Time Series Forecasting on ETTh1 (336) Multivariate

Metric: MAE (lower is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	MAE▲	Extra Data	Paper	Date↕	Code
1	DeformTime	0.2158	No	DeformTime: Capturing Variable Dependencies with...	2024-06-11	Code
2	Fredformer	0.403	No	Fredformer: Frequency Debiased Transformer for T...	2024-06-13	Code
3	TimeCMA	0.405	No	TimeCMA: Towards LLM-Empowered Multivariate Time...	2024-06-03	Code
4	D-PAD	0.406	No	D-PAD: Deep-Shallow Multi-Frequency Patterns Dis...	2024-03-26	Code
5	UniTime	0.407	No	UniTime: A Language-Empowered Unified Model for ...	2023-10-15	Code
6	PatchMixer	0.414	No	PatchMixer: A Patch-Mixing Architecture for Long...	2023-10-01	Code
7	xPatch	0.415	No	xPatch: Dual-Stream Time Series Forecasting with...	2024-12-23	Code
8	SegRNN	0.417	No	SegRNN: Segment Recurrent Neural Network for Lon...	2023-08-22	Code
9	GTT-Large(Fine-tune)	0.418	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
10	GTT-Large	0.419	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
11	ConvTimeNet	0.42	No	ConvTimeNet: A Deep Hierarchical Fully Convoluti...	2024-03-03	Code
12	TimeMachine	0.421	No	TimeMachine: A Time Series is Worth 4 Mambas for...	2024-03-14	Code
13	UniTS-ST	0.422	No	UniTS: A Unified Multi-Task Time Series Model	2024-02-29	Code
14	ROSE	0.422	No	ROSE: Register Assisted General Time Series Fore...	2024-05-24	-
15	RLinear	0.423	No	Revisiting Long-term Time Series Forecasting: An...	2023-05-18	Code
16	LTBoost (drop_last=false)	0.423	No	-	-	Code
17	GPHT	0.423	No	Generative Pretrained Hierarchical Transformer f...	2024-02-26	Code
18	TEMPO	0.425	No	TEMPO: Prompt-based Generative Pre-trained Trans...	2023-10-08	Code
19	SAMformer	0.425	No	SAMformer: Unlocking the Potential of Transforme...	2024-02-15	Code
20	WinNet	0.426	No	WinNet: Make Only One Convolutional Layer Effect...	2023-11-01	Code
21	AMD	0.427	No	Adaptive Multi-Scale Decomposition Framework for...	2024-06-06	Code
22	NLinear	0.427	No	Are Transformers Effective for Time Series Forec...	2022-05-26	Code
23	GTT-Smal	0.427	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
24	AutoTimes	0.429	No	AutoTimes: Autoregressive Time Series Forecaster...	2024-02-04	Code
25	MOIRAISmall	0.429	No	Unified Training of Universal Time Series Foreca...	2024-02-04	Code
26	HiMTM	0.43	No	HiMTM: Hierarchical Multi-Scale Masked Time Seri...	2024-01-10	-
27	TSMixer	0.431	No	TSMixer: An All-MLP Architecture for Time Series...	2023-03-10	Code
28	Pathformer	0.432	No	Pathformer: Multi-scale Transformers with Adapti...	2024-02-04	Code
29	GPHT*	0.432	No	Generative Pretrained Hierarchical Transformer f...	2024-02-26	Code
30	GTT-Large(100M traing samples)	0.432	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
31	TiDE	0.433	No	Long-term Forecasting with TiDE: Time-series Den...	2023-04-17	Code
32	PatchTST + LIFT	0.435	No	Rethinking Channel Dependence for Multivariate T...	2024-01-31	Code
33	TSMixer	0.436	No	TSMixer: Lightweight MLP-Mixer Model for Multiva...	2023-06-14	Code
34	LLaTA	0.436	No	-	-	Code
35	CALF	0.436	No	CALF: Aligning LLMs for Time Series Forecasting ...	2024-03-12	Code
36	GTT-Tiny	0.436	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
37	TimesFM	0.436	No	A decoder-only foundation model for time-series ...	2023-10-14	Code
38	CATS	0.437	No	CATS: Enhancing Multivariate Time Series Forecas...	2024-03-04	Code
39	PatchTST/64	0.44	No	A Time Series is Worth 64 Words: Long-term Forec...	2022-11-27	Code
40	GridTST	0.44	No	Leveraging 2D Information for Long-term Time Ser...	2024-05-22	Code
41	TEFN	0.441	No	Time Evidence Fusion Network: Multi-source View ...	2024-05-10	Code
42	DLinear	0.443	No	Are Transformers Effective for Time Series Forec...	2022-05-26	Code
43	Simba	0.443	No	Mamba-360: Survey of State Space Models as Trans...	2024-04-24	Code
44	GTT-Large(50M traing samples)	0.444	No	Only the Curve Shape Matters: Training Foundatio...	2024-02-12	-
45	FiLM	0.445	No	FiLM: Frequency improved Legendre Memory Model f...	2022-05-18	Code
46	Bi-Mamba4TS	0.445	No	Bi-Mamba+: Bidirectional Mamba for Time Series F...	2024-04-24	-
