{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T20:37:34Z","timestamp":1776803854635,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62362069"],"award-info":[{"award-number":["62362069"]}]},{"name":"Yunnan Fundamental Research Projects","award":["202401BF070001-024"],"award-info":[{"award-number":["202401BF070001-024"]}]},{"name":"Open Project Program of Yunnan Key Laboratory of Intelligent Systems and Computing","award":["ISC24Y05"],"award-info":[{"award-number":["ISC24Y05"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780165","type":"proceedings-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:44:16Z","timestamp":1776800656000},"page":"1975-1986","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8248-9441","authenticated-orcid":false,"given":"Yiji","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0529-4642","authenticated-orcid":false,"given":"Zihao","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0310-5216","authenticated-orcid":false,"given":"Ao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6130-126X","authenticated-orcid":false,"given":"Haomin","family":"Wen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-4811","authenticated-orcid":false,"given":"Ming","family":"Jin","sequence":"additional","affiliation":[{"name":"Griffith University, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2817-7337","authenticated-orcid":false,"given":"Yuxuan","family":"Liang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0501-9363","authenticated-orcid":false,"given":"Huaiyu","family":"Wan","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3696-9281","authenticated-orcid":false,"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"17804","volume-title":"Lin (Eds.)","volume":"33","author":"Lina Yao LEI BAI","year":"2020","unstructured":"LEI BAI, Lina Yao, Can Li, Xianzhi Wang, and Can Wang. 2020. Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting. In Adv. Neural Inf. Process. Syst. (NeurIPS), H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. 17804-17815."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3554028"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25854"},{"key":"e_1_3_2_2_4_1","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR). 1-19","author":"Chen Peng","year":"2024","unstructured":"Peng Chen, Yingying Zhang, Yunyao Cheng, Yang Shu, Yihang Wang, Qingsong Wen, Bin Yang, and Chenjuan Guo. 2024. Pathformer: Multi-scale, Transformers with Adaptive Pathways for Time Series Forecasting. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-19."},{"key":"e_1_3_2_2_5_1","first-page":"1","article-title":"TSMixer: An All-MLP Architecture for Time Series Forecast-ing","volume":"2023","author":"Chen Si-An","year":"2023","unstructured":"Si-An Chen, Chun-Liang Li, Sercan \u00d6. Arik, Nathanael C. Yoder, and Tomas Pfister. 2023. TSMixer: An All-MLP Architecture for Time Series Forecast-ing. Trans. Mach. Learn. Res., Vol. 2023 (2023), 1-24.","journal-title":"Trans. Mach. Learn. Res."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1675"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25880"},{"key":"e_1_3_2_2_8_1","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML). 933-941","author":"Dauphin Yann N.","year":"2017","unstructured":"Yann N. Dauphin, Angela Fan, Michael Auli, and David Grangier. 2017. Language Modeling with Gated Convolutional Networks. In Proc. Int. Conf. Mach. Learn. (ICML). 933-941."},{"key":"e_1_3_2_2_9_1","article-title":"On the Nystr\u00f6m Method for Approximating a Gram Matrix for Improved Kernel-Based Learning","volume":"6","author":"Drineas Petros","year":"2005","unstructured":"Petros Drineas, Michael W Mahoney, and Nello Cristianini. 2005. On the Nystr\u00f6m Method for Approximating a Gram Matrix for Improved Kernel-Based Learning. J. Mach. Learn. Res., Vol. 6, 12 (2005).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02288367"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709177"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467430"},{"key":"e_1_3_2_2_13_1","volume-title":"Proc. Int. Joint Conf. Artif. Intell. (IJCAI). 3998-4006","author":"Gao Haotian","year":"2024","unstructured":"Haotian Gao, Renhe Jiang, Zheng Dong, Jinliang Deng, Yuxin Ma, and Xuan Song. 2024. Spatial-Temporal-Decoupled Masked Pre-Training for Spatiotemporal Forecasting. In Proc. Int. Joint Conf. Artif. Intell. (IJCAI). 3998-4006."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3056502"},{"key":"e_1_3_2_2_16_1","first-page":"124","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","volume":"15108","author":"Han Dongchen","year":"2024","unstructured":"Dongchen Han, Tianzhu Ye, Yizeng Han, Zhuofan Xia, Siyuan Pan, Pengfei Wan, Shiji Song, and Gao Huang. 2024a. Agent Attention: On, the Integration of Softmax and Linear Attention. In Proc. Eur. Conf. Comput. Vis. (ECCV), Vol. 15108. 124-140."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/3641204.3641217"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-3245-6_9"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00101"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3333824"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28707"},{"key":"e_1_3_2_2_23_1","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR). 1-19","author":"Lee Hyunwook","year":"2024","unstructured":"Hyunwook Lee and Sungahn Ko. 2024. TESTAM: A, Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-19."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16542"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615068"},{"key":"e_1_3_2_2_26_1","volume-title":"Traffic Forecasting. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-16","author":"Li Yaguang","year":"2018","unstructured":"Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2018. Diffusion Convolutional Recurrent Neural Network: Data-driven, Traffic Forecasting. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-16."