This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model. This repository is still being continuously improved. If you have found any relevant papers that need to be included in this repository, please feel free to submit a pull request (PR) or open an issue.

Each paper may apply to one or several types of forecasting, including univariate time series forecasting, multivariate time series forecasting, and spatio-temporal forecasting, which are also marked in the Type column. If covariates and exogenous variables are not considered, univariate time series forecasting involves predicting the future of one variable with the history of this variable, while multivariate time series forecasting involves predicting the future of C variables with the history of C variables. Note that repeating univariate forecasting multiple times can also achieve the goal of multivariate forecasting. However, univariate forecasting methods cannot extract relationships between variables, so the basis for distinguishing between univariate and multivariate forecasting methods is whether the method involves interaction between variables. Besides, in the era of deep learning, many univariate models can be easily modified to directly process multiple variables for multivariate forecasting. And multivariate models generally can be directly used for univariate forecasting. Here we classify solely based on the model's description in the original paper. Spatio-temporal forecasting is often used in traffic and weather forecasting, and it adds a spatial dimension compared to univariate and multivariate forecasting. In spatio-temporal forecasting, if each measurement point has only one variable, it is equivalent to multivariate forecasting. Therefore, the distinction between spatio-temporal forecasting and multivariate forecasting is not clear. Spatio-temporal models can usually be directly applied to multivariate forecasting, and multivariate models can also be used for spatio-temporal forecasting with minor modifications. Here we also classify solely based on the model's description in the original paper.

• univariate time series forecasting: , where L is the history length, H is the prediction horizon length.
• multivariate time series forecasting: , where C is the number of variables (channels).
• spatio-temporal forecasting: , where N is the spatial dimension (number of measurement points).

🚩 I have marked some recommended papers with 🌟 (Just my personal preference 😉).

Date	Method	Type	Conference	Paper Title and Paper Interpretation (In Chinese)	Code
19-06-29	LogTrans		NIPS 2019	Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting	flowforecast
19-12-19	TFT🌟		IJoF 2021	Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting	tft
20-01-23	InfluTrans		Arxiv 2020	Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case	influenza transformer
20-06-05	AST		NIPS 2020	Adversarial Sparse Transformer for Time Series Forecasting	AST
20-12-14	Informer🌟		AAAI 2021	Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting	Informer
21-05-22	ProTran		NIPS 2021	Probabilistic Transformer for Time Series Analysis	None
21-06-24	Autoformer🌟		NIPS 2021	Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting	Autoformer
21-09-17	Aliformer		Arxiv 2021	From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba	None
21-10-05	Pyraformer		ICLR 2022	Pyraformer: Low-complexity Pyramidal Attention for Long-range Time Series Modeling and Forecasting	Pyraformer
22-01-14	Preformer		ICASSP 2023	Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecasting	Preformer
22-01-30	FEDformer🌟		ICML 2022	FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting	FEDformer
22-02-03	ETSformer		Arxiv 2022	ETSformer: Exponential Smoothing Transformers for Time-series Forecasting	etsformer
22-02-07	TACTiS		ICML 2022	TACTiS: Transformer-Attentional Copulas for Time Series	TACTiS
22-04-28	Triformer		IJCAI 2022	Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting	Triformer
22-05-27	TDformer		NIPSW 2022	First De-Trend then Attend: Rethinking Attention for Time-Series Forecasting	TDformer
22-05-28	Non-stationary Transformer		NIPS 2022	Non-stationary Transformers: Rethinking the Stationarity in Time Series Forecasting	Non-stationary Transformers
22-06-08	Scaleformer		ICLR 2023	Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting	Scaleformer
22-08-14	Quatformer		KDD 2022	Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting	Quatformer
22-08-30	Persistence Initialization		Arxiv 2022	Persistence Initialization: A novel adaptation of the Transformer architecture for Time Series Forecasting	None
22-09-08	W-Transformers		Arxiv 2022	W-Transformers: A Wavelet-based Transformer Framework for Univariate Time Series Forecasting	w-transformer
22-09-22	Crossformer		ICLR 2023	Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting	Crossformer
22-09-22	PatchTST🌟		ICLR 2023	A Time Series is Worth 64 Words: Long-term Forecasting with Transformers	PatchTST
22-11-29	AirFormer		AAAI 2023	AirFormer: Predicting Nationwide Air Quality in China with Transformers	AirFormer
23-01-19	PDFormer		AAAI 2023	PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction	PDFormer
23-05-20	CARD		Arxiv 2023	Make Transformer Great Again for Time Series Forecasting: Channel Aligned Robust Dual Transformer	None
23-05-24	JTFT		Arxiv 2023	A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecasting	None
23-05-30	HSTTN		IJCAI 2023	Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer	None
23-05-30	Client		Arxiv 2023	Client: Cross-variable Linear Integrated Enhanced Transformer for Multivariate Long-Term Time Series Forecasting	Client
23-05-30	Taylorformer		Arxiv 2023	Taylorformer: Probabilistic Predictions for Time Series and other Processes	Taylorformer
23-06-05	Corrformer🌟		NMI 2023	Interpretable weather forecasting for worldwide stations with a unified deep model	Corrformer
23-06-14	GCformer		Arxiv 2023	GCformer: An Efficient Framework for Accurate and Scalable Long-Term Multivariate Time Series Forecasting	GCformer
23-07-04	SageFormer		Arxiv 2023	SageFormer: Series-Aware Graph-Enhanced Transformers for Multivariate Time Series Forecasting	None
23-07-10	DifFormer		TPAMI 2023	DifFormer: Multi-Resolutional Differencing Transformer With Dynamic Ranging for Time Series Analysis	None
23-07-27	HUTFormer		Arxiv 2023	HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting	None
23-08-07	DSformer		CIKM 2023	DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction	None
23-08-09	SBT		KDD 2023	Sparse Binary Transformers for Multivariate Time Series Modeling	None
23-08-09	PETformer		Arxiv 2023	PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformer	None
23-10-02	TACTiS-2		Arxiv 2023	TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series	None
23-10-03	PrACTiS		Arxiv 2023	PrACTiS: Perceiver-Attentional Copulas for Time Series	None
23-10-10	iTransformer		Arxiv 2023	iTransformer: Inverted Transformers Are Effective for Time Series Forecasting	None

