mlsanityData to 14 Oct 2026

Long-term series forecasting with Query Selector -- efficient model of sparse attention

arXiv 2107.08687 ↗First posted 19 Jul 2021cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Various modifications of TRANSFORMER were recently used to solve time-series forecasting problem. We propose Query Selector - an efficient, deterministic algorithm for sparse attention matrix. Experiments show it achieves state-of-the art results on ETT, Helpdesk and BPI'12 datasets.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 19 Jul 2021.

Builds on

18 of 29 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2020Longformer: The Long-Document Transformercited by 3,413
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  6. 2020Reformer: The Efficient Transformercited by 1,668
  7. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  8. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  9. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  10. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  11. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
  12. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
6 more
  1. 2021ZeRO-Offload: Democratizing Billion-Scale Model Trainingcited by 341
  2. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  3. 2016Predictive Business Process Monitoring with LSTM Neural Networkscited by 104
  4. 2021Do We Really Need Deep Learning Models for Time Series Forecasting?cited by 45
  5. 2016Time and Activity Sequence Prediction of Business Process Instancescited by 24
  6. 2019Sequence to Sequence with Attention for Influenza Prevalence Prediction using Google Trendscited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 0; 2025: 1.

4 papers.

  1. 2021Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecastingcited by 11
  2. 2023CREATED: Generating Viable Counterfactual Sequences for Predictive Process Analyticscited by 4
  3. 2022Temporal Saliency Detection Towards Explainable Transformer-based Timeseries Forecastingcited by 1
  4. 2025Naga: Vedic Encoding for Deep State Space Modelscited by 0