{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T08:00:20Z","timestamp":1773388820143,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["No. 62337001"],"award-info":[{"award-number":["No. 62337001"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["No.92367110"],"award-info":[{"award-number":["No.92367110"]}]},{"name":"the grants of Provincial Natural Science Foundation of Anhui Province","award":["No. 2408085QF193"],"award-info":[{"award-number":["No. 2408085QF193"]}]},{"name":"the Fundamental Research Funds for the Central Universities of China","award":["No. PA2024GDSK0112"],"award-info":[{"award-number":["No. PA2024GDSK0112"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,10]]},"DOI":"10.1145\/3701551.3703498","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:30:16Z","timestamp":1740573016000},"page":"175-183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Cross-Domain Pre-training with Language Models for Transferable Time Series Representations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9873-7681","authenticated-orcid":false,"given":"Mingyue","family":"Cheng","sequence":"first","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0634-6254","authenticated-orcid":false,"given":"Xiaoyu","family":"Tao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-5550","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0877-2681","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7166-1179","authenticated-orcid":false,"given":"Yiheng","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3507-9607","authenticated-orcid":false,"given":"Defu","family":"Lian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"}]}],"member":"320","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.2307\/2985674"},{"key":"e_1_3_2_1_2_1","volume-title":"Tempo: Prompt-based generative pre-trained transformer for time series forecasting. arXiv preprint arXiv:2310.04948","author":"Cao Defu","year":"2023","unstructured":"Defu Cao, Furong Jia, Sercan O Arik, Tomas Pfister, Yixiang Zheng, Wen Ye, and Yan Liu. 2023. Tempo: Prompt-based generative pre-trained transformer for time series forecasting. arXiv preprint arXiv:2310.04948 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification. arXiv preprint arXiv:2302.09818","author":"Cheng Mingyue","year":"2023","unstructured":"Mingyue Cheng, Qi Liu, Zhiding Liu, Zhi Li, Yucong Luo, and Enhong Chen. 2023a. FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification. arXiv preprint arXiv:2302.09818 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Timemae: Self-supervised representations of time series with decoupled masked autoencoders. arXiv preprint arXiv:2303.00320","author":"Cheng Mingyue","year":"2023","unstructured":"Mingyue Cheng, Qi Liu, Zhiding Liu, Hao Zhang, Rujiao Zhang, and Enhong Chen. 2023b. Timemae: Self-supervised representations of time series with decoupled masked autoencoders. arXiv preprint arXiv:2303.00320 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis. arXiv preprint arXiv:2403.01493","author":"Cheng Mingyue","year":"2024","unstructured":"Mingyue Cheng, Jiqian Yang, Tingyue Pan, Qi Liu, and Zhi Li. 2024. ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis. arXiv preprint arXiv:2403.01493 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_1_7_1","volume-title":"The human infant brain: A neural architecture able to learn language. Psychonomic bulletin & review","author":"Dehaene-Lambertz Ghislaine","year":"2017","unstructured":"Ghislaine Dehaene-Lambertz. 2017. The human infant brain: A neural architecture able to learn language. Psychonomic bulletin & review, Vol. 24 (2017), 48--55."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.02.030"},{"key":"e_1_3_2_1_9_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454226"},{"key":"e_1_3_2_1_11_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Dong Jiaxiang","year":"2024","unstructured":"Jiaxiang Dong, Haixu Wu, Haoran Zhang, Li Zhang, Jianmin Wang, and Mingsheng Long. 2024. Simmtm: A simple pre-training framework for masked time-series modeling. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Xiaoli Li, and Cuntai Guan.","author":"Eldele Emadeldeen","year":"2021","unstructured":"Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, Xiaoli Li, and Cuntai Guan. 2021. Time-series representation learning via temporal and contextual contrasting. arXiv preprint arXiv:2106.14112 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3586589.3586709"},{"key":"e_1_3_2_1_14_1","volume-title":"Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights. arXiv preprint arXiv:2305.15036","author":"Fu Junchen","year":"2023","unstructured":"Junchen Fu, Fajie Yuan, Yu Song, Zheng Yuan, Mingyue Cheng, Shenghui Cheng, Jiaqi Zhang, Jie Wang, and Yunzhu Pan. 2023. Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights. arXiv preprint arXiv:2305.15036 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"arXiv preprint arXiv:2310.03589","author":"Garza Azul","year":"2023","unstructured":"Azul Garza and Max Mergenthaler-Canseco. 2023. TimeGPT-1. arXiv preprint arXiv:2310.03589 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Moment: A family of open time-series foundation models. arXiv preprint arXiv:2402.03885","author":"Goswami Mononito","year":"2024","unstructured":"Mononito Goswami, Konrad Szafer, Arjun Choudhry, Yifu Cai, Shuo Li, and Artur Dubrawski. 2024. Moment: A family of open time-series foundation models. arXiv preprint arXiv:2402.03885 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting. arXiv preprint arXiv:2304.05206","author":"Han Lu","year":"2023","unstructured":"Lu Han, Han-Jia Ye, and De-Chuan Zhan. 2023. The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting. arXiv preprint arXiv:2304.05206 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_19_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_20_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability. arXiv preprint arXiv:2103.07162","author":"Kao Wei-Tsung","year":"2021","unstructured":"Wei-Tsung Kao and Hung-yi Lee. 2021. Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability. arXiv preprint arXiv:2103.07162 (2021)."