, ICLR'22, AAAI'22, IJCAI'22!

Table of Contents

AI4TS Tutorials and Surveys

AI4TS Tutorials

  • Robust Time Series Analysis and Applications: An Industrial Perspective, in KDD 2022. [Link]
  • Time Series in Healthcare: Challenges and Solutions, in AAAI 2022. [Link]
  • Robust Time Series Analysis: from Theory to Applications in the AI Era, in IJCAI 2022. [Link]
  • Time Series Anomaly Detection: Tools, Techniques and Tricks, in DASFAA 2022. [Link]
  • Modern Aspects of Big Time Series Forecasting, in IJCAI 2021. [Link]
  • Explainable AI for Societal Event Predictions: Foundations, Methods, and Applications, in AAAI 2021. [Link]
  • Physics-Guided AI for Large-Scale Spatiotemporal Data, in KDD 2021. [Link]
  • Building Forecasting Solutions Using Open-Source and Azure Machine Learning, in KDD 2020. [Link]
  • Interpreting and Explaining Deep Neural Networks: A Perspective on Time Series Data, KDD 2020. [Link]
  • Forecasting Big Time Series: Theory and Practice, KDD 2019. [Link]
  • Spatio-Temporal Event Forecasting and Precursor Identification, KDD 2019. [Link]
  • Modeling and Applications for Temporal Point Processes, KDD 2019. [Link] [Link2]

AI4TS Surveys

General Time Series Survey

  • Time series data augmentation for deep learning: a survey, in IJCAI 2021. [paper]
  • Neural temporal point processes: a review, in IJCAI 2021. [paper]
  • Causal inference for time series analysis: problems, methods and evaluation, in KAIS 2022. [paper]
  • Survey and Evaluation of Causal Discovery Methods for Time Series, in JAIR 2022. [paper]
  • Deep learning for spatio-temporal data mining: A survey, in TKDE 2020. [paper]
  • Generative Adversarial Networks for Spatio-temporal Data: A Survey, in TIST 2022. [paper]
  • Spatio-Temporal Data Mining: A Survey of Problems and Methods, in CSUR 2018. [paper]
  • A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series, in NeurIPS Workshop 2020. [paper]
  • A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data, in arXiv 2020. [paper]
  • Transformers in Time Series: A Survey, in arXiv 2022. [paper]

Time Series Forecasting Survey

  • Forecasting: theory and practice, in IJF 2022. [paper]
  • Time-series forecasting with deep learning: a survey, in Philosophical Transactions of the Royal Society A 2021. [paper]
  • Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions, in TITS 2022. [paper]
  • Event prediction in the big data era: A systematic survey, in CSUR 2022. [paper]
  • A brief history of forecasting competitions, in IJF 2020. [paper]
  • Neural forecasting: Introduction and literature overview, in arXiv 2020. [paper]

Time Series Anomaly Detection Survey

  • A review on outlier/anomaly detection in time series data, in CSUR 2021. [paper]
  • Anomaly detection for IoT time-series data: A survey, in IEEE Internet of Things Journal 2019. [paper]
  • A Survey of AIOps Methods for Failure Management, in TIST 2021. [paper]
  • Sequential (quickest) change detection: Classical results and new directions, in IEEE Journal on Selected Areas in Information Theory 2021. [paper]
  • Anomaly detection for discrete sequences: A survey, TKDE'12. [paper]

Time Series Classification Survey

  • Deep learning for time series classification: a review, in Data Mining and Knowledge Discovery 2019. [paper]
  • Approaches and Applications of Early Classification of Time Series: A Review, in IEEE Transactions on Artificial Intelligence 2020. [paper]

AI4TS Papers 2022

NeurIPS 2022

Not yet announced

ICML 2022

Time Series Forecasting

  • FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting [paper] [official code]
  • TACTiS: Transformer-Attentional Copulas for Time Series [paper]
  • Domain Adaptation for Time Series Forecasting via Attention Sharing [paper]
  • Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes
  • DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting

Time Series Anomaly Detection

  • Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection

Other Time Series Analysis

  • Adaptive Conformal Predictions for Time Series [paper] [official code]
  • Modeling Irregular Time Series with Continuous Recurrent Units [paper]
  • Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion [paper]
  • Reconstructing nonlinear dynamical systems from multi-modal time series [paper]
  • Utilizing Expert Features for Contrastive Learning of Time-Series Representations
  • Learning of Cluster-based Feature Importance for Electronic Health Record Time-series

