{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T08:01:02Z","timestamp":1786089662738,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737123","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:04:26Z","timestamp":1754255066000},"page":"2269-2280","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Semantics-Aware Patch Encoding and Hierarchical Dependency Modeling for Long-Term Time Series Forecasting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9639-0397","authenticated-orcid":false,"given":"Sijia","family":"Peng","sequence":"first","affiliation":[{"name":"Shanghai Key Lab of Data Science, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8575-5415","authenticated-orcid":false,"given":"Yun","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Data Science, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6258-0747","authenticated-orcid":false,"given":"Yangyong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Key Lab of Data Science, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China and Shanghai Data Research Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4560-5092","authenticated-orcid":false,"given":"Zhiqiang","family":"Shen","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Forecasting daily meteorological time series using arima and regression models,'' International agrophysics","author":"Murat M.","unstructured":"M. Murat, I. Malinowska, M. Gos, and J. Krzyszczak, ''Forecasting daily meteorological time series using arima and regression models,'' International agrophysics, vol. 32, no. 2, 2018."},{"key":"e_1_3_2_2_2_1","unstructured":"S. Scher ''Artificial intelligence in weather and climate prediction: Learning atmospheric dynamics '' Ph.D. dissertation Department of Meteorology Stockholm University 2020."},{"key":"e_1_3_2_2_3_1","volume-title":"Materials & Continua","author":"Haq M. A.","unstructured":"M. A. Haq, ''Cdlstm: A novel model for climate change forecasting.'' Computers, Materials & Continua, vol. 71, no. 2, 2022."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3632775.3662161"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106181"},{"key":"e_1_3_2_2_6_1","volume-title":"Financial time-series forecasting: Towards synergizing performance and interpretability within a hybrid machine learning approach,'' arXiv preprint arXiv:2401.00534","author":"Liu S.","year":"2023","unstructured":"S. Liu, K. Wu, C. Jiang, B. Huang, and D. Ma, ''Financial time-series forecasting: Towards synergizing performance and interpretability within a hybrid machine learning approach,'' arXiv preprint arXiv:2401.00534, 2023."},{"key":"e_1_3_2_2_7_1","volume-title":"Supervised autoencoder mlp for financial time series forecasting,'' arXiv preprint arXiv:2404.01866","author":"Bieganowski B.","year":"2024","unstructured":"B. Bieganowski and R. Slepaczuk, ''Supervised autoencoder mlp for financial time series forecasting,'' arXiv preprint arXiv:2404.01866, 2024."},{"key":"e_1_3_2_2_8_1","volume-title":"Comparative analysis of time series forecasting approaches for household electricity consumption prediction,'' arXiv preprint arXiv:2207.01019","author":"Bilal M.","year":"2022","unstructured":"M. Bilal, H. Kim, M. Fayaz, and P. Pawar, ''Comparative analysis of time series forecasting approaches for household electricity consumption prediction,'' arXiv preprint arXiv:2207.01019, 2022."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2023.03.042"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2022.100360"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3268199"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3489496.3489503"},{"key":"e_1_3_2_2_13_1","first-page":"3202","article-title":"Bridging self-attention and time series decomposition for periodic forecasting","author":"Jiang S.","year":"2022","unstructured":"S. Jiang, T. Syed, X. Zhu, J. Levy, B. Aronchik, and Y. Sun, ''Bridging self-attention and time series decomposition for periodic forecasting,'' in Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022, pp. 3202-3211.","journal-title":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management"},{"key":"e_1_3_2_2_14_1","volume-title":"Condconv: Conditionally parameterized convolutions for efficient inference,'' Advances in neural information processing systems","author":"Yang B.","year":"2019","unstructured":"B. Yang, G. Bender, Q. V. Le, and J. Ngiam, ''Condconv: Conditionally parameterized convolutions for efficient inference,'' Advances in neural information processing systems, vol. 32, 2019."