Pith. sign in

REVIEW 18 cited by

Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.13008 v5 pith:YATVK45K submitted 2021-06-24 cs.LG cs.AI

Haixu Wu , Jiehui Xu , Jianmin Wang , Mingsheng Long This is my paper · ORCID
classification cs.LGcs.AI
keywords seriesautoformerlong-termauto-correlationdecompositionforecastingdependenciesdesign
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Extending the forecasting time is a critical demand for real applications, such as extreme weather early warning and long-term energy consumption planning. This paper studies the long-term forecasting problem of time series. Prior Transformer-based models adopt various self-attention mechanisms to discover the long-range dependencies. However, intricate temporal patterns of the long-term future prohibit the model from finding reliable dependencies. Also, Transformers have to adopt the sparse versions of point-wise self-attentions for long series efficiency, resulting in the information utilization bottleneck. Going beyond Transformers, we design Autoformer as a novel decomposition architecture with an Auto-Correlation mechanism. We break with the pre-processing convention of series decomposition and renovate it as a basic inner block of deep models. This design empowers Autoformer with progressive decomposition capacities for complex time series. Further, inspired by the stochastic process theory, we design the Auto-Correlation mechanism based on the series periodicity, which conducts the dependencies discovery and representation aggregation at the sub-series level. Auto-Correlation outperforms self-attention in both efficiency and accuracy. In long-term forecasting, Autoformer yields state-of-the-art accuracy, with a 38% relative improvement on six benchmarks, covering five practical applications: energy, traffic, economics, weather and disease. Code is available at this repository: \url{https://github.com/thuml/Autoformer}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis

    cs.AI 2025-10 conditional novelty 7.0 of 10

    TelecomTS is a new observability dataset from 5G networks that preserves absolute scale and supports multi-modal tasks, showing that current time series and language models struggle with abrupt noisy dynamics.

  2. CAMP: A Cycle-Aware Multi-Scale Patch Mixer for Time Series Forecasting

    cs.LG 2026-08 conditional novelty 6.0 of 10

    CAMP forecasts time series by learning sample-specific cycles with FFT, removing them, modeling the leftover at multiple wavelet scales, and reporting state-of-the-art benchmark results.

  3. Time Series Foundation Models for Multivariate Financial Time Series Forecasting

    q-fin.GN 2025-07 reject novelty 6.0 of 10

    Pretrained TTM shows large transfer and sample-efficiency gains in three financial forecasting tasks relative to training from scratch, but methodological flaws including possible look-ahead bias weaken the quantitati...

  4. RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting

    cs.LG 2026-07 conditional novelty 5.5 of 10

    RhyMix reaches state-of-the-art long-term multivariate forecasting on 10 of 12 public benchmarks with a ~40K-parameter dual-path adaptive architecture of linear complexity.

  5. When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series

    cs.LG 2026-08 reject novelty 5.0 of 10

    This paper introduces a temporal correlation volatility metric, shows that graph and transformer forecasters fail when it is high, and proposes a GNN layer with path-based and static/dynamic separated propagation that...

  6. Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariates

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Exogenous dropout, a model-agnostic whole-channel training mask, restores corruption robustness better than a deliberately bounded gated-FiLM architecture across three forecasting domains.

  7. MSTN: A Lightweight and Fast Model for General TimeSeries Analysis

    cs.LG 2025-11 unverdicted novelty 5.0 of 10

    MSTN is a lightweight hybrid model that reports new state-of-the-art results on 33 of 40 time series benchmarks for imputation, forecasting, and classification while using under one million parameters and sub-second i...

  8. FinCast: A Foundation Model for Financial Time-Series Forecasting

    cs.LG 2025-08 conditional novelty 5.0 of 10

    FinCast, a 1B-parameter sparse-MoE transformer pretrained on 20B+ financial time points, reports 20% and 23% average MSE reductions over SOTA in zero-shot and supervised financial forecasting.

  9. QuantBench: Benchmarking AI Methods for Quantitative Investment

    q-fin.CP 2025-04 conditional novelty 5.0 of 10

    QuantBench introduces a unified, industry-aligned benchmark platform for evaluating AI methods across the full quantitative investment pipeline, with data, models, and empirical comparisons.

  10. A Comparative Study of Pruning Methods in Transformer-based Time Series Forecasting

    cs.LG 2024-12 conditional novelty 5.0 of 10

    A benchmark shows most time-series Transformers tolerate about 50% unstructured pruning without clear accuracy loss, while structured pruning rarely delivers meaningful inference speedups.

  11. QuantFormer: Learning to Quantize for Neural Activity Forecasting in Mouse Visual Cortex

    q-bio.NC 2024-12 reject novelty 5.0 of 10

    QuantFormer forecasts neural activity by quantizing calcium signals into codes and classifying the future codes, but its headline forecasting gains over a trivial mean baseline disappear under standard error metrics.

  12. Towards Foundation Auto-Encoders for Time-Series Anomaly Detection

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A univariate VAE with dilated convolutions is proposed as a simple 'foundation' model for time-series anomaly detection, with preliminary zero-shot experiments on two datasets.

  13. Enhancing Channel-Independent Time Series Forecasting via Cross-Variate Patch Embedding

    cs.LG 2025-05 conditional novelty 4.0 of 10

    Adding Crossformer-style router attention to Time-LLM patch embeddings improves average MSE on Weather and a 10-feature Traffic subset, while degrading ETTh2, ETTm1, and ETTm2.

  14. Physics-inspired Energy Transition Neural Network for Sequence Learning

    cs.LG 2025-05 conditional novelty 4.0 of 10

    A physics-themed recurrent cell with a time-decay reset and a self-mixing gate matches or beats several Transformer baselines on forecasting benchmarks at a fraction of the compute.

  15. Forecasting Anonymized Electricity Load Profiles

    cs.CR 2025-01 conditional novelty 4.0 of 10

    Microaggregating smart meter data before forecasting leaves aggregated load forecasts accurate or improves them, with volatility dropping as group size k increases.

  16. Dynamic ETF Portfolio Optimization Using enhanced Transformer-Based Models for Covariance and Semi-Covariance Prediction(Work in Progress)

    q-fin.PM 2024-11 reject novelty 4.0 of 10

    Transformer-based covariance and semi-covariance forecasts are claimed to improve ETF portfolio returns, but the supporting backtest is short, leaky, and unreproducible.

  17. Foundation Models for Clean Energy Forecasting: A Comprehensive Review

    eess.SY 2025-07 conditional novelty 3.0 of 10

    A survey of foundation model methods, data, and open problems for renewable energy forecasting, built from roughly 218 cited works.

  18. A Novel Hybrid Approach Using an Attention-Based Transformer + GRU Model for Predicting Cryptocurrency Prices

    cs.LG 2025-04 reject novelty 2.0 of 10

    A Transformer-GRU hybrid is benchmarked for daily Bitcoin and Ethereum price prediction and beats four baselines on error metrics, but the Bitcoin gain over BiGRU is not significant and the architecture is not novel.

Pith tools