ICLR 2022

Time Series Forecasting

  • Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting [paper] [official code]
  • DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting [paper] [official code]
  • CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting [paper] [official code]
  • Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift [paper] [official code]
  • TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting [paper] [official code]
  • Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [paper] [official code]
  • On the benefits of maximum likelihood estimation for Regression and Forecasting [paper]
  • Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting [paper] [official code]

Time Series Anomaly Detection

Time Series Classification

  • T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis [paper]
  • Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification [paper]

Other Time Series Analysis

  • Graph-Guided Network for Irregularly Sampled Multivariate Time Series [paper]
  • Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series [paper]
  • Transformer Embeddings of Irregularly Spaced Events and Their Participants [paper]
  • Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks [paper]
  • PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series [paper]
  • Huber Additive Models for Non-stationary Time Series Analysis [paper]
  • LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations [paper]
  • Imbedding Deep Neural Networks [paper]
  • Coherence-based Label Propagation over Time Series for Accelerated Active Learning [paper]
  • Long Expressive Memory for Sequence Modeling [paper]
  • Autoregressive Quantile Flows for Predictive Uncertainty Estimation [paper]
  • Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks [paper]
  • Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification [paper]
  • Explaining Point Processes by Learning Interpretable Temporal Logic Rules [paper]

KDD 2022

Not yet announced

AAAI 2022

Time Series Forecasting

  • CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting [paper]
  • Reinforcement Learning based Dynamic Model Combination for Time Series Forecasting [paper]
  • PrEF: Probabilistic Electricity Forecasting via Copula-Augmented State Space Model [paper]
  • LIMREF: Local Interpretable Model Agnostic Rule-Based Explanations for Forecasting, with an Application to Electricity Smart Meter Data [paper]
  • Learning and Dynamical Models for Sub-Seasonal Climate Forecasting: Comparison and Collaboration [paper] [official code]
  • CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting [paper]
  • Conditional Local Convolution for Spatio-Temporal Meteorological Forecasting [paper] [official code]
  • Graph Neural Controlled Differential Equations for Traffic Forecasting [paper] [official code]
  • STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction [paper] [official code]

Time Series Anomaly Detection

  • Towards a Rigorous Evaluation of Time-Series Anomaly Detection [paper]
  • AnomalyKiTS-Anomaly Detection Toolkit for Time Series [Demo paper]

Other Time Series Analysis

  • TS2Vec: Towards Universal Representation of Time Series [paper] [official code]
  • I-SEA: Importance Sampling and Expected Alignment-Based Deep Distance Metric Learning for Time Series Analysis and Embedding [paper]
  • Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis [paper]
  • Conditional Loss and Deep Euler Scheme for Time Series Generation [paper]
  • Clustering Interval-Censored Time-Series for Disease Phenotyping [paper]

IJCAI 2022

Time Series Forecasting

  • Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting [paper]
  • Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts [paper] [official code]
  • Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting
  • DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data [paper] [official code]
  • Memory Augmented State Space Model for Time Series Forecasting
  • Physics-Informed Long-Sequence Forecasting From Multi-Resolution Spatiotemporal Data
  • Long-term Spatio-Temporal Forecasting via Dynamic Multiple-Graph Attention [paper] [official code]
  • FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting

Time Series Anomaly Detection

  • Neural Contextual Anomaly Detection for Time Series [paper]
  • GRELEN: Multivariate Time Series Anomaly Detection from the Perspective of Graph Relational Learning

Time Series Classification

  • A Reinforcement Learning-Informed Pattern Mining Framework for Multivariate Time Series Classification [paper]
  • T-SMOTE: Temporal-oriented Synthetic Minority Oversampling Technique for Imbalanced Time Series Classification

SIGMOD VLDB ICDE 2022

Time Series Forecasting

  • METRO: A Generic Graph Neural Network Framework for Multivariate Time Series Forecasting, VLDB'22. [paper] [official code]
  • AutoCTS: Automated Correlated Time Series Forecasting, VLDB'22. [paper]
  • Towards Spatio-Temporal Aware Traffic Time Series Forecasting, ICDE'22. [paper] [official code]

Time Series Anomaly Detection

  • Sintel: A Machine Learning Framework to Extract Insights from Signals, SIGMOD'22. [paper] [official code]
  • TSB-UAD: An End-to-End Benchmark Suite for Univariate Time-Series Anomaly Detection, VLDB'22. [paper] [official code]
  • TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data, VLDB'22. [paper] [official code]
  • Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles, VLDB'22. [paper]
  • Robust and Explainable Autoencoders for Time Series Outlier Detection, ICDE'22. [paper]
  • Anomaly Detection in Time Series with Robust Variational Quasi-Recurrent Autoencoders, ICDE'22.

