The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting
Open accessAbstract
Transformers have gained popularity in time series forecasting for their ability to capture long-sequence interactions. However, their memory and compute-intensive requirements pose a critical bottleneck for long-term forecasting, despite numerous advancements in compute-aware self-attention modules. To address this, we propose TSMixer, a lightweight neural architecture exclusively composed of multi-layer perceptron (MLP) modules. TSMixer is designed for multivariate forecasting and representation learning on patched time series, providing an efficient alternative to Transformers. Our model draws inspiration from the success of MLP-Mixer models in computer vision. We demonstrate the challenges involved in adapting Vision MLP-Mixer for time series and introduce empirically validated components to enhance accuracy. This includes a novel design paradigm of attaching online reconciliation heads to the MLP-Mixer backbone, for explicitly modeling the time-series properties such as hierarchy and channel-correlations. We also propose a Hybrid channel modeling approach to effectively handle noisy channel interactions and generalization across diverse datasets, a common challenge in existing patch channel-mixing methods. Additionally, a simple gated attention mechanism is introduced in the backbone to prioritize important features. By incorporating these lightweight components, we significantly enhance the learning capability of simple MLP structures, outperforming complex Transformer models with minimal computing usage. Moreover, TSMixer's modular design enables compatibility with both supervised and masked self-supervised learning methods, making it a promising building block for time-series Foundation Models. TSMixer outperforms state-of-the-art MLP and Transformer models in forecasting by a considerable margin of 8-60%. It also outperforms the latest strong benchmarks of Patch-Transformer models (by 1-2%) with a significant reduction in memory and runtime (2-3X).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17325 · Cited by 7,752
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242 · cited 4×
“We categorize SOTA forecasting benchmarks into the following categories: (i) Standard Transformers: FEDformer [38], Autoformer[30] and Informer [37], (ii) Patch Transformers: PatchTST [22] and CrossFormer [3], (iii) MLPs and Non-Transformers: DLinear [34], LightTS [36] and S4 [12], (iv) Self-supervised models: BTSF [3…”
MethodInfluentialForecasting principles and practice
Hyndman, R. J., & Athanasopoulos, G. (2018) · Cited by 4,405
Are Transformers Effective for Time Series Forecasting?
Zeng, A., Chen, M., Zhang, L., & Xu, Q. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i9.26317 · Cited by 3,320
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
MLP-Mixer: An all-MLP Architecture for Vision
Tolstikhin, I., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2105.01601 · Cited by 2,087
BEiT: BERT Pre-Training of Image Transformers
Bao, H., Dong, L., Piao, S., & Wei, F. (2021) · arXiv · doi:10.48550/arxiv.2106.08254 · Cited by 1,392
Morgan, M. C. (2025) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.17575540 · Cited by 1,283
TS2Vec: Towards Universal Representation of Time Series
Yue, Z., Wang, Y., Duan, J., Yang, T., Huang, C., Tong, Y., & Xu, B. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20881 · Cited by 850
ResMLP: Feedforward networks for image classification with data-efficient training
Touvron, H., Bojanowski, P., Caron, M., Cord, M., El-Nouby, A., Grave, E., Izacard, G., Joulin, A., Synnaeve, G., Verbeek, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2105.03404 · Cited by 807
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training
Touvron, H., Bojanowski, P., Caron, M., Cord, M., El-Nouby, A., Grave, E., Izacard, G., Joulin, A., Synnaeve, G., Verbeek, J., et al. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3206148 · Cited by 807
Efficiently Modeling Long Sequences with Structured State Spaces
Gu, A., Goel, K., & Ré, C. (2021) · arXiv · doi:10.48550/arxiv.2111.00396 · Cited by 805
Time-Series Representation Learning via Temporal and Contextual Contrasting
Eldele, E., Ragab, M., Chen, Z., Wu, M., Kwoh, C. K., Li, X., & Guan, C. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/324 · Cited by 696
M5 accuracy competition: Results, findings, and conclusions
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2021.11.013 · Cited by 554
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
Nie, Y., Nguyen, N. H., Sinthong, P., & Kalagnanam, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.14730 · Cited by 548
Self-citationFEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., & Jin, R. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.12740 · Cited by 533
Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP StructuresPreprint
Zhang, T., Zhang, Y., Cao, W., Bian, J., Yi, X., Zheng, S., & Li, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.01186 · Cited by 473
Al-Musaylh, M. S., Deo, R. C., Adamowski, J. F., & Li, Y. (2018) · Advanced Engineering Informatics · doi:10.1016/j.aei.2017.11.002 · Cited by 300
An Image Patch is a Wave: Phase-Aware Vision MLP
Tang, Y., Han, K., Guo, J., Xu, C., Li, Y., Xu, C., & Wang, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01066 · Cited by 216
Unsupervised representation learning for time series with temporal neighborhood coding
Tonekaboni, S., Eytan, D., & Goldenberg, A. (2021) · arXiv · doi:10.48550/arxiv.2106.00750 · Cited by 170
Hire-MLP: Vision MLP via Hierarchical Rearrangement
Guo, J., Tang, Y., Han, K., Chen, X., Wu, H., Xu, C., Xu, C., & Wang, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00090 · Cited by 156
CycleMLP: A MLP-like Architecture for Dense PredictionPreprint
Chen, S., Xie, E., Ge, C., Chen, R., Liang, D., & Luo, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10224 · Cited by 128
Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral FusionPreprint
Yang, L. Q., & Hong, S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2202.04770 · Cited by 99
MLP4Rec: A Pure MLP Architecture for Sequential Recommendations
Li, M., Zhao, X., Lyu, C., Zhao, M., Wu, R., & Guo, R. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/297 · Cited by 75
A Novel Encoder-Decoder Model for Multivariate Time Series Forecasting
Zhang, H., Li, S., Chen, Y., Dai, J., & Yi, Y. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/5596676 · Cited by 40
S$^2$-MLP: Spatial-Shift MLP Architecture for VisionPreprint
Yu, T., Xu, L., Cai, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.07477 · Cited by 29
Cited by
Kim, J., Kim, H., Kim, H., Lee, D., & Yoon, S. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11223-9 · Cited by 263
Wang, F., Jiang, Y., Zhang, R., Wei, A., Xie, J., & Pang, X. (2025) · Sensors · doi:10.3390/s25010190 · Cited by 119
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
Cao, D., Jia, F., Arik, S. O., Pfister, T., Zheng, Y., Ye, W., & Liu, Y. (2023) · arXiv · doi:10.48550/arxiv.2310.04948 · Cited by 59
TSLA: A Multi-Task Time Series Language Model
Fang, L., Chen, Y., Yu, W., Liu, Y., Tang, L.-A., Torvik, V. I., & Chen, H. (2025) · ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49660.2025.10888390
Metadata
- Authors
- Ekambaram, V., Jati, A., Nguyen, N., Sinthong, P., & Kalagnanam, J.
- Venue
- Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2023-08-04
- Pages
- 459-469
- OpenAlex
- W4381245607
- Cited by
- 278
- References
- 31
- FWCI
- 61.49
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.