{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:02:33Z","timestamp":1776178953075,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62466016"],"award-info":[{"award-number":["62466016"]}]},{"name":"National Natural Science Foundation of China","award":["62241202"],"award-info":[{"award-number":["62241202"]}]},{"name":"National Natural Science Foundation of China","award":["2021ZD0111000"],"award-info":[{"award-number":["2021ZD0111000"]}]},{"name":"National Natural Science Foundation of China","award":["2021ZD0111002"],"award-info":[{"award-number":["2021ZD0111002"]}]},{"name":"National Key Research and Development Program of China","award":["62466016"],"award-info":[{"award-number":["62466016"]}]},{"name":"National Key Research and Development Program of China","award":["62241202"],"award-info":[{"award-number":["62241202"]}]},{"name":"National Key Research and Development Program of China","award":["2021ZD0111000"],"award-info":[{"award-number":["2021ZD0111000"]}]},{"name":"National Key Research and Development Program of China","award":["2021ZD0111002"],"award-info":[{"award-number":["2021ZD0111002"]}]},{"name":"Key Research and Development Plan of the Ministry of Science and Technology","award":["62466016"],"award-info":[{"award-number":["62466016"]}]},{"name":"Key Research and Development Plan of the Ministry of Science and Technology","award":["62241202"],"award-info":[{"award-number":["62241202"]}]},{"name":"Key Research and Development Plan of the Ministry of Science and Technology","award":["2021ZD0111000"],"award-info":[{"award-number":["2021ZD0111000"]}]},{"name":"Key Research and Development Plan of the Ministry of Science and Technology","award":["2021ZD0111002"],"award-info":[{"award-number":["2021ZD0111002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Temporal knowledge graphs (TKGs) are crucial for modeling evolving real-world facts and are widely applied in event forecasting and risk analysis. However, current TKG reasoning models struggle to separate causal signals from noisy observations, align temporal dynamics with semantic structures, and integrate long-term and short-term knowledge effectively. To address these challenges, we propose the Temporal Causal Contrast Graph Network (TCCGN), a unified framework that disentangles causal features from noise via orthogonal decomposition and adversarial learning; applies dual-domain contrastive learning to enhance both temporal and semantic consistency; and introduces a gated fusion module for adaptive integration of static and dynamic features across time scales. Extensive experiments on five benchmarks (ICEWS14\/05-15\/18, YAGO, GDELT) show that TCCGN consistently outperforms prior models. On ICEWS14, it achieves 42.46% MRR and 31.63% Hits@1, surpassing RE-GCN by 1.21 points. On the high-noise GDELT dataset, it improves MRR by 1.0%. These results highlight TCCGN\u2019s robustness and its promise for real-world temporal reasoning tasks involving fine-grained causal inference under noisy conditions.<\/jats:p>","DOI":"10.3390\/info16090717","type":"journal-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:31:26Z","timestamp":1755865886000},"page":"717","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Causal Decoupling for Temporal Knowledge Graph Reasoning via Contrastive Learning and Adaptive Fusion"],"prefix":"10.3390","volume":"16","author":[{"given":"Siling","family":"Feng","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Haikou 570228, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Housheng","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Haikou 570228, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9262-8840","authenticated-orcid":false,"given":"Qian","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Haikou 570228, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Haikou 570228, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Haikou 570228, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bolin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Haikou 570228, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxing","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Hainan University, Haikou 570228, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"ref_1","unstructured":"Gao, H., Wu, L., Hu, P., Wei, Z., Xu, F., and Long, B. (2022, January 20\u201323). Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph. Proceedings of the AACL-IJCNLP, Online."