47	Minusformer-96	0.446	No	Minusformer: Improving Time Series Forecasting b...	2024-02-04	Code
48	ForecastGrapher	0.448	No	ForecastGrapher: Redefining Multivariate Time Se...	2024-05-28	-
49	VCformer	0.449	No	VCformer: Variable Correlation Transformer with ...	2024-05-19	Code
50	MOIRAIBase	0.45	No	Unified Training of Universal Time Series Foreca...	2024-02-04	Code
51	CPNet	0.45	No	Boosting MLPs with a Coarsening Strategy for Lon...	2024-05-06	Code
52	Basisformer	0.451	No	BasisFormer: Attention-based Time Series Forecas...	2023-10-31	Code
53	SOFTS	0.452	No	SOFTS: Efficient Multivariate Time Series Foreca...	2024-04-22	Code
54	DLinear + LIFT	0.453	No	Rethinking Channel Dependence for Multivariate T...	2024-01-31	Code
55	iTransformer	0.458	No	iTransformer: Inverted Transformers Are Effectiv...	2023-10-10	Code
56	S-Mamba	0.468	No	Is Mamba Effective for Time Series Forecasting?	2024-03-17	Code
57	MOIRAILarge	0.474	No	Unified Training of Universal Time Series Foreca...	2024-02-04	Code
58	Autoformer	0.484	No	Autoformer: Decomposition Transformers with Auto...	2021-06-24	Code
59	SCINet	0.495	No	SCINet: Time Series Modeling and Forecasting wit...	2021-06-17	Code
60	RPMixer	0.498	No	RPMixer: Shaking Up Time Series Forecasting with...	2024-02-16	-
61	ATFNet	0.521	No	ATFNet: Adaptive Time-Frequency Ensembled Networ...	2024-04-08	Code
62	Aaren	0.55	No	Attention as an RNN	2024-05-22	Code
63	QuerySelector	0.7039	No	Long-term series forecasting with Query Selector...	2021-07-19	Code
64	Transformer	0.7041	No	Long-term series forecasting with Query Selector...	2021-07-19	Code
65	Informer	0.753	No	Informer: Beyond Efficient Transformer for Long ...	2020-12-14	Code

#1DeformTimeSOTA
0.2158
MAE· 2024-06-11
DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting Code
#2Fredformer
0.403
MAE· 2024-06-13
Fredformer: Frequency Debiased Transformer for Time Series Forecasting Code
#3TimeCMASOTA
0.405
MAE· 2024-06-03
TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment Code
#4D-PADSOTA
0.406
MAE· 2024-03-26
D-PAD: Deep-Shallow Multi-Frequency Patterns Disentangling for Time Series Forecasting Code
#5UniTimeSOTA
0.407
MAE· 2023-10-15
UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting Code
#6PatchMixerSOTA
0.414
MAE· 2023-10-01
PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting Code
#7xPatch
0.415
MAE· 2024-12-23
xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition Code
#8SegRNNSOTA
0.417
MAE· 2023-08-22
SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting Code
#9GTT-Large(Fine-tune)
0.418
MAE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#10GTT-Large
0.419
MAE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#11ConvTimeNet
0.42
MAE· 2024-03-03
ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis Code
#12TimeMachine
0.421
MAE· 2024-03-14
TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting Code
#13UniTS-ST
0.422
MAE· 2024-02-29
UniTS: A Unified Multi-Task Time Series Model Code
#14ROSE
0.422
MAE· 2024-05-24
ROSE: Register Assisted General Time Series Forecasting with Decomposed Frequency Learning
#15RLinearSOTA
0.423
MAE· 2023-05-18
Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping Code
#16LTBoost (drop_last=false)
0.423
MAE
No paperCode
#17GPHT
0.423
MAE· 2024-02-26
Generative Pretrained Hierarchical Transformer for Time Series Forecasting Code
#18TEMPO
0.425
MAE· 2023-10-08
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting Code
#19SAMformer
0.425
MAE· 2024-02-15
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention Code
#20WinNet
0.426
MAE· 2023-11-01
WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting Code
#21AMD
0.427
MAE· 2024-06-06
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting Code
#22NLinearSOTA
0.427
MAE· 2022-05-26
Are Transformers Effective for Time Series Forecasting?Code
#23GTT-Smal
0.427
MAE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#24AutoTimes
0.429
MAE· 2024-02-04
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models Code
