Papers › Temporal Pattern Attention for Multivariate Time Series Forecasting

Temporal Pattern Attention for Multivariate Time Series Forecasting

12 Sep 2018arXiv:1809.04206archive 2025-07-28

Shun-Yao Shih, Fan-Keng Sun, Hung-Yi Lee

Forecasting multivariate time series data, such as prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdependencies between time steps and series complicate the task. To obtain accurate prediction, it is crucial to model long-term dependency in time series data, which can be achieved to some good extent by recurrent neural network (RNN) with attention mechanism. Typical attention mechanism reviews the information at each previous time step and selects the relevant information to help generate the outputs, but it fails to capture the temporal patterns across multiple time steps. In this paper, we propose to use a set of filters to extract time-invariant temporal patterns, which is similar to transforming time series data into its "frequency domain". Then we proposed a novel attention mechanism to select relevant time series, and use its "frequency domain" information for forecasting. We applied the proposed model on several real-world tasks and achieved state-of-the-art performance in all of them with only one exception.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

gantheory/TPA-LSTM officialmentioned in papermentioned on GitHubtf report

abinashsinha330/Air-Pollution-Forecasting-using-Machine-Learning-APF-Model mentioned on GitHubtf report

abinashsinha330/Air-Pollution-Forecasting-using-Recurrent-Neural-Networks mentioned on GitHubtf report

abinashsinha330/Solve-Air-Air-Pollution-Forecasting-using-Deep-Attentive-Sequence-Learning mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multivariate Time Series Forecasting Time Series Time Series Analysis Time Series Forecasting Univariate Time Series Forecasting

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Univariate Time Series Forecasting	Electricity	TPA-LSTM (3 step)	RRSE	0.0823	#2 of 12	Archive leaderboard	report
Univariate Time Series Forecasting	Electricity	TPA-LSTM (6 step)	RRSE	0.0916	#6 of 12	Archive leaderboard	report
Univariate Time Series Forecasting	Electricity	TPA-LSTM (12 step)	RRSE	0.0964	#9 of 12	Archive leaderboard	report
Univariate Time Series Forecasting	Electricity	TPA-LSTM (24 step)	RRSE	0.1006	#10 of 12	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections