{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T05:47:46Z","timestamp":1773294466627,"version":"3.50.1"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"name":"JST SPRING","award":["JPMJSP2110"],"award-info":[{"award-number":["JPMJSP2110"]}]},{"name":"JST FOREST Program","award":["JPMJFR232S"],"award-info":[{"award-number":["JPMJFR232S"]}]},{"name":"JSPS KAKENHI","award":["21H04979"],"award-info":[{"award-number":["21H04979"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>\n                    Estimating treatment effects can assist decision-making in various areas, such as commerce and medicine. One application of the treatment effect estimation is to predict the effect of an advertisement on the purchase result of a customer, known as individual treatment effect (ITE). In online websites, the outcome of an individual can be affected by treatments of other individuals, as people often propagate information with their friends. This is referred to as interference. Prior studies have attempted to model interference for accurate ITE estimation under a static network among individuals. However, the network usually changes over time in real-world applications due to complex social activities among individuals. In this case, the outcomes of individuals can be interfered with not only by treatments for current neighbors but also by past information and treatments for past neighbors, which we refer to as\n                    <jats:italic toggle=\"yes\">dynamic interference<\/jats:italic>\n                    . In this work, we model dynamic interference by developing an architecture to aggregate both the past information of individuals and their neighbors. Specifically, our proposed method contains an attention-based historical aggregation, which models interference received by individuals from previous timestamps, and an attention-based neighbor aggregation, which captures interference received by individuals within every timestamp. Since information about individuals changes over time, we propose a parameter evolution trick to adaptively update the parameters of the model, which enables the model to capture the dynamics effectively. In our experiments on multiple datasets with dynamic interference, our method outperforms existing methods for ITE estimation because they cannot capture dynamic interference, which corroborates the importance of dynamic interference modeling.\n                  <\/jats:p>","DOI":"10.1145\/3796240","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T11:51:17Z","timestamp":1770378677000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Modeling Dynamic Interference for Treatment Effect Estimation from Dynamic Graphs"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4147-3037","authenticated-orcid":false,"given":"Xiaofeng","family":"Lin","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4473-2604","authenticated-orcid":false,"given":"Han","family":"Bao","sequence":"additional","affiliation":[{"name":"The Institute of Statistical Mathematics, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3245-888X","authenticated-orcid":false,"given":"Koh","family":"Takeuchi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6066-8117","authenticated-orcid":false,"given":"Yan","family":"Cui","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2770-0184","authenticated-orcid":false,"given":"Hisashi","family":"Kashima","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Abien Fred Agarap. 2018. Deep learning using rectified linear units. arXiv:1803.08375. Retrieved from https:\/\/arxiv.org\/abs\/1803.08375"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1214\/16-AOAS1005"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614892"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26657"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3692319"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467302"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2022.1401"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02902-1"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1768100"},{"issue":"289","key":"e_1_3_2_12_2","first-page":"1","article-title":"Estimating causal effects under network interference with Bayesian generalized propensity scores","volume":"23","author":"Forastiere Laura","year":"2022","unstructured":"Laura Forastiere, Fabrizia Mealli, Albert Wu, and Edoardo M. Airoldi. 2022. Estimating causal effects under network interference with Bayesian generalized propensity scores. Journal of Machine Learning Research 23, 289 (2022), 1\u201361.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_13_2","unstructured":"Dennis Frauen Konstantin Hess and Stefan Feuerriegel. 