Mlinear: Rethink the Linear Model for Time-series Forecasting

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

1. Very close Not relevant

   An Efficient Decomposition-Driven Linear Framework for Long-Term Time-Series Forecasting

   Zhihong Chen, Yu Zhao, Tao Zou et al. · 2025 · 2025 IEEE Cyber Science and Technology Congress (CyberSciTech) · Not summarized yet

   Abstract

   Recent advances in long-term time-series forecasting have been predominantly driven by Transformer-based architectures, which demonstrate strong performance through powerful attention mechanisms and high model capacity. However, these models often suffer from substantial computational overhead, slow training and inference speeds, and complex feature extraction procedures, making them less suitable for real-time or resource-constrained scenarios. In this work, we revisit the potential of simple yet effective models and propose a novel forecasting framework (iLinear) based on multilayer perceptions, which we refer to as a lightweight linear MLP model. Our model captures long-term temporal depe…

2. Close Not relevant

   MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with 0.1K Parameters

   Ai-Tian Ma, Dongsheng Luo, Mo Sha · 2024 · International Conference on Learning Representations · cited 18 times · Not summarized yet

   Abstract

   Recently, there has been a growing interest in Long-term Time Series Forecasting (LTSF), which involves predicting long-term future values by analyzing a large amount of historical time-series data to identify patterns and trends. There exist significant challenges in LTSF due to its complex temporal dependencies and high computational demands. Although Transformer-based models offer high forecasting accuracy, they are often too compute-intensive to be deployed on devices with hardware constraints. On the other hand, the linear models aim to reduce the computational overhead by employing either decomposition methods in the time domain or compact representations in the frequency domain. In th…

3. Close Not relevant

   Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities

   Mingyu Jin, Hua Tang, Chong Zhang et al. · 2024 · Computation and Language · cited 104 times · AI summary available

   Abstract

   Large language models (LLMs) have been applied in many fields with rapid development in recent years. As a classic machine learning task, time series forecasting has recently received a boost from LLMs. However, there is a research gap in the LLMs' preferences in this field. In this paper, by comparing LLMs with traditional models, many properties of LLMs in time series prediction are found. For example, our study shows that LLMs excel in predicting time series with clear patterns and trends but face challenges with datasets lacking periodicity. We explain our findings through designing prompts to require LLMs to tell the period of the datasets. In addition, the input strategy is investigate…

4. Close Not relevant

   Time-LLM: Time Series Forecasting by Reprogramming Large Language Models

   Ming Jin, Shiyu Wang, Lintao Ma et al. · 2023 · Machine Learning · cited 1,324 times · AI summary available

   Abstract

   Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. Unlike natural language process (NLP) and computer vision (CV), where a single large model can tackle multiple tasks, models for time series forecasting are often specialized, necessitating distinct designs for different tasks and applications. While pre-trained foundation models have made impressive strides in NLP and CV, their development in time series domains has been constrained by data sparsity. Recent studies have revealed that large language models (LLMs) possess robust pattern recognition and reasoning abilities over complex sequences of tokens. However, the chal…

5. Close Not relevant

   Analysis and modeling to forecast in time series: a systematic review

   Fatoumata Dama, Christine Sinoquet · 2021 · Machine Learning · cited 42 times · AI summary available

   Abstract

   This paper surveys state-of-the-art methods and models dedicated to time series analysis and modeling, with the final aim of prediction. This review aims to offer a structured and comprehensive view of the full process flow, and encompasses time series decomposition, stationary tests, modeling and forecasting. Besides, to meet didactic purposes, a unified presentation has been adopted throughout this survey, to present decomposition frameworks on the one hand and linear and nonlinear time series models on the other hand. First, we decrypt the relationships between stationarity and linearity, and further examine the main classes of methods used to test for weak stationarity. Next, the main fr…

6. Close Cites this paper Not relevant

   Disentangled Parameter-Efficient Linear Model for Long-Term Time Series Forecasting

   Yuan Zhao, Tian-Yu Li, Jiadong Chen et al. · 2024 · International Conference on Database Systems for Advanced Applications · cited 4 times · Not summarized yet