Date	Method	Type	Conference	Paper Title and Paper Interpretation (In Chinese)	Code
17-03-21	LSTNet🌟		SIGIR 2018	Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks	LSTNet
17-04-07	DA-RNN		IJCAI 2017	A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction	DARNN
17-04-13	DeepAR🌟		IJoF 2019	DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks	DeepAR
17-11-29	MQRNN		NIPSW 2017	A Multi-Horizon Quantile Recurrent Forecaster	MQRNN
18-06-23	mWDN		KDD 2018	Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis	mWDN
18-09-06	MTNet		AAAI 2019	A Memory-Network Based Solution for Multivariate Time-Series Forecasting	MTNet
19-05-28	DF-Model		ICML 2019	Deep Factors for Forecasting	None
19-07-18	ESLSTM		IJoF 2020	A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting	None
19-07-25	MH-TAL		KDD 2019	Multi-Horizon Time Series Forecasting with Temporal Attention Learning	None
22-05-16	C2FAR		NIPS 2022	C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting	C2FAR
23-06-02	RNN-ODE-Adap		Arxiv 2023	Neural Differential Recurrent Neural Network with Adaptive Time Steps	RNN_ODE_Adap
23-08-22	SegRNN		Arxiv 2023	SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting	None

Date	Method	Type	Conference	Paper Title and Paper Interpretation (In Chinese)	Code
19-05-24	NBeats🌟		ICLR 2020	N-BEATS: Neural Basis Expansion Analysis For Interpretable Time Series Forecasting	NBeats
21-04-12	NBeatsX		IJoF 2022	Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx	NBeatsX
22-01-30	N-HiTS🌟		AAAI 2023	N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting	N-HiTS
22-05-15	DEPTS		ICLR 2022	DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting	DEPTS
22-05-24	FreDo		Arxiv 2022	FreDo: Frequency Domain-based Long-Term Time Series Forecasting	None
22-05-26	DLinear🌟		AAAI 2023	Are Transformers Effective for Time Series Forecasting?	DLinear
22-06-24	TreeDRNet		Arxiv 2022	TreeDRNet: A Robust Deep Model for Long Term Time Series Forecasting	None
22-07-04	LightTS		Arxiv 2022	Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures	LightTS
22-08-10	STID		CIKM 2022	Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting	STID
23-01-30	SimST		Arxiv 2023	Do We Really Need Graph Neural Networks for Traffic Forecasting?	None
23-02-09	MTS-Mixers		Arxiv 2023	MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing	MTS-Mixers
23-03-10	TSMixer		Arxiv 2023	TSMixer: An all-MLP Architecture for Time Series Forecasting	None
23-04-17	TiDE🌟		Arxiv 2023	Long-term Forecasting with TiDE: Time-series Dense Encoder	TiDE
23-05-18	RTSF		Arxiv 2023	Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping	RTSF
23-05-30	Koopa🌟		NIPS 2023	Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors	Koopa
23-06-14	CI-TSMixer		KDD 2023	TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting	None
23-07-06	FITS		Arxiv 2023	FITS: Modeling Time Series with 10k Parameters	FITS
23-08-14	ST-MLP		Arxiv 2023	ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecasting	None
23-08-25	TFDNet		Arxiv 2023	TFDNet: Time-Frequency Enhanced Decomposed Network for Long-term Time Series Forecasting	None