Time Series Classification

  • IPS: Instance Profile for Shapelet Discovery for Time Series Classification, ICDE'22. [paper]
  • Towards Backdoor Attack on Deep Learning based Time Series Classification, ICDE'22. [paper]

Other Time Series Analysis

  • OnlineSTL: Scaling Time Series Decomposition by 100x, VLDB'22. [paper]
  • Efficient temporal pattern mining in big time series using mutual information, VLDB'22. [paper]
  • Learning Evolvable Time-series Shapelets, ICDE'22.

Misc 2022

Time Series Forecasting

  • CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting, WWW'22. [paper] [official code]
  • Multi-Granularity Residual Learning with Confidence Estimation for Time Series Prediction, WWW'22. [paper]
  • RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph, WWW'22. [paper]
  • Robust Probabilistic Time Series Forecasting, AISTATS'22. [paper] [official code]
  • Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting, AISTATS'22. [paper]

Time Series Anomaly Detection

  • Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection, AISTATS'22. [paper] [official code]
  • A Semi-Supervised VAE Based Active Anomaly Detection Framework in Multivariate Time Series for Online Systems, WWW'22. [paper]

Other Time Series Analysis

  • Decoupling Local and Global Representations of Time Series, AISTATS'22. [paper] [official code]
  • LIMESegment: Meaningful, Realistic Time Series Explanations, AISTATS'22. [paper]
  • Using time-series privileged information for provably efficient learning of prediction models, AISTATS'22. [paper] [official code]
  • Amortised Likelihood-free Inference for Expensive Time-series Simulators with Signatured Ratio Estimation, AISTATS'22. [paper] [official code]
  • EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting, WWW'22. [paper]

AI4TS Papers 2021

NeurIPS 2021

Time Series Forecasting

  • Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting [paper] [official code]
  • MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data [paper]
  • Conformal Time-Series Forecasting [paper] [official code]
  • Probabilistic Forecasting: A Level-Set Approach [paper]
  • Topological Attention for Time Series Forecasting [paper]
  • When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [paper] [official code]
  • Monash Time Series Forecasting Archive [paper] [official code]

Time Series Anomaly Detection

  • Revisiting Time Series Outlier Detection: Definitions and Benchmarks [paper] [official code]
  • Online false discovery rate control for anomaly detection in time series [paper]
  • Detecting Anomalous Event Sequences with Temporal Point Processes [paper]

Other Time Series Analysis

ICML 2021

Time Series Forecasting

Time Series Anomaly Detection

Other Time Series Analysis

ICLR 2021

Other Time Series Analysis

KDD 2021

Time Series Forecasting

  • ST-Norm: Spatial and Temporal Normalization for Multi-variate Time Series Forecasting [paper] [official code]
  • Graph Deep Factors for Forecasting with Applications to Cloud Resource Allocation [paper]
  • Quantifying Uncertainty in Deep Spatiotemporal Forecasting [paper]
  • Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting [paper] [official code]
  • TrajNet: A Trajectory-Based Deep Learning Model for Traffic Prediction [paper]
  • Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting [paper]

Time Series Anomaly Detection

  • Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding [paper] [official code]
  • Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization [paper] [official code]
  • Time Series Anomaly Detection for Cyber-physical Systems via Neural System Identification and Bayesian Filtering [paper] [official code]
  • Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection [paper] [official code]

Other Time Series Analysis

  • Representation Learning of Multivariate Time Series using a Transformer Framework [paper] [official code]
  • Causal and Interpretable Rules for Time Series Analysis [paper]
  • MiniRocket: A Fast (Almost) Deterministic Transform for Time Series Classification [paper] [official code]
  • Statistical models coupling allows for complex localmultivariate time series analysis [paper]
  • Fast and Accurate Partial Fourier Transform for Time Series Data [paper] [official code]
  • Deep Learning Embeddings for Data Series Similarity Search [paper] [link]

