{"type":"ScholarlyArticle","title":"CASA: CNN Autoencoder-based Score Attention for Efficient Multivariate Long-term Time-series Forecasting","authors":[{"name":"Minhyuk Lee","slug":"minhyuk-lee","given":"Minhyuk","family":"Lee","affiliation":""},{"name":"Hyekyung Yoon","slug":"hyekyung-yoon","given":"Hyekyung","family":"Yoon","affiliation":""},{"name":"MyungJoo Kang","slug":"myungjoo-kang","given":"MyungJoo","family":"Kang","affiliation":""}],"abstract":"Multivariate long-term time series forecasting is critical for applications such as weather prediction, and traffic analysis. In addition, the implementation of Transformer variants has improved prediction accuracy. Following these variants, different input data process approaches also enhanced the field, such as tokenization techniques including point-wise, channel-wise, and patch-wise tokenization. However, previous studies still have limitations in time complexity, computational resources, and cross-dimensional interactions. To address these limitations, we introduce a novel CNN Autoencoder-based Score Attention mechanism (CASA), which can be introduced in diverse Transformers model-agnosticically by reducing memory and leading to improvement in model performance. Experiments on eight real-world datasets validate that CASA decreases computational resources by up to 77.7%, accelerates inference by 44.0%, and achieves state-of-the-art performance, ranking first in 87.5% of evaluated metrics. Our code is available at https://github.com/lmh9507/CASA.","doi":"10.24963/ijcai.2025/619","url":"https://ijcai.org/proceedings/2025/619","pdf":"https://ijcai.org/proceedings/2025/0619.pdf","markdown":"https://ijcai.org/proceedings/2025/619.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/619","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":619,"pages":{"first":5563,"last":5570},"keywords":["Machine Learning: ML: Deep learning architectures","Machine Learning: ML: Convolutional networks","Machine Learning: ML: Time series and data streams"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}