Papers › Minimal Time Series Transformer

Minimal Time Series Transformer

12 Mar 2025arXiv:2503.09791archive 2025-07-28

Joni-Kristian Kämäräinen

Transformer is the state-of-the-art model for many natural language processing, computer vision, and audio analysis problems. Transformer effectively combines information from the past input and output samples in auto-regressive manner so that each sample becomes aware of all inputs and outputs. In sequence-to-sequence (Seq2Seq) modeling, the transformer processed samples become effective in predicting the next output. Time series forecasting is a Seq2Seq problem. The original architecture is defined for discrete input and output sequence tokens, but to adopt it for time series, the model must be adapted for continuous data. This work introduces minimal adaptations to make the original transformer architecture suitable for continuous value time series data.

PaperPDFCode

Code

kamarain/minimal_time_series_transformer officialmentioned on GitHub 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

Time SeriesTime Series Forecasting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ADOPTAWAREAbsolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLSTMLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSeq2SeqSigmoid ActivationSoftmaxTanh ActivationTransformer

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