Time Series Forecasting on ETTh1 (336) Multivariate

Metric: MSE (lower is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	MSE▲	Extra Data	Paper	Date↕	Code
1	D-PAD	0.374	No	D-PAD: Deep-Shallow Multi-Frequency Patterns Dis...	2024-03-26	Code
2	xPatch	0.391	No	xPatch: Dual-Stream Time Series Forecasting with...	2024-12-23	Code
3	PatchMixer	0.392	No	PatchMixer: A Patch-Mixing Architecture for Long...	2023-10-01	Code
4	Fredformer	0.395	No	Fredformer: Frequency Debiased Transformer for T...	2024-06-13	Code
5	UniTime	0.398	No	UniTime: A Language-Empowered Unified Model for ...	2023-10-15	Code
6	AutoTimes	0.401	No	AutoTimes: Autoregressive Time Series Forecaster...	2024-02-04	Code
7	SegRNN	0.401	No	SegRNN: Segment Recurrent Neural Network for Lon...	2023-08-22	Code
8	TimeCMA	0.403	No	TimeCMA: Towards LLM-Empowered Multivariate Time...	2024-06-03	Code
9	UniTS-ST	0.405	No	UniTS: A Unified Multi-Task Time Series Model	2024-02-29	Code
10	ConvTimeNet	0.405	No	ConvTimeNet: A Deep Hierarchical Fully Convoluti...	2024-03-03	Code
11	ROSE	0.406	No	ROSE: Register Assisted General Time Series Fore...	2024-05-24	-
12	TEMPO	0.408	No	TEMPO: Prompt-based Generative Pre-trained Trans...	2023-10-08	Code
13	MMFNet	0.409	No	MMFNet: Multi-Scale Frequency Masking Neural Net...	2024-10-02	Code
14	MOIRAISmall	0.412	No	Unified Training of Universal Time Series Foreca...	2024-02-04	Code
15	AMD	0.418	No	Adaptive Multi-Scale Decomposition Framework for...	2024-06-06	Code
16	WinNet	0.419	No	WinNet: Make Only One Convolutional Layer Effect...	2023-11-01	Code
17	RLinear	0.42	No	Revisiting Long-term Time Series Forecasting: An...	2023-05-18	Code
18	TSMixer	0.421	No	TSMixer: Lightweight MLP-Mixer Model for Multiva...	2023-06-14	Code
19	TSMixer	0.421	No	TSMixer: Lightweight MLP-Mixer Model for Multiva...	2023-06-14	Code
20	PatchTST/64	0.422	No	A Time Series is Worth 64 Words: Long-term Forec...	2022-11-27	Code
21	HiMTM	0.422	No	HiMTM: Hierarchical Multi-Scale Masked Time Seri...	2024-01-10	-
22	CATS	0.423	No	CATS: Enhancing Multivariate Time Series Forecas...	2024-03-04	Code
23	SAMformer	0.423	No	SAMformer: Unlocking the Potential of Transforme...	2024-02-15	Code
24	LTBoost (drop_last=false)	0.424	No	-	-	Code
25	GTT-Large	0.424	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
26	DiPE-Linear	0.424	No	Disentangled Interpretable Representation for Ef...	2024-11-26	Code
27	FITS	0.427	No	FITS: Modeling Time Series with $10k$ Parameters	2023-07-06	Code
28	PRformer	0.427	No	PRformer: Pyramidal Recurrent Transformer for Mu...	2024-08-20	Code
29	NLinear	0.429	No	Are Transformers Effective for Time Series Forec...	2022-05-26	Code
30	TimeMachine	0.429	No	TimeMachine: A Time Series is Worth 4 Mambas for...	2024-03-14	Code
31	GPHT	0.43	No	Generative Pretrained Hierarchical Transformer f...	2024-02-26	Code
32	MoLE-RLinear	0.43	No	Mixture-of-Linear-Experts for Long-term Time Ser...	2023-12-11	Code
33	PatchTST + LIFT	0.433	No	Rethinking Channel Dependence for Multivariate T...	2024-01-31	Code
34	GTT-Large(Fine-tune)	0.433	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
35	SparseTSF	0.434	No	SparseTSF: Modeling Long-term Time Series Foreca...	2024-05-02	Code
36	TiDE	0.435	No	Long-term Forecasting with TiDE: Time-series Den...	2023-04-17	Code
37	GridTST	0.436	No	Leveraging 2D Information for Long-term Time Ser...	2024-05-22	Code
38	DLinear	0.439	No	Are Transformers Effective for Time Series Forec...	2022-05-26	Code
39	FiLM	0.442	No	FiLM: Frequency improved Legendre Memory Model f...	2022-05-18	Code
40	OLS	0.448	No	An Analysis of Linear Time Series Forecasting Mo...	2024-03-21	Code
41	DLinear + LIFT	0.453	No	Rethinking Channel Dependence for Multivariate T...	2024-01-31	Code
42	Pathformer	0.454	No	Pathformer: Multi-scale Transformers with Adapti...	2024-02-04	Code
43	Bi-Mamba4TS	0.455	No	Bi-Mamba+: Bidirectional Mamba for Time Series F...	2024-04-24	-
44	MOIRAIBase	0.456	No	Unified Training of Universal Time Series Foreca...	2024-02-04	Code
45	LLaTA	0.456	No	-	-	Code
46	CALF	0.456	No	CALF: Aligning LLMs for Time Series Forecasting ...	2024-03-12	Code
47	GPHT*	0.456	No	Generative Pretrained Hierarchical Transformer f...	2024-02-26	Code
48	GTT-Smal	0.459	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
49	Minusformer-96	0.465	No	Minusformer: Improving Time Series Forecasting b...	2024-02-04	Code
50	GTT-Tiny	0.466	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
