Research map / Time series / Long-term forecasting

Attention for time series forecasting

Forecast long series with spectral, multi-scale and adaptive transformers and normalization.

123 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Long-term forecasting, keyword cluster “graph · multivariate time · spatial”

State History Benchmarks Tried Baselines Checklist Preprints Who Export

How it got here

Most cited paper of each year

• 2016 · Correcting Forecasts with Multifactor Neural Attention (ICML 2016 · 16 citations)
• 2019 · Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (NeurIPS 2019 · 1,086 citations)
• 2020 · Adversarial Sparse Transformer for Time Series Forecasting (NeurIPS 2020 · 116 citations)
• 2021 · Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (AAAI 2021 · 7,037 citations)
• 2022 · Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting (NeurIPS 2022 · 263 citations)
• 2023 · NHITS: Neural Hierarchical Interpolation for Time Series Forecasting (AAAI 2023 · 516 citations)
• 2024 · iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024 · 385 citations)
• 2025 · Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting (AAAI 2025 · 58 citations)
• 2026 · EMAformer: Enhancing Transformer Through Embedding Armor for Time Series Forecasting (AAAI 2026 · 4 citations)

Earliest papers here

• Correcting Forecasts with Multifactor Neural Attention (ICML 2016 · 16 citations)
• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (NeurIPS 2019 · 1,086 citations)
• Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting (NeurIPS 2019 · 95 citations)

Benchmark records

The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.

What has been tried

61 papers here report 669 measured changes (a component added, removed or swapped, compared with a baseline): helped 68%, no clear effect 6%, hurt 22%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

Baseline numbers that disagree

The same baseline on the same benchmark and metric, reported more than 5% apart by different papers here. Training budgets, data splits and reimplementations differ, so state which number you compare with.

What reviewers will expect

Datasets and baselines named in the 41 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.

Recent preprints

Who publishes on it

Institutions on the most papers of this approach since 2023 (of 111 papers; from OpenAlex and the papers' affiliations).

• Fudan University · 5 papers
• University of Science and Technology of China · 5 papers
• Tsinghua University · 5 papers
• Shanghai Jiao Tong University · 4 papers
• Tongji University · 4 papers
• Hong Kong University of Science and Technology · 4 papers
• Chinese Academy of Sciences · 4 papers
• Alibaba Group · 3 papers
• Shenzhen University · 3 papers
• Beijing Institute of Technology · 3 papers

Use it

Download BibTeX of 29 key papersOpen the topic in the interactive map

Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.

Related approaches

Same keyword cluster

• Spatiotemporal forecasting models (77 papers)
• Graph-based multivariate forecasting (87 papers)

Elsewhere in the topic

• Lightweight long-term forecasters (94 papers)
• Transformers for long-term forecasting (25 papers)

Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).