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26676"},{"key":"e_1_3_2_2_28_1","first-page":"106315","article-title":"CycleNet: Enhancing, Time Series Forecasting through Modeling Periodic Patterns","volume":"37","author":"Lin Shengsheng","year":"2024","unstructured":"Shengsheng Lin, Weiwei Lin, Xinyi HU, Wentai Wu, Ruichao Mo, and Haocheng Zhong. 2024. CycleNet: Enhancing, Time Series Forecasting through Modeling Periodic Patterns. In Adv. Neural Inf. Process. Syst. (NeurIPS), Vol. 37. 106315-106345.","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615160"},{"key":"e_1_3_2_2_30_1","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR). 1-20","author":"Liu Shizhan","year":"2022","unstructured":"Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X. Liu, and Schahram Dustdar. 2022. Pyraformer: Low-complexity, Pyramidal Attention for Long-Range Time Series Modeling and Forecasting. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-20."},{"key":"e_1_3_2_2_31_1","volume-title":"Empowering","author":"Liu Xu","year":"2024","unstructured":"Xu Liu, Juncheng Liu, Gerald Woo, Taha Aksu, Yuxuan Liang, Roger Zimmermann, Chenghao Liu, Silvio Savarese, Caiming Xiong, and Doyen Sahoo. 2024b. Moirai-MoE: Empowering, Time Series Foundation Models with Sparse Mixture of Experts. arXiv preprint arXiv:2410.10469 (2024). arXiv:2410.10469"},{"key":"e_1_3_2_2_32_1","first-page":"75354","article-title":"LargeST: A, Benchmark Dataset for Large-Scale Traffic Forecasting","volume":"36","author":"Liu Xu","year":"2023","unstructured":"Xu Liu, Yutong Xia, Yuxuan Liang, Junfeng Hu, Yiwei Wang, Lei Bai, Chao Huang, Zhenguang Liu, Bryan Hooi, and Roger Zimmermann. 2023b. LargeST: A, Benchmark Dataset for Large-Scale Traffic Forecasting. In Adv. Neural Inf. Process. Syst. (NeurIPS), Vol. 36. 75354-75371.","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"e_1_3_2_2_33_1","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR). 1-25","author":"Liu Yong","year":"2024","unstructured":"Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu Wang, Lintao Ma, and Mingsheng Long. 2024a. iTransformer: Inverted, Transformers Are Effective for Time Series Forecasting. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-25."},{"key":"e_1_3_2_2_34_1","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR). 1-24","author":"Nie Yuqi","year":"2023","unstructured":"Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2023. A Time Series Is Worth 64 Words: Long-term, Forecasting with Transformers. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-24."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3257759"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3484454"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557702"},{"key":"e_1_3_2_2_38_1","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR). 1-19","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc V. Le, Geoffrey E. Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The, Sparsely-Gated Mixture-of-Experts Layer. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-19."},{"key":"e_1_3_2_2_39_1","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR). 1-33","author":"Shi Xiaoming","year":"2025","unstructured":"Xiaoming Shi, Shiyu Wang, Yuqi Nie, Dianqi Li, Zhou Ye, Qingsong Wen, and Ming Jin. 2025. Time-MoE: Billion-scale, Time Series Foundation Models with Mixture of Experts. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-33."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5438"},{"key":"e_1_3_2_2_41_1","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR). 1-27","author":"Wang Shiyu","year":"2024","unstructured":"Shiyu Wang, Haixu Wu, Xiaoming Shi, Tengge Hu, Huakun Luo, Lintao Ma, James Y. Zhang, and Jun Zhou. 2024. TimeMixer: Decomposable, Multiscale Mixing for Time Series Forecasting. In Proc. Int. Conf. Learn. Represent. (ICLR). 1-27."},{"key":"e_1_3_2_2_42_1","first-page":"1","article-title":"Using the Nystr\u00f6m method to speed up kernel machines","volume":"13","author":"Williams Christopher","year":"2000","unstructured":"Christopher Williams and Matthias Seeger. 2000. Using the Nystr\u00f6m method to speed up kernel machines. In Adv. Neural Inf. Process. Syst. (NeurIPS), Vol. 13. 1-7.","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403118"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/264"},{"key":"e_1_3_2_2_45_1","volume-title":"Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. (KDD). 3919-3930","author":"Michael Yeh Chin-Chia","year":"2024","unstructured":"Chin-Chia Michael Yeh, Yujie Fan, Xin Dai, Uday Singh Saini, Vivian Lai, Prince Osei Aboagye, Junpeng Wang, Huiyuan Chen, Yan Zheng, Zhongfang Zhuang, Liang Wang, and Wei Zhang. 2024. RPMixer: Shaking, up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data. In Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. (KDD). 3919-3930."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_3_2_2_48_1","first-page":"12360","article-title":"Root Mean Square Layer Normalization","author":"Zhang Biao","year":"2019","unstructured":"Biao Zhang and Rico Sennrich. 2019. Root Mean Square Layer Normalization. In Adv. Neural Inf. Process. Syst. (NeurIPS). 12360-12371.","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3220089"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5477"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_2_52_1","first-page":"7103","article-title":"Mixture-of-Experts with Expert Choice Routing","volume":"35","author":"Zhou Yanqi","year":"2022","unstructured":"Yanqi Zhou, Tao Lei, Hanxiao Liu, Nan Du, Yanping Huang, Vincent Y. Zhao, Andrew M. Dai, Zhifeng Chen, Quoc V. Le, and James Laudon. 2022. Mixture-of-Experts with Expert Choice Routing. In Adv. Neural Inf. Process. Syst. (NeurIPS), Vol. 35. 7103-7114.","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:44:23Z","timestamp":1776800663000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":52,"alternative-id":["10.1145\/3770854.3780165","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780165","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}