51	GTT-Large(100M traing samples)	0.468	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
52	MoLE-DLinear	0.469	No	Mixture-of-Linear-Experts for Long-term Time Ser...	2023-12-11	Code
53	ForecastGrapher	0.472	No	ForecastGrapher: Redefining Multivariate Time Se...	2024-05-28	-
54	Basisformer	0.473	No	BasisFormer: Attention-based Time Series Forecas...	2023-10-31	Code
55	VCformer	0.473	No	VCformer: Variable Correlation Transformer with ...	2024-05-19	Code
56	Simba	0.473	No	Mamba-360: Survey of State Space Models as Trans...	2024-04-24	Code
57	GTT-Large(50M traing samples)	0.475	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
58	TEFN	0.475	No	Time Evidence Fusion Network: Multi-source View ...	2024-05-10	Code
59	CPNet	0.479	No	Boosting MLPs with a Coarsening Strategy for Lon...	2024-05-06	Code
60	SOFTS	0.48	No	SOFTS: Efficient Multivariate Time Series Foreca...	2024-04-22	Code
61	iTransformer	0.487	No	iTransformer: Inverted Transformers Are Effectiv...	2023-10-10	Code
62	S-Mamba	0.489	No	Is Mamba Effective for Time Series Forecasting?	2024-03-17	Code
63	SCINet	0.504	No	SCINet: Time Series Modeling and Forecasting wit...	2021-06-17	Code
64	Autoformer	0.505	No	Autoformer: Decomposition Transformers with Auto...	2021-06-24	Code
65	ATFNet	0.514	No	ATFNet: Adaptive Time-Frequency Ensembled Networ...	2024-04-08	Code
66	MOIRAILarge	0.514	No	Unified Training of Universal Time Series Foreca...	2024-02-04	Code
67	RPMixer	0.521	No	RPMixer: Shaking Up Time Series Forecasting with...	2024-02-16	-
68	Aaren	0.65	No	Attention as an RNN	2024-05-22	Code
69	Transformer	0.8321	No	Long-term series forecasting with Query Selector...	2021-07-19	Code
70	QuerySelector	0.8503	No	Long-term series forecasting with Query Selector...	2021-07-19	Code
71	Informer	0.884	No	Informer: Beyond Efficient Transformer for Long ...	2020-12-14	Code

#1D-PADSOTA
0.374
MSE· 2024-03-26
D-PAD: Deep-Shallow Multi-Frequency Patterns Disentangling for Time Series Forecasting Code
#2xPatch
0.391
MSE· 2024-12-23
xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition Code
#3PatchMixerSOTA
0.392
MSE· 2023-10-01
PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting Code
#4Fredformer
0.395
MSE· 2024-06-13
Fredformer: Frequency Debiased Transformer for Time Series Forecasting Code
#5UniTime
0.398
MSE· 2023-10-15
UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting Code
#6AutoTimes
0.401
MSE· 2024-02-04
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models Code
#7SegRNNSOTA
0.401
MSE· 2023-08-22
SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting Code
#8TimeCMA
0.403
MSE· 2024-06-03
TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment Code
#9UniTS-ST
0.405
MSE· 2024-02-29
UniTS: A Unified Multi-Task Time Series Model Code
#10ConvTimeNet
0.405
MSE· 2024-03-03
ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis Code
#11ROSE
0.406
MSE· 2024-05-24
ROSE: Register Assisted General Time Series Forecasting with Decomposed Frequency Learning
#12TEMPO
0.408
MSE· 2023-10-08
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting Code
#13MMFNet
0.409
MSE· 2024-10-02
MMFNet: Multi-Scale Frequency Masking Neural Network for Multivariate Time Series Forecasting Code
#14MOIRAISmall
0.412
MSE· 2024-02-04
Unified Training of Universal Time Series Forecasting Transformers Code
#15AMD
0.418
MSE· 2024-06-06
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting Code
#16WinNet
0.419
MSE· 2023-11-01
WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting Code
#17RLinearSOTA
0.42
MSE· 2023-05-18
Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping Code
#18TSMixer
0.421
MSE· 2023-06-14
TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting Code
#19TSMixer
0.421
MSE· 2023-06-14
TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting Code
#20PatchTST/64SOTA
0.422
MSE· 2022-11-27
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers Code
#21HiMTM
0.422
MSE· 2024-01-10
HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling for Long-Term Forecasting
#22CATS
0.423
MSE· 2024-03-04
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables Code
#23SAMformer
0.423
MSE· 2024-02-15
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention Code
#24LTBoost (drop_last=false)
0.424
MSE
No paperCode
#25GTT-Large
0.424
MSE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#26DiPE-Linear
0.424
MSE· 2024-11-26