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00604"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.48.1752"},{"key":"e_1_3_2_1_25_1","volume-title":"Experiencing SAX: a novel symbolic representation of time series. Data Mining and knowledge discovery","author":"Lin Jessica","year":"2007","unstructured":"Jessica Lin, Eamonn Keogh, Li Wei, and Stefano Lonardi. 2007. Experiencing SAX: a novel symbolic representation of time series. Data Mining and knowledge discovery, Vol. 15 (2007), 107--144."},{"key":"e_1_3_2_1_26_1","volume-title":"Gated transformer networks for multivariate time series classification. arXiv preprint arXiv:2103.14438","author":"Liu Minghao","year":"2021","unstructured":"Minghao Liu, Shengqi Ren, Siyuan Ma, Jiahui Jiao, Yizhou Chen, Zhiguang Wang, and Wei Song. 2021. Gated transformer networks for multivariate time series classification. arXiv preprint arXiv:2103.14438 (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Liu Zhiding","year":"2024","unstructured":"Zhiding Liu, Mingyue Cheng, Zhi Li, Zhenya Huang, Qi Liu, Yanhu Xie, and Enhong Chen. 2024a. Adaptive normalization for non-stationary time series forecasting: A temporal slice perspective. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Generative Pretrained Hierarchical Transformer for Time Series Forecasting. arXiv preprint arXiv:2402.16516","author":"Liu Zhiding","year":"2024","unstructured":"Zhiding Liu, Jiqian Yang, Mingyue Cheng, Yucong Luo, and Zhi Li. 2024b. Generative Pretrained Hierarchical Transformer for Time Series Forecasting. arXiv preprint arXiv:2402.16516 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Bake off redux: a review and experimental evaluation of recent time series classification algorithms. arXiv preprint arXiv:2304.13029","author":"Middlehurst Matthew","year":"2023","unstructured":"Matthew Middlehurst, Patrick Sch\u00e4fer, and Anthony Bagnall. 2023. Bake off redux: a review and experimental evaluation of recent time series classification algorithms. arXiv preprint arXiv:2304.13029 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499","author":"van den Oord Aaron","year":"2016","unstructured":"Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. 2016. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)."},{"key":"e_1_3_2_1_31_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_32_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0377-7"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2247596.2247656"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00679-8"},{"key":"e_1_3_2_1_37_1","volume-title":"Self-supervised transformer for sparse and irregularly sampled multivariate clinical time-series. ACM Transactions on Knowledge Discovery from Data (TKDD)","author":"Tipirneni Sindhu","year":"2022","unstructured":"Sindhu Tipirneni and Chandan K Reddy. 2022. Self-supervised transformer for sparse and irregularly sampled multivariate clinical time-series. ACM Transactions on Knowledge Discovery from Data (TKDD), Vol. 16, 6 (2022), 1--17."},{"key":"e_1_3_2_1_38_1","volume-title":"Unsupervised representation learning for time series with temporal neighborhood coding. arXiv preprint arXiv:2106.00750","author":"Tonekaboni Sana","year":"2021","unstructured":"Sana Tonekaboni, Danny Eytan, and Anna Goldenberg. 2021. Unsupervised representation learning for time series with temporal neighborhood coding. arXiv preprint arXiv:2106.00750 (2021)."},{"key":"e_1_3_2_1_39_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems Vol. 30 (2017)."},{"key":"e_1_3_2_1_40_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"Transformers in time series: A survey. arXiv preprint arXiv:2202.07125","author":"Wen Qingsong","year":"2022","unstructured":"Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, and Liang Sun. 2022. Transformers in time series: A survey. arXiv preprint arXiv:2202.07125 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Unified training of universal time series forecasting transformers. arXiv preprint arXiv:2402.02592","author":"Woo Gerald","year":"2024","unstructured":"Gerald Woo, Chenghao Liu, Akshat Kumar, Caiming Xiong, Silvio Savarese, and Doyen Sahoo. 2024. Unified training of universal time series forecasting transformers. arXiv preprint arXiv:2402.02592 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Cost: Contrastive learning of disentangled seasonal-trend representations for time series forecasting. arXiv preprint arXiv:2202.01575","author":"Woo Gerald","year":"2022","unstructured":"Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, and Steven Hoi. 2022. Cost: Contrastive learning of disentangled seasonal-trend representations for time series forecasting. arXiv preprint arXiv:2202.01575 (2022)."},{"key":"e_1_3_2_1_44_1","volume-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in neural information processing systems","author":"Wu Haixu","year":"2021","unstructured":"Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in neural information processing systems, Vol. 34 (2021), 22419--22430."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557122"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467401"},{"key":"e_1_3_2_1_48_1","unstructured":"Kexin Zhang Qingsong Wen Chaoli Zhang Rongyao Cai Ming Jin Yong Liu James Zhang Yuxuan Liang Guansong Pang Dongjin Song et al. 2023. Self-Supervised Learning for Time Series Analysis: Taxonomy Progress and Prospects. arXiv preprint arXiv:2306.10125 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08010-9_33"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"}],"event":{"name":"WSDM '25: The Eighteenth ACM International Conference on Web Search and Data Mining","location":"Hannover Germany","acronym":"WSDM '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703498","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701551.3703498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:06:01Z","timestamp":1755767161000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":50,"alternative-id":["10.1145\/3701551.3703498","10.1145\/3701551"],"URL":"https:\/\/doi.org\/10.1145\/3701551.3703498","relation":{},"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"2025-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}