{"ID":2843494,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.08396","arxiv_id":"2511.08396","title":"EMAformer: Enhancing Transformer through Embedding Armor for Time Series Forecasting","abstract":"Multivariate time series forecasting is crucial across a wide range of domains. While presenting notable progress for the Transformer architecture, iTransformer still lags behind the latest MLP-based models. We attribute this performance gap to unstable inter-channel relationships. To bridge this gap, we propose EMAformer, a simple yet effective model that enhances the Transformer with an auxiliary embedding suite, akin to armor that reinforces its ability. By introducing three key inductive biases, i.e., \\textit{global stability}, \\textit{phase sensitivity}, and \\textit{cross-axis specificity}, EMAformer unlocks the further potential of the Transformer architecture, achieving state-of-the-art performance on 12 real-world benchmarks and reducing forecasting errors by an average of 2.73\\% in MSE and 5.15\\% in MAE. This significantly advances the practical applicability of Transformer-based approaches for multivariate time series forecasting. The code is available on https://github.com/PlanckChang/EMAformer.","short_abstract":"Multivariate time series forecasting is crucial across a wide range of domains. While presenting notable progress for the Transformer architecture, iTransformer still lags behind the latest MLP-based models. We attribute this performance gap to unstable inter-channel relationships. To bridge this gap, we propose EMAfor...","url_abs":"https://arxiv.org/abs/2511.08396","url_pdf":"https://arxiv.org/pdf/2511.08396v1","authors":"[\"Zhiwei Zhang\",\"Xinyi Du\",\"Xuanchi Guo\",\"Weihao Wang\",\"Wenjuan Han\"]","published":"2025-11-11T16:12:44Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":607220,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2843494,"paper_url":"https://arxiv.org/abs/2511.08396","paper_title":"EMAformer: Enhancing Transformer through Embedding Armor for Time Series Forecasting","repo_url":"https://github.com/PlanckChang/EMAformer","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}