},{"key":"ref_2","unstructured":"Trivedi, R., Dai, H., Wang, Y., and Chang, L. (2017, January 6\u201311). Know-evolve: Deep temporal reasoning for dynamic knowledge graphs. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Australia."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"109134","DOI":"10.1016\/j.knosys.2022.109134","article-title":"Temporal knowledge graph question answering via subgraph reasoning","volume":"251","author":"Chen","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"109951","DOI":"10.1016\/j.knosys.2022.109951","article-title":"Building and exploiting spatial\u2013temporal knowledge graph for next POI recommendation","volume":"258","author":"Chen","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_5","first-page":"1","article-title":"Representation learning for dynamic graphs: A survey","volume":"21","author":"Kazemi","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-Dur\u00e1n, A., Duman\u010di\u0107, S., and Niepert, M. (2018). Learning sequence encoders for temporal knowledge graph completion. arXiv.","DOI":"10.18653\/v1\/D18-1516"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Leblay, J., and Chekol, M.W. (2018, January 23\u201327). Deriving validity time in knowledge graph. Proceedings of the Companion Proceedings of The Web Conference 2018, Lyon, France.","DOI":"10.1145\/3184558.3191639"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Dasgupta, S.S., Ray, S.N., and Talukdar, P. (November, January 31). HyTE: Hyperplane-based temporally aware knowledge graph embedding. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium.","DOI":"10.18653\/v1\/D18-1225"},{"key":"ref_9","unstructured":"Trivedi, R., Farajtabar, M., Biswal, P., and Zha, H. (2019, January 6\u20139). DyRep: Learning representations over dynamic graphs. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Jin, W., Yang, Y., Liu, X., Sun, Z., and Huang, H. (2019). Recurrent event network: Autoregressive structure inference over temporal knowledge graphs. arXiv.","DOI":"10.18653\/v1\/2020.emnlp-main.541"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Xu, C., Kou, B., Zhang, L., Li, P., Liu, Y., and Wu, B. (2021, January 6\u201311). Temporal knowledge graph completion using a linear temporal regularizer and multivector embeddings. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online.","DOI":"10.18653\/v1\/2021.naacl-main.202"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Li, Z., Sun, Z., Yu, J., Zhang, W., and Ji, H. (2021, January 11\u201315). Temporal knowledge graph reasoning based on evolutional representation learning. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event.","DOI":"10.1145\/3404835.3462963"},{"key":"ref_13","first-page":"4733","article-title":"Learning from history: Modeling temporal knowledge graphs with sequential copy-generation networks","volume":"35","author":"Zhu","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1109\/TKDE.2024.3486747","article-title":"TGformer: A Graph Transformer Framework for Knowledge Graph Embedding","volume":"37","author":"Shi","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"10929","DOI":"10.1007\/s10489-024-05767-6","article-title":"Temporal knowledge graph reasoning based on evolutional representation and contrastive learning","volume":"54","author":"Ma","year":"2024","journal-title":"Appl. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Fang, Z., Lei, S.L., Zhu, X., Yang, C., Zhang, S.X., Yin, X.C., and Qin, J. (2024, January 14\u201318). Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Washington, DC, USA.","DOI":"10.1145\/3626772.3657706"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sun, H., Geng, S., Zhong, J., Hu, H., and He, K. (2022, January 7\u201311). Graph Hawkes Transformer for Extrapolated Reasoning on Temporal Knowledge Graphs. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates.","DOI":"10.18653\/v1\/2022.emnlp-main.507"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, K., Zhao, F., Chen, H., Li, Y., Xu, G., and Jin, H. (2022, January 17\u201321). Da-net: Distributed Attention Network for Temporal Knowledge Graph Reasoning. Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM), Atlanta, GA, USA.","DOI":"10.1145\/3511808.3557280"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"120069","DOI":"10.1016\/j.ins.2023.120069","article-title":"Simre: Simple Contrastive Learning with Soft Logical Rule for Knowledge Graph Embedding","volume":"661","author":"Zhang","year":"2024","journal-title":"Inf. