Pith. sign in

REVIEW 15 cited by

Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures

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 2207.01186 v1 pith:LV6BLGYG submitted 2022-07-04 cs.LG cs.AI

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

Multivariate time series forecasting has seen widely ranging applications in various domains, including finance, traffic, energy, and healthcare. To capture the sophisticated temporal patterns, plenty of research studies designed complex neural network architectures based on many variants of RNNs, GNNs, and Transformers. However, complex models are often computationally expensive and thus face a severe challenge in training and inference efficiency when applied to large-scale real-world datasets. In this paper, we introduce LightTS, a light deep learning architecture merely based on simple MLP-based structures. The key idea of LightTS is to apply an MLP-based structure on top of two delicate down-sampling strategies, including interval sampling and continuous sampling, inspired by a crucial fact that down-sampling time series often preserves the majority of its information. We conduct extensive experiments on eight widely used benchmark datasets. Compared with the existing state-of-the-art methods, LightTS demonstrates better performance on five of them and comparable performance on the rest. Moreover, LightTS is highly efficient. It uses less than 5% FLOPS compared with previous SOTA methods on the largest benchmark dataset. In addition, LightTS is robust and has a much smaller variance in forecasting accuracy than previous SOTA methods in long sequence forecasting tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 15 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. AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    AnchorMoE turns multivariate time-series classification into an additive Mixture-of-Experts over multi-view patches, with orthogonal anchors and reliability gates that suppress noise while matching strong classifiers.

  3. 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.

  4. From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Large vision models slightly beat strong baselines on imaged time series classification, but their forecasting advantage is narrow, tied to periodic patterns, and shrinks with long histories.

  5. TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state

    cs.LG 2025-05 conditional novelty 6.0 of 10

    TimePro forecasts long multivariate series by scanning across variables with a Mamba-like model, then tuning each variable's hidden state at adaptively chosen time points.

  6. 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.

  7. Modular Foundation Models for Time-Series Perception in Digital Twins

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A gated bank of frozen self-supervised time-series encoders, aligned and aggregated by a Transformer, supports competitive multi-task perception for digital twins and hydro-generator virtual sensing.

  8. 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...

  9. CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting

    cs.LG 2025-11 conditional novelty 5.0 of 10

    CaReTS forecasts multi-step time series by combining a trend classifier with a deviation regressor in a residual, uncertainty-weighted multi-task framework.

  10. Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Using Fourier basis expansion to build time-frequency features improves long-term and short-term time series forecasting across linear, MLP, and transformer backbones.

  11. 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...

  12. TFKAN: Time-Frequency KAN for Long-Term Time Series Forecasting

    cs.LG 2025-06 conditional novelty 5.0 of 10

    TFKAN places Kolmogorov-Arnold Networks directly on FFT coefficients alongside a time-domain KAN branch, improving long-term forecast accuracy on seven benchmark datasets.

  13. FaCTR: Factorized Channel-Temporal Representation Transformers for Efficient Time Series Forecasting

    cs.LG 2025-06 conditional novelty 5.0 of 10

    FaCTR uses a factorization machine, instead of dense spatiotemporal attention, to model cross-channel relationships in a compact transformer for time series forecasting.

  14. Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A learnable fusor that reads meta-features of an input time series and weights 13 pre-trained forecasters per sample outperforms each individual model on most benchmark samples, including zero-shot settings.

  15. UDuo: Universal Dual Optimization Framework for Online Matching

    cs.IR 2025-05 reject novelty 4.0 of 10

    UDuo replaces the static arrival assumption in online matching with forecasted dual values and reports modest A/B improvements, but its optimality and feasibility guarantees are stated without proof.

Pith tools