AAAI 2021

Time Series Forecasting

  • Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting [paper] [official code]
  • Deep Switching Auto-Regressive Factorization: Application to Time Series Forecasting [paper] [official code]
  • Dynamic Gaussian Mixture Based Deep Generative Model for Robust Forecasting on Sparse Multivariate Time Series [paper] [official code]
  • Temporal Latent Autoencoder: A Method for Probabilistic Multivariate Time Series Forecasting [paper]
  • Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting [paper]
  • Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting [paper]
  • Attentive Neural Point Processes for Event Forecasting [paper] [official code]
  • Forecasting Reservoir Inflow via Recurrent Neural ODEs [paper]
  • Hierarchical Graph Convolution Network for Traffic Forecasting [paper]
  • Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network [paper] [official code]
  • Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting [paper] [official code]
  • FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting [paper] [official code]
  • Fairness in Forecasting and Learning Linear Dynamical Systems [paper]
  • A Multi-Step-Ahead Markov Conditional Forward Model with Cube Perturbations for Extreme Weather Forecasting [paper]
  • Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances [paper]

Time Series Anomaly Detection

  • Graph Neural Network-Based Anomaly Detection in Multivariate Time Series [paper] [official code]
  • Time Series Anomaly Detection with Multiresolution Ensemble Decoding [paper]
  • Outlier Impact Characterization for Time Series Data [paper]

Time Series Classification

  • Correlative Channel-Aware Fusion for Multi-View Time Series Classification [paper]
  • Learnable Dynamic Temporal Pooling for Time Series Classification [paper] [official code]
  • ShapeNet: A Shapelet-Neural Network Approach for Multivariate Time Series Classification [paper]
  • Joint-Label Learning by Dual Augmentation for Time Series Classification [paper]

Other Time Series Analysis

  • Time Series Domain Adaptation via Sparse Associative Structure Alignment [paper] [official code]
  • Learning Representations for Incomplete Time Series Clustering [paper]
  • Generative Semi-Supervised Learning for Multivariate Time Series Imputation [paper] [official code]
  • Second Order Techniques for Learning Time-Series with Structural Breaks [paper]

IJCAI 2021

Time Series Forecasting

  • Two Birds with One Stone: Series Saliency for Accurate and Interpretable Multivariate Time Series Forecasting [paper]
  • Residential Electric Load Forecasting via Attentive Transfer of Graph Neural Networks [paper]
  • Hierarchical Adaptive Temporal-Relational Modeling for Stock Trend Prediction [paper]
  • TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning [paper] [official code]

Other Time Series Analysis

  • Time Series Data Augmentation for Deep Learning: A Survey [paper]
  • Time-Series Representation Learning via Temporal and Contextual Contrasting [paper] [official code]
  • Adversarial Spectral Kernel Matching for Unsupervised Time Series Domain Adaptation [paper] [official code]
  • Time-Aware Multi-Scale RNNs for Time Series Modeling [paper]
  • TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data [paper]

SIGMOD VLDB ICDE 2021

Time Series Forecasting

  • AutoAI-TS:AutoAI for Time Series Forecasting, SIGMOD'21. [paper]
  • FlashP: An Analytical Pipeline for Real-time Forecasting of Time-Series Relational Data, VLDB'21. [paper]
  • MDTP: a multi-source deep traffic prediction framework over spatio-temporal trajectory data, VLDB'21. [paper]
  • EnhanceNet: Plugin Neural Networks for Enhancing Correlated Time Series Forecasting, ICDE'21. [paper] [slides]
  • An Effective Joint Prediction Model for Travel Demands and Traffic Flows, ICDE'21. [paper]

Time Series Anomaly Detection

  • Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series, VLDB'21. [paper] [official code]
  • SAND: Streaming Subsequence Anomaly Detection, VLDB'21. [paper]

Other Time Series Analysis

  • RobustPeriod: Robust Time-Frequency Mining for Multiple Periodicity Detection, SIGMOD'21. [paper] [code]
  • ORBITS: Online Recovery of Missing Values in Multiple Time Series Streams, VLDB'21. [paper] [official code]
  • Missing Value Imputation on Multidimensional Time Series, VLDB'21. [paper]

