Pith. sign in

REVIEW 8 cited by

SegRNN: Segment Recurrent Neural Network for Long-Term 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 2308.11200 v1 pith:VBGIHAVT submitted 2023-08-22 cs.LG

classification cs.LG
keywords ltsfiterationsrnnsdomainforecastingrecurrentsegrnnapproaches
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

RNN-based methods have faced challenges in the Long-term Time Series Forecasting (LTSF) domain when dealing with excessively long look-back windows and forecast horizons. Consequently, the dominance in this domain has shifted towards Transformer, MLP, and CNN approaches. The substantial number of recurrent iterations are the fundamental reasons behind the limitations of RNNs in LTSF. To address these issues, we propose two novel strategies to reduce the number of iterations in RNNs for LTSF tasks: Segment-wise Iterations and Parallel Multi-step Forecasting (PMF). RNNs that combine these strategies, namely SegRNN, significantly reduce the required recurrent iterations for LTSF, resulting in notable improvements in forecast accuracy and inference speed. Extensive experiments demonstrate that SegRNN not only outperforms SOTA Transformer-based models but also reduces runtime and memory usage by more than 78%. These achievements provide strong evidence that RNNs continue to excel in LTSF tasks and encourage further exploration of this domain with more RNN-based approaches. The source code is coming soon.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting

    cs.LG 2026-08 conditional novelty 6.0 of 10

    CosDir aligns the first-difference vectors of predictions and targets via cosine similarity, improving directional accuracy while preserving MSE.

  2. ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting

    cs.LG 2025-09 conditional novelty 6.0 of 10

    ARIES shows that deep forecasting models have consistent performance preferences tied to time series properties, and uses those preferences to recommend models for new datasets.

  3. MillGNN: Learning Multi-Scale Lead-Lag Dependencies for Multi-Variate Time Series Forecasting

    cs.LG 2025-09 conditional novelty 6.0 of 10

    MillGNN learns delayed (lead-lag) influences between time series and between groups of series at multiple grouping scales, reporting state-of-the-art forecast errors on 11 benchmarks.

  4. CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations

    cs.LG 2025-05 conditional novelty 6.0 of 10

    CMoS, a linear chunk-wise model with per-channel mixing of shared correlation matrices, achieves competitive long-term forecasting accuracy on seven benchmarks while using up to 100x fewer parameters than DLinear.

  5. Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework

    cs.LG 2026-07 conditional novelty 5.0 of 10

    WrapFlow combines continuous-time event/gap tokenization with simulation-free residual flow matching on a Transformer to improve irregular multivariate time-series forecasting.

  6. Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives

    cs.LG 2025-06 reject novelty 5.0 of 10

    TimesCLIP aligns image-based and text-based views of the same time series via contrastive learning to improve forecasting accuracy on several benchmarks, but the full multimodal model is not used on two of the six lon...

  7. Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting

    cs.LG 2025-05 conditional novelty 4.0 of 10

    MoLA adapts a pre-trained short-horizon forecaster to multiple forecast steps via segment-specific mixtures of shared low-rank adapters, reporting modest mean-squared-error gains over the base models on most of eight ...

  8. Human in the Loop Adaptive Optimization for Improved Time Series Forecasting

    cs.LG 2025-05 reject novelty 3.0 of 10

    The core idea is standard forecast recalibration, and the reported experiments show mixed, sometimes negative, results with internal table errors, so the claim of consistent improvement fails.

Pith tools