   Abstract

   Long-term Time Series Forecasting (LTSF) is crucial across various domains, but complex deep models like Transformers are often prone to overfitting on extended sequences. Linear Fully Connected models have emerged as a powerful alternative, achieving competitive results with fewer parameters. However, their reliance on a single, monolithic weight matrix leads to quadratic parameter redundancy and an entanglement of temporal and frequential properties. To address this, we propose DiPE-Linear, a novel model that disentangles this monolithic mapping into a sequence of specialized, parameter-efficient modules. DiPE-Linear features three core components: Static Frequential Attention to prioritiz…

7. Close Not relevant

   Exploring Inter-Variate and Long-Term Dependencies to Boost Multivariate Time Series Forecasting

   Xi Ding, Yifan He, Shui-Geng Zhou et al. · 2025 · IEEE International Conference on Acoustics, Speech, and Signal Processing · cited 1 time · Not summarized yet

   Abstract

   Multivariate Time Series Forecasting (MTSF) is a critical task in various domains, and Large Language Models (LLMs) for MTSF have recently received considerable attention. Despite significant progress in large-scale time series models, particularly in fine-tuning pre-trained LLMs for MTSF, there are still limitations with existing works. First, multivariate time series (MTS) are often handled as multiple independent univariate inputs and processed separately across different variates, which neglects the dependencies between the variates. Second, most existing approaches employ Mean Squared Error (MSE) as loss function, which evaluates error at each time point separately, ignoring long-term d…

8. Close Not relevant

   Mixture-of-Linear-Experts for Long-term Time Series Forecasting

   Ronghao Ni, Zinan Lin, Shuaiqi Wang et al. · 2023 · International Conference on Artificial Intelligence and Statistics · cited 73 times · Not summarized yet

   Abstract

   Long-term time series forecasting (LTSF) aims to predict future values of a time series given the past values. The current state-of-the-art (SOTA) on this problem is attained in some cases by linear-centric models, which primarily feature a linear mapping layer. However, due to their inherent simplicity, they are not able to adapt their prediction rules to periodic changes in time series patterns. To address this challenge, we propose a Mixture-of-Experts-style augmentation for linear-centric models and propose Mixture-of-Linear-Experts (MoLE). Instead of training a single model, MoLE trains multiple linear-centric models (i.e., experts) and a router model that weighs and mixes their outputs…

Prior work it builds on

1. Close Used in depth by this paper A method it uses Not relevant

   Are Transformers Effective for Time Series Forecasting?

   Ailing Zeng, Muxi Chen, Lei Zhang et al. · 2022 · Artificial Intelligence · cited 5,141 times · AI summary available

   Abstract

   Recently, there has been a surge of Transformer-based solutions for the time series forecasting (TSF) task, especially for the challenging long-term TSF problem. Transformer architecture relies on self-attention mechanisms to effectively extract the semantic correlations between paired elements in a long sequence, which is permutation-invariant and anti-ordering to some extent. However, in time series modeling, we are to extract the temporal relations among an ordering set of continuous points. Consequently, whether Transformer-based techniques are the right solutions for long-term time series forecasting is an interesting problem to investigate, despite the performance improvements shown in…

2. Related Used in depth by this paper A method it uses Not relevant

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

   Haoyi Zhou, Shang-Hang Zhang, Jieqi Peng et al. · 2020 · AAAI Conference on Artificial Intelligence · cited 9,572 times · Not summarized yet

   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 tr…

3. Close Not relevant

   Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting-Full Version

   Razvan-Gabriel Cirstea, Chen-Juan Guo, B. Yang et al. · 2022 · International Joint Conference on Artificial Intelligence · cited 177 times · Not summarized yet

   Abstract

   A variety of real-world applications rely on far future information to make decisions, thus calling for efficient and accurate long sequence multivariate time series forecasting. While recent attention-based forecasting models show strong abilities in capturing long-term dependencies, they still suffer from two key limitations. First, canonical self attention has a quadratic complexity w.r.t. the input time series length, thus falling short in efficiency. Second, different variables’ time series often have distinct temporal dynamics, which existing studies fail to capture, as they use the same model parameter space, e.g., projection matrices, for all variables’ time series, thus falling shor…

4. Related Used in depth by this paper A method it uses Not relevant

   A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

   Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong et al. · 2022 · Machine Learning · cited 5,298 times · AI summary available

   Abstract

   We propose an efficient design of Transformer-based models for multivariate time series forecasting and self-supervised representation learning. It is based on two key components: (i) segmentation of time series into subseries-level patches which are served as input tokens to Transformer; (ii) channel-independence where each channel contains a single univariate time series that shares the same embedding and Transformer weights across all the series. Patching design naturally has three-fold benefit: local semantic information is retained in the embedding; computation and memory usage of the attention maps are quadratically reduced given the same look-back window; and the model can attend long…