Misc 2021

Time Series Forecasting

  • DeepFEC: Energy Consumption Prediction under Real-World Driving Conditions for Smart Cities, WWW'21. [paper] [official code]
  • AutoSTG: Neural Architecture Search for Predictions of Spatio-Temporal Graph, WWW'21. [paper] [official code]
  • REST: Reciprocal Framework for Spatiotemporal-coupled Predictions, WWW'21. [paper]
  • Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series, AISTATS'21. [paper]
  • SSDNet: State Space Decomposition Neural Network for Time Series Forecasting, ICDM'21. [paper]
  • AdaRNN: Adaptive Learning and Forecasting of Time Series, CIKM'21. [paper] [official code]
  • Learning to Learn the Future: Modeling Concept Drifts in Time Series Prediction, CIKM'21. [paper]
  • Stock Trend Prediction with Multi-Granularity Data: A Contrastive Learning Approach with Adaptive Fusion, CIKM'21. [paper]
  • DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction, CIKM'21. [paper] [official code1] [official code2]
  • Long Horizon Forecasting With Temporal Point Processes, WSDM'21. [paper] [official code]
  • Time-Series Event Prediction with Evolutionary State Graph, WSDM'21. [paper] [official code].

Time Series Anomaly Detection

  • SDFVAE: Static and Dynamic Factorized VAE for Anomaly Detection of Multivariate CDN KPIs, WWW'21. [paper]
  • Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding, WWW'21. [paper] [official code]
  • FluxEV: A Fast and Effective Unsupervised Framework for Time-Series Anomaly Detection, WSDM'21. [paper]
  • Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warping, ICCV'21. [paper] [official code]

Other Time Series Analysis

  • Network of Tensor Time Series, WWW'21. [paper] [official code]
  • Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series, WWW'21. [paper] [official code]
  • SrVARM: State Regularized Vector Autoregressive Model for Joint Learning of Hidden State Transitions and State-Dependent Inter-Variable Dependencies from Multi-variate Time Series, WWW'21. [paper]
  • Deep Fourier Kernel for Self-Attentive Point Processes, AISTATS'21. [paper]
  • Differentiable Divergences Between Time Series, AISTATS'21. [paper] [official code]
  • Aligning Time Series on Incomparable Spaces, AISTATS'21. [paper] [official code]
  • Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions, ICDM'21. [paper]
  • Towards Generating Real-World Time Series Data, ICDM'21. [paper] [official code]
  • Learning Saliency Maps to Explain Deep Time Series Classifiers, CIKM'21. [paper] [official code]
  • Actionable Insights in Urban Multivariate Time-series, CIKM'21. [paper]
  • Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervals, WSDM'21. [paper]

AI4TS Papers 201X-2020 Selected

NeurIPS 201X-2020

Time Series Forecasting

  • Adversarial Sparse Transformer for Time Series Forecasting, NeurIPS'20. [paper] [official code]
  • Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting, NeurIPS'20. [paper] [official code]
  • Deep Rao-Blackwellised Particle Filters for Time Series Forecasting, NeurIPS'20. [paper]
  • Probabilistic Time Series Forecasting with Shape and Temporal Diversity, NeurIPS'20. [paper] [official code]
  • Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting, NeurIPS'20. [paper] [official code]
  • Interpretable Sequence Learning for Covid-19 Forecasting, NeurIPS'20. [paper]
  • Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting, NeurIPS'19. [paper] [code]
  • Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting, NeurIPS'19. [paper] [official code]
  • High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes, NeurIPS'19. [paper] [official code]
  • Deep State Space Models for Time Series Forecasting, NeurIPS'18. [paper]
  • Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction, NeurIPS'16. [paper]

Time Series Anomaly Detection

  • Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network, NeurIPS'20. [paper]
  • PIDForest: Anomaly Detection via Partial Identification, NeurIPS'19. [paper] [official code]
  • Precision and Recall for Time Series, NeurIPS'18. [paper] [official code]

Time Series Classification

  • Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices, NeurIPS'19. [paper]

Time Series Clustering

  • Learning Representations for Time Series Clustering, NeurIPS'19. [paper] [official code]
  • Learning low-dimensional state embeddings and metastable clusters from time series data, NeurIPS'19. [paper]

Time Series Imputation

Time Series Neural xDE

General Time Series Analysis

  • High-recall causal discovery for autocorrelated time series with latent confounders, NeurIPS'20. [paper] [paper2] [official code]
  • Benchmarking Deep Learning Interpretability in Time Series Predictions, NeurIPS'20. [paper] [official code]
  • What went wrong and when? Instance-wise feature importance for time-series black-box models, NeurIPS'20. [paper] [official code]
  • Normalizing Kalman Filters for Multivariate Time Series Analysis, NeurIPS'20. [paper]
  • Unsupervised Scalable Representation Learning for Multivariate Time Series, NeurIPS'19. [paper] [official code]
  • Time-series Generative Adversarial Networks, NeurIPS'19. [paper] [official code]
  • U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging, NeurIPS'19. [paper] [official code]
  • Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders, NeurIPS'18. [paper]
  • Safe Active Learning for Time-Series Modeling with Gaussian Processes, NeurIPS'18. [paper]