Date	Method	Type	Conference	Paper Title and Paper Interpretation (In Chinese)	Code
19-05-09	DeepGLO🌟		NIPS 2019	Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting	deepglo
19-05-22	DSANet		CIKM 2019	DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting	DSANet
19-12-11	MLCNN		AAAI 2020	Towards Better Forecasting by Fusing Near and Distant Future Visions	MLCNN
21-06-17	SCINet		NIPS 2022	SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction	SCINet
22-09-22	MICN		ICLR 2023	MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting	MICN
22-09-22	TimesNet🌟		ICLR 2023	TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis	TimesNet
23-02-23	LightCTS		SIGMOD 2023	LightCTS: A Lightweight Framework for Correlated Time Series Forecasting	LightCTS
23-05-25	TLNets		Arxiv 2023	TLNets: Transformation Learning Networks for long-range time-series prediction	TLNets
23-06-04	Cross-LKTCN		Arxiv 2023	Cross-LKTCN: Modern Convolution Utilizing Cross-Variable Dependency for Multivariate Time Series Forecasting Dependency for Multivariate Time Series Forecasting	None
23-06-12	MPPN		Arxiv 2023	MPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting	None
23-06-19	FDNet		KBS 2023	FDNet: Focal Decomposed Network for Efficient, Robust and Practical Time Series Forecasting	FDNet
23-10-01	PatchMixer		Arxiv 2023	PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting	PatchMixer

Date	Method	Type	Conference	Paper Title and Paper Interpretation (In Chinese)	Code
17-09-14	STGCN🌟		IJCAI 2018	Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting	STGCN
19-05-31	Graph WaveNet		IJCAI 2019	Graph WaveNet for Deep Spatial-Temporal Graph Modeling	Graph-WaveNet
19-07-17	ASTGCN		AAAI 2019	Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting	ASTGCN
20-04-03	SLCNN		AAAI 2020	Spatio-Temporal Graph Structure Learning for Traffic Forecasting	None
20-04-03	GMAN		AAAI 2020	GMAN: A Graph Multi-Attention Network for Traffic Prediction	GMAN
20-05-03	MTGNN🌟		KDD 2020	Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks	MTGNN
21-03-13	StemGNN🌟		NIPS 2020	Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting	StemGNN
22-05-16	TPGNN		NIPS 2022	Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks	TPGNN
22-06-18	D2STGNN		VLDB 2022	Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting	D2STGNN
23-07-10	NexuSQN		Arxiv 2023	Nexus sine qua non: Essentially connected neural networks for spatial-temporal forecasting of multivariate time series	None

Date	Method	Type	Conference	Paper Title and Paper Interpretation (In Chinese)	Code
17-05-25	ND		TNNLS 2017	Neural Decomposition of Time-Series Data for Effective Generalization	None
17-08-25	Prophet🌟		TAS 2018	Forecasting at Scale	Prophet
22-07-13	DeepTime		ICML 2023	Learning Deep Time-index Models for Time Series Forecasting	DeepTime
23-06-09	TimeFlow		Arxiv 2023	Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations	None

Date	Method	Type	Conference	Paper Title and Paper Interpretation (In Chinese)	Code
22-02-23	FSNet		ICLR 2023	Learning Fast and Slow for Online Time Series Forecasting	FSNet
23-09-22	OneNet		NIPS 2023	OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling	OneNet
23-09-25	MemDA		CIKM 2023	MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation	None