5. Related Used in depth by this paper A method it uses Not relevant

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

   Haixu Wu, Jie-Hui Xu, Jian-Min Wang et al. · 2021 · Neural Information Processing Systems · cited 6,161 times · Not summarized yet

   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 architectu…

Papers that cite it

1. Close Not relevant

   FEDA: Fast Exponential Decay Approach for Multivariate Time Series Forecasting

   Ming-Ting Zhong, Cheng-Yu Sie, Che-Rung Lee · 2026 · Annual International Computer Software and Applications Conference · Not summarized yet

   Abstract

   Multivariate time series forecasting that uses past observations to predict future data has been widely used in various application. Numerous methods have been developed, including deep learning based approaches. One of the most successful models is Mamba, which is based the state space models (SSMs). However, Mamba and its variants still face the challenges of long training times owing to its nonlinear operations. In this paper, we proposed a Fast Exponential Decay Approach (FEDA) to improve the training efficiency of Mamba. We have observed that the hidden states in the model are linear combinations of past inputs. Therefore, we attempted to use a fully connected layer to generate all the …

2. Close Not relevant

   Is Channel Independent strategy optimal for Time Series Forecasting?

   Peiwen Yuan, Changsheng Zhu · 2023 · arXiv.org · preprint, not peer reviewed · cited 4 times · Not summarized yet

   Abstract

   There has been an emergence of various models for long-term time series forecasting. Recent studies have demonstrated that a single linear layer, using Channel Dependent (CD) or Channel Independent (CI) modeling, can even outperform a large number of sophisticated models. However, current research primarily considers CD and CI as two complementary yet mutually exclusive approaches, unable to harness these two extremes simultaneously. And it is also a challenging issue that both CD and CI are static strategies that cannot be determined to be optimal for a specific dataset without extensive experiments. In this paper, we reconsider whether the current CI strategy is the best solution for time …

3. Related Not relevant

   From Similarity to Superiority: Channel Clustering for Time Series Forecasting

   Jia-Lin Chen, J. Lenssen, Aosong Feng et al. · 2024 · Neural Information Processing Systems · cited 86 times · Not summarized yet

   Abstract

   Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while it leads to poor generalization on unseen instances and ignores potentially necessary interactions between channels. Conversely, the Channel-Dependent (CD) strategy mixes all channels with even irrelevant and indiscriminate information, which, however, results in oversmoothing issues and limits forecasting accuracy. There is a lack of channel strategy that effectively balances individual channel treatment for improved forecasting performance without overl…

4. Related Not relevant

   Multivariate Time Series Forecasting based on Time-Frequency Decomposition

   Ke-Han Li, Ying-Guang Hao, Hong-Yu Wang et al. · 2023 · 2023 3rd International Conference on Electronic Information Engineering and Computer Science (EIECS) · cited 1 time · Not summarized yet

   Abstract

   Multivariate time series forecasting is a current research hot spot in academic and industrial fields; however, it is still challenging to effectively mine the underlying patterns in multivariate time series data and achieve accurate long-term predictions. To cope with this problem, a model based on timefrequency decomposition is proposed. First, the multivariate time-series data are decomposed into different frequency components by using frequency domain decomposition methods, combined by their contributions in energy, and then the combined different components are reduced back to the time domain, and the multi-scale time windows are used to extract the global and local attention of differe…

5. Related Not relevant

   A Transformer Framework for Multi-Step Network Latency Prediction

   Yilin Wang, Dong-Dong Lin · 2025 · 2025 6th International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · Not summarized yet

   Abstract

   Accurate network latency prediction is essential for Ultra-Reliable and Low-Latency Communication (URLLC) in 5G networks, enabling mission-critical applications such as the Industrial Internet of Things (IIoT) and the Internet of Vehicles (IoV). Existing statistical and deep learning methods, including RNNs, LSTMs, and Transformer-based architectures, often struggle to capture the complex, non-linear dependencies in multivariate network data, while incurring high computational and memory costs. In this paper, we investigate the application of TimeXer to the specific task of network latency forecasting, and we propose a practical adaptation workflow for incorporating TimeXer into latency pred…