Pith. sign in

REVIEW 12 cited by

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

Not yet reviewed by Pith; the record is open.

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 2012.07436 v3 pith:OELBUZP3 submitted 2020-12-14 cs.LG cs.AIcs.IR

classification cs.LGcs.AIcs.IR
keywords longlstftime-seriesinformerinputpredictionsequencesequences
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Many real-world applications require the prediction of long sequence time-series, such as electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a high prediction capacity of the model, which is the ability to capture precise long-range dependency coupling between output and input efficiently. Recent studies have shown the potential of Transformer to increase the prediction capacity. However, there are several severe issues with Transformer that prevent it from being directly applicable to LSTF, including quadratic time complexity, high memory usage, and inherent limitation of the encoder-decoder architecture. To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a $ProbSparse$ self-attention mechanism, which achieves $O(L \log L)$ in time complexity and memory usage, and has comparable performance on sequences' dependency alignment. (ii) the self-attention distilling highlights dominating attention by halving cascading layer input, and efficiently handles extreme long input sequences. (iii) the generative style decoder, while conceptually simple, predicts the long time-series sequences at one forward operation rather than a step-by-step way, which drastically improves the inference speed of long-sequence predictions. Extensive experiments on four large-scale datasets demonstrate that Informer significantly outperforms existing methods and provides a new solution to the LSTF problem.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 472 citations worldwide. 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. Customizing the Inductive Biases of Softmax Attention using Structured Matrices

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Structured-matrix scoring functions, BTT and MLR, let attention escape the low-rank bottleneck and add a distance-dependent compute bias, improving accuracy for fixed compute on regression, language modeling, and forecasting.

  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. Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions

    cs.LG 2025-05 reject novelty 6.0 of 10

    CHARM is a 7M-parameter self-supervised embedding model for multivariate time series that uses channel descriptions to beat specialized baselines on forecasting, classification, and anomaly detection.

  5. Forking-Sequences: Statistically and Computationally Efficient Multi-Horizon Forecasting with Reduced Volatility

    cs.LG 2025-10 conditional novelty 5.0 of 10

    Forking-sequences trains forecasting models on all forecast-creation dates jointly, reducing gradient and forecast variance relative to per-date window sampling.

  6. From Noise to Precision: A Diffusion-Driven Approach to Zero-Inflated Precipitation Prediction

    cs.LG 2025-09 reject novelty 5.0 of 10

    A Gaussian-smoothing, Transformer, and DDPM denoising stack is claimed to cut MSE by up to 56.7% on zero-inflated precipitation forecasting, with a theoretical guarantee that does not hold.

  7. 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.

  8. Foundation Models and Fine-Tuning: Toward a New Generation of Models for Time Series Forecasting

    cs.LG 2026-07 reject novelty 4.0 of 10

    Fine-tuning time series foundation models helps on some datasets and sizes, but the paper's claim that it consistently beats zero-shot forecasting is not supported by the reported experiments.

  9. STGAtt: A Spatial-Temporal Unified Graph Attention Network for Traffic Flow Forecasting

    cs.LG 2025-08 unverdicted novelty 4.0 of 10

    STGAtt claims a unified spatial-temporal graph attention model with a neighborhood signal-exchanging mechanism beats state-of-the-art traffic forecasters on PEMS-BAY and SHMetro.

  10. Applying multimodal learning to Classify transient Detections Early (AppleCiDEr) I: Data set, methods, and infrastructure

    astro-ph.IM 2025-07 conditional novelty 4.0 of 10

    AppleCiDEr combines photometry, images, metadata, and spectra in one deep learning pipeline to classify ZTF transients and variable stars, with high accuracy on common classes but poor performance on tidal disruption events.

  11. Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A small Transformer trained with a cosine-based triplet loss learns 16-dimensional embeddings that retrieve similar short driving trajectories from Argoverse 2 substantially better than FFT-based triplet training.

  12. Generative Modeling of Networked Time-Series via Transformer Architectures

    cs.LG 2025-06 reject novelty 3.0 of 10

    A GPT-style encoder-only transformer generates synthetic time-series data that slightly improves downstream ML performance on two network datasets.

Pith tools