ICML 201X-2020

General Time Series Analysis

  • Learning from Irregularly-Sampled Time Series: A Missing Data Perspective, ICML'20. [paper] [official code]
  • Set Functions for Time Series, ICML'20. [paper] [official code]
  • Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders, ICML'20. [paper] [official code]
  • Spectral Subsampling MCMC for Stationary Time Series, ICML'20. [paper]
  • Learnable Group Transform For Time-Series, ICML'20. [paper]
  • Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models, ICML'19. [paper] [official code]
  • Discovering Latent Covariance Structures for Multiple Time Series, ICML'19. [paper]
  • Autoregressive convolutional neural networks for asynchronous time series, ICML'18. [paper] [official code]
  • Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series, ICML'18. [paper]
  • Soft-DTW: a Differentiable Loss Function for Time-Series, ICML'17. [paper] [official code]

Time Series Forecasting

  • Forecasting Sequential Data Using Consistent Koopman Autoencoders, ICML'20. [paper] [official code]
  • Adversarial Attacks on Probabilistic Autoregressive Forecasting Models, ICML'20. [paper] [official code]
  • Influenza Forecasting Framework based on Gaussian Processes, ICML'20. [paper]
  • Deep Factors for Forecasting, ICML'19. [paper]
  • Coherent Probabilistic Forecasts for Hierarchical Time Series, ICML'17. [paper]

ICLR 201X-2020

General Time Series Analysis

Time Series Forecasting

  • N-BEATS: Neural basis expansion analysis for interpretable time series forecasting, ICLR'20. [paper] [official code]
  • Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting, ICLR'18. [paper] [official code]
  • Automatically Inferring Data Quality for Spatiotemporal Forecasting, ICLR'18. [paper]

KDD 201X-2020

General Time Series Analysis

  • Fast RobustSTL: Efficient and Robust Seasonal-Trend Decomposition for Time Series with Complex Patterns, KDD'20. [paper] [code]
  • Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data, KDD'20. [paper] [official code]
  • Online Amnestic DTW to allow Real-Time Golden Batch Monitoring, KDD'19. [paper]
  • Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis, KDD'18. [paper]
  • Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data, KDD'17. [paper]

Time Series Forecasting

  • Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks, KDD'20. [paper] [official code]
  • Attention based Multi-Modal New Product Sales Time-series Forecasting, KDD'20. [paper]
  • Forecasting the Evolution of Hydropower Generation, KDD'20. [paper]
  • Modeling Extreme Events in Time Series Prediction, KDD'19. [paper]
  • Multi-Horizon Time Series Forecasting with Temporal Attention Learning, KDD'19. [paper]
  • Regularized Regression for Hierarchical Forecasting Without Unbiasedness Conditions, KDD'19. [paper]
  • Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units, KDD'19. [paper] [official code]
  • Dynamic Modeling and Forecasting of Time-evolving Data Streams, KDD'19. [paper] [official code]
  • DeepUrbanEvent: A System for Predicting Citywide Crowd Dynamics at Big Events, KDD'19. [paper] [official code]
  • Stock Price Prediction via Discovering Multi-Frequency Trading Patterns, KDD'17. [paper] [official code]

Time Series Anomaly Detection

  • USAD: UnSupervised Anomaly Detection on Multivariate Time Series, KDD'20. [paper] [official code]
  • RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks, KDD'20 MiLeTS. [paper]
  • Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network, KDD'19. [paper] [official code]
  • Time-Series Anomaly Detection Service at Microsoft, KDD'19. [paper]
  • Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding, KDD'18. [paper] [official code]
  • Anomaly Detection in Streams with Extreme Value Theory, KDD'17. [paper]