Disentangled Interpretable Representation for Efficient Long-term Time Series Forecasting Code
#27FITS
0.427
MSE· 2023-07-06
FITS: Modeling Time Series with $10k$ Parameters Code
#28PRformer
0.427
MSE· 2024-08-20
PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting Code
#29NLinearSOTA
0.429
MSE· 2022-05-26
Are Transformers Effective for Time Series Forecasting?Code
#30TimeMachine
0.429
MSE· 2024-03-14
TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting Code
#31GPHT
0.43
MSE· 2024-02-26
Generative Pretrained Hierarchical Transformer for Time Series Forecasting Code
#32MoLE-RLinear
0.43
MSE· 2023-12-11
Mixture-of-Linear-Experts for Long-term Time Series Forecasting Code
#33PatchTST + LIFT
0.433
MSE· 2024-01-31
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators Code
#34GTT-Large(Fine-tune)
0.433
MSE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#35SparseTSF
0.434
MSE· 2024-05-02
SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters Code
#36TiDE
0.435
MSE· 2023-04-17
Long-term Forecasting with TiDE: Time-series Dense Encoder Code
#37GridTST
0.436
MSE· 2024-05-22
Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers Code
#38DLinearSOTA
0.439
MSE· 2022-05-26
Are Transformers Effective for Time Series Forecasting?Code
#39FiLMSOTA
0.442
MSE· 2022-05-18
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting Code
#40OLS
0.448
MSE· 2024-03-21
An Analysis of Linear Time Series Forecasting Models Code
#41DLinear + LIFT
0.453
MSE· 2024-01-31
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators Code
#42Pathformer
0.454
MSE· 2024-02-04
Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting Code
#43Bi-Mamba4TS
0.455
MSE· 2024-04-24
Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting
#44MOIRAIBase
0.456
MSE· 2024-02-04
Unified Training of Universal Time Series Forecasting Transformers Code
#45LLaTA
0.456
MSE
No paperCode
#46CALF
0.456
MSE· 2024-03-12
CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning Code
#47GPHT*
0.456
MSE· 2024-02-26
Generative Pretrained Hierarchical Transformer for Time Series Forecasting Code
#48GTT-Smal
0.459
MSE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#49Minusformer-96
0.465
MSE· 2024-02-04
Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals Code
#50GTT-Tiny
0.466
MSE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#51GTT-Large(100M traing samples)
0.468
MSE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#52MoLE-DLinear
0.469
MSE· 2023-12-11
Mixture-of-Linear-Experts for Long-term Time Series Forecasting Code
#53ForecastGrapher
0.472
MSE· 2024-05-28
ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks
#54Basisformer
0.473
MSE· 2023-10-31
BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis Code
#55VCformer
0.473
MSE· 2024-05-19
VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting Code
#56Simba
0.473
MSE· 2024-04-24
Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges Code
#57GTT-Large(50M traing samples)
0.475
MSE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#58TEFN
0.475
MSE· 2024-05-10
Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting Code
#59CPNet
0.479
MSE· 2024-05-06
Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting Code
#60SOFTS
0.48
MSE· 2024-04-22
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion Code
#61iTransformer
0.487
MSE· 2023-10-10
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting Code
#62S-Mamba
0.489
MSE· 2024-03-17
Is Mamba Effective for Time Series Forecasting?Code
#63SCINetSOTA
0.504
MSE· 2021-06-17
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction Code
#64Autoformer
0.505
MSE· 2021-06-24
Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting Code
#65ATFNet
0.514
MSE· 2024-04-08
ATFNet: Adaptive Time-Frequency Ensembled Network for Long-term Time Series Forecasting Code
#66MOIRAILarge
0.514
MSE· 2024-02-04
Unified Training of Universal Time Series Forecasting Transformers Code
#67RPMixer
0.521
MSE· 2024-02-16
RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data
#68Aaren
0.65
MSE· 2024-05-22
Attention as an RNN Code
#69Transformer
0.8321
MSE· 2021-07-19
Long-term series forecasting with Query Selector -- efficient model of sparse attention Code
#70QuerySelector
0.8503
MSE· 2021-07-19
Long-term series forecasting with Query Selector -- efficient model of sparse attention Code
#71InformerSOTA
0.884
MSE· 2020-12-14
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting Code