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Tan, L., Li, M., and Zhang, W. (2023). Simfy: A Simple yet Effective Approach for Temporal Knowledge Graph Reasoning. Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-emnlp.249"},{"key":"ref_21","first-page":"4521","article-title":"Temporal knowledge graph reasoning with historical contrastive learning","volume":"37","author":"Xu","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_22","unstructured":"Yang, J., Wang, X., Wang, Y., Wang, J., and Wang, F.Y. (2024). AMCEN: An Attention Masking-based Contrastive Event Network for Two-stage Temporal Knowledge Graph Reasoning. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Xu, Y., Shi, B., Ma, T., Dong, B., Zhou, H., and Zheng, Q. (2023, January 3\u20137). CLDG: Contrastive Learning on Dynamic Graphs. Proceedings of the 2023 IEEE 39th International Conference on Data Engineering (ICDE), Anaheim, CA, USA.","DOI":"10.1109\/ICDE55515.2023.00059"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Peng, M., Liu, B., Xu, W., Jiang, Z., Zhu, J., and Peng, M. (2024). Deja Vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning. arXiv.","DOI":"10.18653\/v1\/2024.findings-naacl.75"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xu, W., Liu, B., Peng, M., Jia, X., and Peng, M. (2023). Pre-trained language model with prompts for temporal knowledge graph completion. arXiv.","DOI":"10.18653\/v1\/2023.findings-acl.493"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chen, W., Wan, H., Wu, Y., Zhao, S., Cheng, J., Li, Y., and Lin, Y. (2024, January 13\u201316). Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning. Proceedings of the 2024 IEEE 40th International Conference on Data Engineering (ICDE), Utrecht, The Netherlands.","DOI":"10.1109\/ICDE60146.2024.00062"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107841","DOI":"10.1016\/j.knosys.2021.107841","article-title":"Tucker decomposition-based temporal knowledge graph completion","volume":"238","author":"Shao","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhu, Z., Li, H., and Li, J. (2021, January 11). Spatial-temporal attention network for temporal knowledge graph completion. Proceedings of the Database Systems for Advanced Applications 26th nternational Conference DASFAA 2021, Taipei, Taiwan. Proceedings, Part I.","DOI":"10.1007\/978-3-030-73194-6_15"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Sui, Y., Xie, J., Hou, X., Chen, Z., and Tian, C. (2022, January 14\u201318). Causal attention for interpretable and generalizable graph classification. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/3534678.3539366"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Han, Z., Ye, H., Sun, Z., Lin, Y., Han, X., Zhou, J., Liu, Z., Li, P., Sun, M., and Zhou, J. (2020). Dyernie: Dynamic evolution of riemannian manifold embeddings for temporal knowledge graph completion. arXiv.","DOI":"10.18653\/v1\/2020.emnlp-main.593"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Han, Z., Sun, Z., Lin, Y., Ye, H., Liu, Z., Li, P., and Zhou, J. (2021, January 7\u201311). Learning neural ordinary equations for forecasting future links on temporal knowledge graphs. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Virtual Event.","DOI":"10.18653\/v1\/2021.emnlp-main.658"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wu, J., Feng, Y., Wang, W., Chen, M., and Zhao, Y. (2020). Temp: Temporal message passing for temporal knowledge graph completion. arXiv.","DOI":"10.18653\/v1\/2020.emnlp-main.462"},{"key":"ref_33","unstructured":"Sun, X., Zhang, J., Wu, X., Cheng, H., Xiong, Y., and Li, J. (2023). Graph Prompt Learning: A Comprehensive Survey and Beyond. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Korkmaz, G., Cadena, J., Kuhlman, C.J., Marathe, A., Vullikanti, A., and Ramakrishnan, N. (2015, January 25\u201328). Combining heterogeneous data sources for civil unrest forecasting. Proceedings of the 2015 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining, Paris, France.","DOI":"10.1145\/2808797.2808847"},{"key":"ref_35","unstructured":"Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., and Erhan, D. (2016, January 5\u201310). Domain separation networks. Proceedings of the Advances in Neural Information Processing Systems (NIPS), Barcelona, Spain."