AAAI 201X-2020

General Time Series Analysis

  • Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets, AAAI'20. [paper] [official code]
  • DATA-GRU: Dual-Attention Time-Aware Gated Recurrent Unit for Irregular Multivariate Time Series, AAAI'20. [paper]
  • Tensorized LSTM with Adaptive Shared Memory for Learning Trends in Multivariate Time Series, AAAI'20. [paper] [official code]
  • Factorized Inference in Deep Markov Models for Incomplete Multimodal Time Series, AAAI'20. [paper] [official code]
  • Relation Inference among Sensor Time Series in Smart Buildings with Metric Learning, AAAI'20. [paper]
  • TapNet: Multivariate Time Series Classification with Attentional Prototype Network, AAAI'20. [paper] [official code]
  • RobustSTL: A Robust Seasonal-Trend Decomposition Procedure for Long Time Series, AAAI'19. [paper] [code]
  • Estimating the Causal Effect from Partially Observed Time Series, AAAI'19. [paper]
  • Adversarial Unsupervised Representation Learning for Activity Time-Series, AAAI'19. [paper]
  • Fourier Feature Approximations for Periodic Kernels in Time-Series Modelling, AAAI'18. [paper]

Time Series Forecasting

  • Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values, AAAI'20. [paper]
  • Block Hankel Tensor ARIMA for Multiple Short Time Series Forecasting, AAAI'20. [paper] [official code]
  • Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting, AAAI'20. [paper] [official code]
  • Self-Attention ConvLSTM for Spatiotemporal Prediction, AAAI'20. [paper]
  • Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting, AAAI'20. [paper]
  • Spatio-Temporal Graph Structure Learning for Traffic Forecasting, AAAI'20. [paper]
  • GMAN: A Graph Multi-Attention Network for Traffic Prediction, AAAI'20. [paper] [official code]
  • Cogra: Concept-drift-aware Stochastic Gradient Descent for Time-series Forecasting, AAAI'19. [paper]
  • Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting, AAAI'19. [paper]
  • Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting, AAAI'19. [paper] [official code]
  • MRes-RGNN: A Novel Deep Learning based Framework for Traffic Prediction, AAAI'19. [paper]
  • DeepSTN+: Context-aware Spatial Temporal Neural Network for Crowd Flow Prediction in Metropolis, AAAI'19. [paper] [official code]
  • Incomplete Label Multi-task Deep Learning for Spatio-temporal Event Subtype Forecasting, AAAI'19. [paper]
  • Learning Heterogeneous Spatial-Temporal Representation for Bike-sharing Demand Prediction, AAAI'19. [paper]
  • Spatiotemporal Multi-Graph Convolution Network for Ride-hailing Demand Forecasting, AAAI'19. [paper]

Time Series Anomaly Detection

  • A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data, AAAI'19. [paper]
  • Non-parametric Outliers Detection in Multiple Time Series A Case Study: Power Grid Data Analysis, AAAI'18. [paper]

IJCAI 201X-2020

General Time Series Analysis

  • RobustTrend: A Huber Loss with a Combined First and Second Order Difference Regularization for Time Series Trend Filtering, IJCAI'19. [paper]
  • E2GAN: End-to-End Generative Adversarial Network for Multivariate Time Series Imputation, IJCAI'19. [paper]
  • Causal Inference in Time Series via Supervised Learning, IJCAI'18. [paper]

Time Series Forecasting

  • PewLSTM: Periodic LSTM with Weather-Aware Gating Mechanism for Parking Behavior Prediction, IJCAI'20. [paper] [official code]
  • LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks, IJCAI'20. [paper]
  • Cross-Interaction Hierarchical Attention Networks for Urban Anomaly Prediction, IJCAI'20. [paper]
  • Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting, IJCAI'19. [paper]
  • Explainable Deep Neural Networks for Multivariate Time Series Predictions, IJCAI'19. [paper]
  • Periodic-CRN: A Convolutional Recurrent Model for Crowd Density Prediction with Recurring Periodic Patterns. [paper]
  • Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. [paper] [official code]
  • LC-RNN: A Deep Learning Model for Traffic Speed Prediction. [paper]
  • GeoMAN: Multi-level Attention Networks for Geo-sensory Time Series Prediction, IJCAI'18. [paper] [official code]
  • Hierarchical Electricity Time Series Forecasting for Integrating Consumption Patterns Analysis and Aggregation Consistency, IJCAI'18. [paper]
  • NeuCast: Seasonal Neural Forecast of Power Grid Time Series, IJCAI'18. [paper] [official code]
  • A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction, IJCAI'17. [paper] [code]
  • Hybrid Neural Networks for Learning the Trend in Time Series, IJCAI'17. [paper]