2024. Model-agnostic meta-learners for estimating heterogeneous treatment effects over time. arXiv:2407.05287. Retrieved from https:\/\/arxiv.org\/abs\/2407.05287"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3361166"},{"key":"e_1_3_2_15_2","unstructured":"Johannes Gasteiger Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2018. Predict then propagate: Graph neural networks meet personalized PageRank. arXiv:1810.05997. Retrieved from https:\/\/arxiv.org\/abs\/1810.05997"},{"key":"e_1_3_2_16_2","unstructured":"Aidan Gleich Eric Laber and Alexander Volfovsky. 2025. Scalable policy maximization under network interference. arXiv:2505.18118. Retrieved from https:\/\/arxiv.org\/abs\/2505.18118"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371816"},{"key":"e_1_3_2_19_2","article-title":"Inductive representation learning on large graphs","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems (2017).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482349"},{"key":"e_1_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Adi Haviv Ori Ram Ofir Press Peter Izsak and Omer Levy. 2022. transformer language models without positional encodings still learn positional information. arXiv:2203.16634. Retrieved from https:\/\/arxiv.org\/abs\/2203.16634","DOI":"10.18653\/v1\/2022.findings-emnlp.99"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"3","key":"e_1_3_2_23_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3628449","article-title":"Modeling interference for individual treatment effect estimation from networked observational data","volume":"18","author":"Huang Qiang","year":"2023","unstructured":"Qiang Huang, Jing Ma, Jundong Li, Ruocheng Guo, Huiyan Sun, and Yi Chang. 2023. Modeling interference for individual treatment effect estimation from networked observational data. ACM Transactions on Knowledge Discovery from Data 18, 3 (2023), 1\u201321.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648148"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1198\/016214508000000292"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1002\/cjs.11702"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599272"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557311"},{"key":"e_1_3_2_29_2","first-page":"3020","volume-title":"Proceedings of 33rd International Conference on Machine Learning","volume":"48","author":"Johansson Fredrik","year":"2016","unstructured":"Fredrik Johansson, Uri Shalit, and David Sontag. 2016. Learning representations for counterfactual inference. In Proceedings of 33rd International Conference on Machine Learning, Vol. 48, 3020\u20133029."},{"key":"e_1_3_2_30_2","unstructured":"Dongyeop Kang Waleed Ammar Bhavana Dalvi Madeleine Van Zuylen Sebastian Kohlmeier Eduard Hovy and Roy Schwartz. 2018. A dataset of peer reviews (PeerRead): Collection insights and NLP applications. arXiv:1804.09635. Retrieved from https:\/\/arxiv.org\/abs\/1804.09635"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3633518"},{"key":"e_1_3_2_32_2","volume-title":"Proceedings of 3rd International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of 3rd International Conference on Learning Representations."},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2024.2340789"},{"key":"e_1_3_2_35_2","volume-title":"Proceedings of 11th International Conference on Learning Representations","author":"Li Haoxuan","year":"2023","unstructured":"Haoxuan Li, Chunyuan Zheng, and Peng Wu. 2023. StableDR: Stabilized doubly robust learning for recommendation on data missing not at random. In Proceedings of 11th International Conference on Learning Representations."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806501"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3402317"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06694-w"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43412-9_34"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2013.844698"},{"key":"e_1_3_2_41_2","unstructured":"Meng Liu Yue Liu Ke Liang Wenxuan Tu Siwei Wang Sihang Zhou and Xinwang Liu. 2023. Deep temporal graph clustering. arXiv:2305.10738. Retrieved from https:\/\/arxiv.org\/abs\/2305.10738"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599763"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512139"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441818"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539299"},{"key":"e_1_3_2_46_2","first-page":"3700","volume-title":"Proceedings of 24th International Conference on Artificial Intelligence and Statistics","volume":"130","author":"Ma Yunpu","year":"2021","unstructured":"Yunpu Ma and Volker Tresp. 