},{"key":"e_1_3_2_2_15_1","first-page":"11","article-title":"Dynamic convolution: Attention over convolution kernels","author":"Chen Y.","year":"2020","unstructured":"Y. Chen, X. Dai, M. Liu, D. Chen, L. Yuan, and Z. Liu, ''Dynamic convolution: Attention over convolution kernels,'' in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2020, pp. 11,030-11,039.","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"e_1_3_2_2_16_1","volume-title":"A time series is worth 64 words: Long-term forecasting with transformers,'' in International Conference on Learning Representations","author":"Nie Y.","year":"2023","unstructured":"Y. Nie, N. H. Nguyen, P. Sinthong, and J. Kalagnanam, ''A time series is worth 64 words: Long-term forecasting with transformers,'' in International Conference on Learning Representations, 2023."},{"key":"e_1_3_2_2_17_1","volume-title":"Multi-scale transformers with adaptive pathways for time series forecasting,'' in International Conference on Learning Representations","author":"Chen P.","year":"2024","unstructured":"P. Chen, Y. Zhang, Y. Cheng, Y. Shu, Y. Wang, Q. Wen, B. Yang, and C. Guo, ''Multi-scale transformers with adaptive pathways for time series forecasting,'' in International Conference on Learning Representations, 2024."},{"key":"e_1_3_2_2_18_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces,'' arXiv preprint arXiv:2312.00752","author":"Gu A.","year":"2023","unstructured":"A. Gu and T. Dao, ''Mamba: Linear-time sequence modeling with selective state spaces,'' arXiv preprint arXiv:2312.00752, 2023."},{"key":"e_1_3_2_2_19_1","volume-title":"Is mamba effective for time series forecasting?'' arXiv preprint arXiv:2403.11144","author":"Wang Z.","year":"2024","unstructured":"Z. Wang, F. Kong, S. Feng, M. Wang, H. Zhao, D. Wang, and Y. Zhang, ''Is mamba effective for time series forecasting?'' arXiv preprint arXiv:2403.11144, 2024."},{"key":"e_1_3_2_2_20_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer,'' arXiv preprint arXiv:1701.06538","author":"Shazeer N.","year":"2017","unstructured":"N. Shazeer, A. Mirhoseini, K. Maziarz, A. Davis, Q. Le, G. Hinton, and J. Dean, ''Outrageously large neural networks: The sparsely-gated mixture-of-experts layer,'' arXiv preprint arXiv:1701.06538, 2017."},{"key":"e_1_3_2_2_21_1","volume-title":"ModernTCN: A modern pure convolution structure for general time series analysis,'' in International Conference on Learning Representations","author":"Donghao L.","year":"2024","unstructured":"L. Donghao and W. Xue, ''ModernTCN: A modern pure convolution structure for general time series analysis,'' in International Conference on Learning Representations, 2024."},{"key":"e_1_3_2_2_22_1","volume-title":"Integrating mamba and transformer for long-short range time series forecasting,'' arXiv preprint arXiv:2404.14757","author":"Xu X.","year":"2024","unstructured":"X. Xu, Y. Liang, B. Huang, Z. Lan, and K. Shu, ''Integrating mamba and transformer for long-short range time series forecasting,'' arXiv preprint arXiv:2404.14757, 2024."},{"key":"e_1_3_2_2_23_1","first-page":"95","volume-title":"Modeling long-and short-term temporal patterns with deep neural networks,'' in The 41st international ACM SIGIR conference on research & development in information retrieval","author":"Lai G.","year":"2018","unstructured":"G. Lai, W.-C. Chang, Y. Yang, and H. Liu, ''Modeling long-and short-term temporal patterns with deep neural networks,'' in The 41st international ACM SIGIR conference on research & development in information retrieval, 2018, pp. 95-104."},{"key":"e_1_3_2_2_24_1","volume-title":"Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting,'' Advances in neural information processing systems","author":"Li S.","year":"2019","unstructured":"S. Li, X. Jin, Y. Xuan, X. Zhou, W. Chen, Y.-X. Wang, and X. Yan, ''Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting,'' Advances in neural information processing systems, vol. 32, 2019."},{"key":"e_1_3_2_2_25_1","volume-title":"Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting,'' in The eleventh international conference on learning representations","author":"Zhang Y.","year":"2023","unstructured":"Y. Zhang and J. Yan, ''Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting,'' in The eleventh international conference on learning representations, 2023."},{"key":"e_1_3_2_2_26_1","volume-title":"Pathformer: Multi-scale transformers with adaptive pathways for time series forecasting,'' in The Twelfth International Conference on Learning Representations","author":"Chen P.","year":"2017","unstructured":"P. Chen, Y. ZHANG, Y. Cheng, Y. Shu, Y. Wang, Q. Wen, B. Yang, and C. Guo, ''Pathformer: Multi-scale transformers with adaptive pathways for time series forecasting,'' in The Twelfth International Conference on Learning Representations, 2017."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29155"},{"key":"e_1_3_2_2_28_1","volume-title":"Etsformer: Exponential smoothing transformers for time-series forecasting,'' arXiv preprint arXiv:2202.01381","author":"Woo G.","year":"2022","unstructured":"G. Woo, C. Liu, D. Sahoo, A. Kumar, and S. Hoi, ''Etsformer: Exponential smoothing transformers for time-series forecasting,'' arXiv preprint arXiv:2202.01381, 2022."