Time Series Anomaly Detection

  • BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series, IJCAI'19. [paper] [official code]
  • Outlier Detection for Time Series with Recurrent Autoencoder Ensembles, IJCAI'19. [paper] [official code]
  • Stochastic Online Anomaly Analysis for Streaming Time Series, IJCAI'17. [paper]

Time Series Clustering

  • Linear Time Complexity Time Series Clustering with Symbolic Pattern Forest, IJCAI'19. [paper]
  • Similarity Preserving Representation Learning for Time Series Clustering, IJCAI'19. [paper]

Time Series Classification

  • A new attention mechanism to classify multivariate time series, IJCAI'20. [paper]

SIGMOD VLDB ICDE 201X-2020

General Time Series Analysis

  • Debunking Four Long-Standing Misconceptions of Time-Series Distance Measures, SIGMOD'20. [paper] [official code]
  • Database Workload Capacity Planning using Time Series Analysis and Machine Learning, SIGMOD'20. [paper]
  • Mind the gap: an experimental evaluation of imputation of missing values techniques in time series, VLDB'20. [paper] [official code]
  • Active Model Selection for Positive Unlabeled Time Series Classification, ICDE'20. [paper] [official code]
  • ExplainIt! -- A declarative root-cause analysis engine for time series data, SIGMOD'19. [paper]
  • Cleanits: A Data Cleaning System for Industrial Time Series, VLDB'19. [paper]
  • Matrix Profile X: VALMOD - Scalable Discovery of Variable-Length Motifs in Data Series, SIGMOD'18. [paper]
  • Effective Temporal Dependence Discovery in Time Series Data, VLDB'18. [paper]

Time Series Anomaly Detection

  • Series2Graph: graph-based subsequence anomaly detection for time series, VLDB'20. [paper] [official code]
  • Neighbor Profile: Bagging Nearest Neighbors for Unsupervised Time Series Mining, ICDE'20. [paper]
  • Automated Anomaly Detection in Large Sequences, ICDE'20. [paper] [official code]
  • User-driven error detection for time series with events, ICDE'20. [paper]

Misc 201X-2020

General Time Series Analysis

  • STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural Networks, WWW'19. [paper] [official code]
  • GP-VAE: Deep probabilistic time series imputation, AISTATS'20. [paper] [official code]
  • DYNOTEARS: Structure Learning from Time-Series Data, AISTATS'20. [paper]
  • Personalized Imputation on Wearable-Sensory Time Series via Knowledge Transfer, CIKM'20. [paper]
  • Order-Preserving Metric Learning for Mining Multivariate Time Series, ICDM'20. [paper]
  • Learning Periods from Incomplete Multivariate Time Series, ICDM'20. [paper]
  • Foundations of Sequence-to-Sequence Modeling for Time Series, AISTATS'19. [paper]

Time Series Forecasting

  • Hierarchically Structured Transformer Networks for Fine-Grained Spatial Event Forecasting, WWW'20. [paper]
  • HTML: Hierarchical Transformer-based Multi-task Learning for Volatility Prediction, WWW'20. [paper] [official code]
  • Traffic Flow Prediction via Spatial Temporal Graph Neural Network, WWW'20. [paper]
  • Towards Fine-grained Flow Forecasting: A Graph Attention Approach for Bike Sharing Systems, WWW'20. [paper]
  • Domain Adaptive Multi-Modality Neural Attention Network for Financial Forecasting, WWW'20. [paper]
  • Spatiotemporal Hypergraph Convolution Network for Stock Movement Forecasting, ICDM'20. [paper]
  • Probabilistic Forecasting with Spline Quantile Function RNNs, AISTATS'19. [paper]
  • DSANet: Dual self-attention network for multivariate time series forecasting, CIKM'19. [paper]
  • RESTFul: Resolution-Aware Forecasting of Behavioral Time Series Data, CIKM'18. [paper]
  • Forecasting Wavelet Transformed Time Series with Attentive Neural Networks, ICDM'18. [paper]
  • A Flexible Forecasting Framework for Hierarchical Time Series with Seasonal Patterns: A Case Study of Web Traffic, SIGIR'18. [paper]
  • Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks, SIGIR'18. [paper] [official code]

Time Series Anomaly Detection

  • Multivariate Time-series Anomaly Detection via Graph Attention Network, ICDM'20. [paper] [code]
  • MERLIN: Parameter-Free Discovery of Arbitrary Length Anomalies in Massive Time Series Archives, ICDM'20. [paper] [official code]
  • Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications, WWW'18. [paper] [official code]