{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T02:39:54Z","timestamp":1783564794835,"version":"3.55.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p>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\n\ncapturing 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\u2019 time series often have\n\ndistinct temporal dynamics, which existing studies fail to capture, as they use the same model parameter space, e.g., projection matrices, for all variables\u2019 time series, thus falling short in accuracy. To ensure high efficiency and accuracy, we propose Triformer, a triangular, variable-specific attention. (i) Linear complexity: we introduce a novel patch attention with linear complexity. When stacking multiple layers of the patch attentions, a triangular structure is proposed such that the\n\nlayer sizes shrink exponentially, thus maintaining linear complexity. (ii) Variable-specific parameters: we propose a light-weight method to enable distinct sets of model parameters for different variables\u2019 time series to enhance accuracy\n\nwithout compromising efficiency and memory usage. Strong empirical evidence on four datasets from multiple domains justifies our design choices, and it demonstrates that Triformer outperforms state-of-the-art methods w.r.t. both accuracy and\n\nefficiency. Source code is publicly available at https:\/\/github.com\/razvanc92\/triformer.<\/jats:p>","DOI":"10.24963\/ijcai.2022\/277","type":"proceedings-article","created":{"date-parts":[[2022,7,16]],"date-time":"2022-07-16T02:55:56Z","timestamp":1657940156000},"page":"1994-2001","source":"Crossref","is-referenced-by-count":105,"title":["Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting"],"prefix":"10.24963","author":[{"given":"Razvan-Gabriel","family":"Cirstea","sequence":"first","affiliation":[{"name":"Aalborg University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenjuan","family":"Guo","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Yang","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tung","family":"Kieu","sequence":"additional","affiliation":[{"name":"Aalborg University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanyi","family":"Dong","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[{"name":"Monash University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}","theme":"Artificial Intelligence","location":"Vienna, Austria","acronym":"IJCAI-2022","number":"31","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2022,7,23]]},"end":{"date-parts":[[2022,7,29]]}},"container-title":["Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:08:45Z","timestamp":1658142525000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2022\/277"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2022\/277","relation":{},"subject":[],"published":{"date-parts":[[2022,7]]}}}