},{"key":"e_1_3_2_2_29_1","volume-title":"Mambamixer: Efficient selective state space models with dual token and channel selection,'' arXiv preprint arXiv:2403.19888","author":"Behrouz A.","year":"2024","unstructured":"A. Behrouz, M. Santacatterina, and R. Zabih, ''Mambamixer: Efficient selective state space models with dual token and channel selection,'' arXiv preprint arXiv:2403.19888, 2024."},{"key":"e_1_3_2_2_30_1","volume-title":"Timemachine: A time series is worth 4 mambas for long-term forecasting,'' arXiv preprint arXiv:2403.09898","author":"Ahamed M. A.","year":"2024","unstructured":"M. A. Ahamed and Q. Cheng, ''Timemachine: A time series is worth 4 mambas for long-term forecasting,'' arXiv preprint arXiv:2403.09898, 2024."},{"key":"e_1_3_2_2_31_1","volume-title":"Timemixer: Decomposable multiscale mixing for time series forecasting,'' in International Conference on Learning Representations (ICLR)","author":"Wang S.","year":"2024","unstructured":"S. Wang, H. Wu, X. Shi, T. Hu, H. Luo, L. Ma, J. Y. Zhang, and J. ZHOU, ''Timemixer: Decomposable multiscale mixing for time series forecasting,'' in International Conference on Learning Representations (ICLR), 2024."},{"key":"e_1_3_2_2_32_1","volume-title":"Azhar et al., ''Llama: Open and efficient foundation language models,'' arXiv preprint arXiv:2302.13971","author":"Touvron H.","year":"2023","unstructured":"H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozi\u00e8re, N. Goyal, E. Hambro, F. Azhar et al., ''Llama: Open and efficient foundation language models,'' arXiv preprint arXiv:2302.13971, 2023."},{"key":"e_1_3_2_2_33_1","volume-title":"Autoformer: Decomposition transformers with Auto-Correlation for long-term series forecasting,'' in Advances in Neural Information Processing Systems","author":"Wu H.","year":"2021","unstructured":"H. Wu, J. Xu, J. Wang, and M. Long, ''Autoformer: Decomposition transformers with Auto-Correlation for long-term series forecasting,'' in Advances in Neural Information Processing Systems, 2021."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_3_2_2_35_1","volume-title":"itransformer: Inverted transformers are effective for time series forecasting,'' arXiv preprint arXiv:2310.06625","author":"Liu Y.","year":"2023","unstructured":"Y. Liu, T. Hu, H. Zhang, H. Wu, S. Wang, L. Ma, and M. Long, ''itransformer: Inverted transformers are effective for time series forecasting,'' arXiv preprint arXiv:2310.06625, 2023."},{"key":"e_1_3_2_2_36_1","first-page":"4672","volume-title":"Mixture-of-linear-experts for long-term time series forecasting,'' in International Conference on Artificial Intelligence and Statistics. hskip 1em plus 0.5em minus 0.4emrelax PMLR","author":"Ni R.","year":"2024","unstructured":"R. Ni, Z. Lin, S. Wang, and G. Fanti, ''Mixture-of-linear-experts for long-term time series forecasting,'' in International Conference on Artificial Intelligence and Statistics. hskip 1em plus 0.5em minus 0.4emrelax PMLR, 2024, pp. 4672-4680."},{"key":"e_1_3_2_2_37_1","volume-title":"Revisiting long-term time series forecasting: An investigation on linear mapping,'' arXiv preprint arXiv:2305.10721","author":"Li Z.","year":"2023","unstructured":"Z. Li, S. Qi, Y. Li, and Z. Xu, ''Revisiting long-term time series forecasting: An investigation on linear mapping,'' arXiv preprint arXiv:2305.10721, 2023."},{"key":"e_1_3_2_2_38_1","volume-title":"Squeeze-and-excitation networks,'' IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"Hu J.","unstructured":"J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, ''Squeeze-and-excitation networks,'' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 8, pp. 2011-2023, 2019."},{"key":"e_1_3_2_2_39_1","volume-title":"The hidden attention of mamba models,'' arXiv preprint arXiv:2403.01590","author":"Ali A.","year":"2024","unstructured":"A. Ali, I. Zimerman, and L. Wolf, ''The hidden attention of mamba models,'' arXiv preprint arXiv:2403.01590, 2024."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"e_1_3_2_2_41_1","volume-title":"Gshard: Scaling giant models with conditional computation and automatic sharding,'' arXiv preprint arXiv:2006.16668","author":"Lepikhin D.","year":"2020","unstructured":"D. Lepikhin, H. Lee, Y. Xu, D. Chen, O. Firat, Y. Huang, M. Krikun, N. Shazeer, and Z. Chen, ''Gshard: Scaling giant models with conditional computation and automatic sharding,'' arXiv preprint arXiv:2006.16668, 2020."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:12:29Z","timestamp":1777572749000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":41,"alternative-id":["10.1145\/3711896.3737123","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737123","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}