},{"key":"ref_36","unstructured":"Locatello, F., Bauer, S., Lucic, M., Raetsch, G., Gelly, S., Sch\u00f6lkopf, B., and Bachem, O. (2019, January 9\u201315). Challenging common assumptions in the unsupervised learning of disentangled representations. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: A review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_38","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13\u201318). A simple framework for contrastive learning of visual representations. Proceedings of the International Conference on Machine Learning (ICML), Virtual Event."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1111\/j.1468-2486.2009.00914.x","article-title":"Crisis early warning and decision support: Contemporary approaches and thoughts on future research","volume":"12","year":"2010","journal-title":"Int. Stud. Rev."},{"key":"ref_40","unstructured":"Han, Z., Chen, P., Ma, Y., and Tresp, V. (2021, January 3\u20137). Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs. Proceedings of the International Conference on Learning Representations, Online."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.artint.2012.06.001","article-title":"YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia","volume":"194","author":"Hoffart","year":"2013","journal-title":"Artif. Intell."},{"key":"ref_42","first-page":"1","article-title":"GDELT: Global data on events, location, and tone, 1979\u20132012","volume":"2","author":"Leetaru","year":"2013","journal-title":"ISA Annu. Conv."},{"key":"ref_43","unstructured":"Trouillon, T., Welbl, J., Riedel, S., Gaussier, \u00c9., and Bouchard, G. (2016, January 20\u201322). Complex embeddings for simple link prediction. Proceedings of the International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_44","unstructured":"Yang, B., Yih, W.T., He, X., Gao, J., and Deng, L. (2014, January 14\u201316). Embedding entities and relations for learning and reasoning in knowledge bases. Proceedings of the International Conference on Machine Learning (ICLR) (Poster), Banff, AB, Canada."},{"key":"ref_45","unstructured":"Sun, Z., Deng, Z.H., Nie, J.Y., and Tang, X. (2019). Rotate: Knowledge graph embedding by relational rotation in complex space. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Minervini, P., Stenetorp, P., and Riedel, S. (2018, January 2\u20137). Convolutional 2D knowledge graph embeddings. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA. Art. 221.","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Shang, C., Tang, Y., Huang, J., Bi, J., He, X., and Zhou, B. (February, January 27). End-to-end structure-aware convolutional networks for knowledge base completion. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA. Art. 3060.","DOI":"10.1609\/aaai.v33i01.33013060"},{"key":"ref_48","first-page":"3988","article-title":"Diachronic embedding for temporal knowledge graph completion","volume":"34","author":"Goel","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_49","unstructured":"Kazemi, S.M., and Poole, D.L. (2018, January 3\u20138). Simple Embedding for Link Prediction in Knowledge Graphs. Proceedings of the Advances in Neural Information Processing Systems, Montr\u2019eal, QC, Canada."},{"key":"ref_50","unstructured":"Lacroix, T., Obozinski, G., and Usunier, N. (2020). Tensor decompositions for temporal knowledge base completion. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Gao, Y., Feng, L., Kan, Z., Han, Y., Qiao, L., and Li, D. (2022, January 23\u201329). Modeling Precursors for Temporal Knowledge Graph Reasoning via Auto-encoder Structure. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Vienna, Austria.","DOI":"10.24963\/ijcai.2022\/284"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"2411","DOI":"10.32604\/csse.2023.026823","article-title":"Future Event Prediction Based on Temporal Knowledge Graph Embedding","volume":"44","author":"Li","year":"2023","journal-title":"Comput. Syst. Sci. Eng."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/9\/717\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:33:51Z","timestamp":1760034831000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/9\/717"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"references-count":52,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["info16090717"],"URL":"https:\/\/doi.org\/10.3390\/info16090717","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,22]]}}}