#25MOIRAISmall
0.429
MAE· 2024-02-04
Unified Training of Universal Time Series Forecasting Transformers Code
#26HiMTM
0.43
MAE· 2024-01-10
HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling for Long-Term Forecasting
#27TSMixer
0.431
MAE· 2023-03-10
TSMixer: An All-MLP Architecture for Time Series Forecasting Code
#28Pathformer
0.432
MAE· 2024-02-04
Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting Code
#29GPHT*
0.432
MAE· 2024-02-26
Generative Pretrained Hierarchical Transformer for Time Series Forecasting Code
#30GTT-Large(100M traing samples)
0.432
MAE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#31TiDE
0.433
MAE· 2023-04-17
Long-term Forecasting with TiDE: Time-series Dense Encoder Code
#32PatchTST + LIFT
0.435
MAE· 2024-01-31
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators Code
#33TSMixer
0.436
MAE· 2023-06-14
TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting Code
#34LLaTA
0.436
MAE
No paperCode
#35CALF
0.436
MAE· 2024-03-12
CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning Code
#36GTT-Tiny
0.436
MAE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#37TimesFM
0.436
MAE· 2023-10-14
A decoder-only foundation model for time-series forecasting Code
#38CATS
0.437
MAE· 2024-03-04
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables Code
#39PatchTST/64
0.44
MAE· 2022-11-27
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers Code
#40GridTST
0.44
MAE· 2024-05-22
Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers Code
#41TEFN
0.441
MAE· 2024-05-10
Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting Code
#42DLinearSOTA
0.443
MAE· 2022-05-26
Are Transformers Effective for Time Series Forecasting?Code
#43Simba
0.443
MAE· 2024-04-24
Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges Code
#44GTT-Large(50M traing samples)
0.444
MAE· 2024-02-12
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
#45FiLMSOTA
0.445
MAE· 2022-05-18
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting Code
#46Bi-Mamba4TS
0.445
MAE· 2024-04-24
Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting
#47Minusformer-96
0.446
MAE· 2024-02-04
Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals Code
#48ForecastGrapher
0.448
MAE· 2024-05-28
ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks
#49VCformer
0.449
MAE· 2024-05-19
VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting Code
#50MOIRAIBase
0.45
MAE· 2024-02-04
Unified Training of Universal Time Series Forecasting Transformers Code
#51CPNet
0.45
MAE· 2024-05-06
Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting Code
#52Basisformer
0.451
MAE· 2023-10-31
BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis Code
#53SOFTS
0.452
MAE· 2024-04-22
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion Code
#54DLinear + LIFT
0.453
MAE· 2024-01-31
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators Code
#55iTransformer
0.458
MAE· 2023-10-10
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting Code
#56S-Mamba
0.468
MAE· 2024-03-17
Is Mamba Effective for Time Series Forecasting?Code
#57MOIRAILarge
0.474
MAE· 2024-02-04
Unified Training of Universal Time Series Forecasting Transformers Code
#58AutoformerSOTA
0.484
MAE· 2021-06-24
Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting Code
#59SCINetSOTA
0.495
MAE· 2021-06-17
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction Code
#60RPMixer
0.498
MAE· 2024-02-16
RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data
#61ATFNet
0.521
MAE· 2024-04-08
ATFNet: Adaptive Time-Frequency Ensembled Network for Long-term Time Series Forecasting Code
#62Aaren
0.55
MAE· 2024-05-22
Attention as an RNN Code
#63QuerySelector
0.7039
MAE· 2021-07-19
Long-term series forecasting with Query Selector -- efficient model of sparse attention Code
#64Transformer
0.7041
MAE· 2021-07-19
Long-term series forecasting with Query Selector -- efficient model of sparse attention Code
#65InformerSOTA
0.753
MAE· 2020-12-14
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting Code