2021. Causal inference under networked interference and intervention policy enhancement. In Proceedings of 24th International Conference on Artificial Intelligence and Statistics, Vol. 130, 3700\u20133708."},{"key":"e_1_3_2_47_2","first-page":"15293","volume-title":"Proceedings of 39th International Conference on Machine Learning","author":"Melnychuk Valentyn","year":"2022","unstructured":"Valentyn Melnychuk, Dennis Frauen, and Stefan Feuerriegel. 2022. Causal transformer for estimating counterfactual outcomes. In Proceedings of 39th International Conference on Machine Learning. PMLR, 15293\u201315329."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2022.888592"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5984"},{"key":"e_1_3_2_50_2","first-page":"55","volume-title":"Neural Networks: Tricks of the Trade","author":"Prechelt Lutz","year":"2002","unstructured":"Lutz Prechelt. 2002. Early stopping-but when? In Neural Networks: Tricks of the Trade. Genevieve B. Orr and Klaus-Robert M\u00fcller (Eds.), Springer, 55\u201369."},{"key":"e_1_3_2_51_2","unstructured":"Roger Pros and Jordi Vitri\u00e0. 2024. Neural networks with causal graph constraints: A new approach for treatment effects estimation. arXiv:2404.12238. Retrieved from https:\/\/arxiv.org\/abs\/2404.12238"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3269267"},{"key":"e_1_3_2_53_2","unstructured":"Emanuele Rossi Ben Chamberlain Fabrizio Frasca Davide Eynard Federico Monti and Michael Bronstein. 2020. Temporal graph networks for deep learning on dynamic graphs. arXiv:2006.10637. Retrieved from https:\/\/arxiv.org\/abs\/2006.10637"},{"issue":"371","key":"e_1_3_2_54_2","doi-asserted-by":"crossref","first-page":"591","DOI":"10.2307\/2287653","article-title":"Randomization analysis of experimental data: The fisher randomization test comment","volume":"75","author":"Rubin Donald B.","year":"1980","unstructured":"Donald B. Rubin. 1980. Randomization analysis of experimental data: The fisher randomization test comment. Journal of the American Statistical Association 75, 371 (1980), 591\u2013593.","journal-title":"Journal of the American Statistical Association"},{"key":"e_1_3_2_55_2","unstructured":"T. Konstantin Rusch Michael M. Bronstein and Siddhartha Mishra. 2023. A survey on oversmoothing in graph neural networks. arXiv:2303.10993. Retrieved from https:\/\/arxiv.org\/abs\/2303.10993"},{"key":"e_1_3_2_56_2","unstructured":"Aravind Sankar Yanhong Wu Liang Gou Wei Zhang and Hao Yang. 2018. Dynamic graph representation learning via self-attention networks. arXiv:1812.09430. Retrieved from https:\/\/arxiv.org\/abs\/1812.09430"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0000000000001470"},{"key":"e_1_3_2_58_2","first-page":"3076","volume-title":"Proceedings of 34th International Conference on Machine Learning","volume":"70","author":"Shalit Uri","year":"2017","unstructured":"Uri Shalit, Fredrik D. Johansson, and David Sontag. 2017. Estimating individual treatment effect: Generalization bounds and algorithms. In Proceedings of 34th International Conference on Machine Learning, Vol. 70, 3076\u20133085."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3437665"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645549"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1177\/0962280210386779"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1811098"},{"key":"e_1_3_2_64_2","article-title":"Attention is all you need","volume":"30","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. In Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_65_2","volume-title":"Proceedings of 6th International Conference on Learning Representations","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of 6th International Conference on Learning Representations."},{"key":"e_1_3_2_66_2","unstructured":"Davide Viviano. 2019. Policy targeting under network interference. arXiv:1906.10258. Retrieved from https:\/\/arxiv.org\/abs\/1906.10258"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2022.0406"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3536427"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-012-0555-0"},{"key":"e_1_3_2_70_2","unstructured":"Ye Wang. 2021. Causal inference with panel data under temporal and spatial interference. arXiv:2106.15074. Retrieved from https:\/\/arxiv.org\/abs\/2106.15074"},{"key":"e_1_3_2_71_2","unstructured":"Yingrong Wang Haoxuan Li Minqin Zhu Anpeng Wu Ruoxuan Xiong Fei Wu and Kun Kuang. 2024. Causal inference with complex treatments: A survey. arXiv:2407.14022. Retrieved from https:\/\/arxiv.org\/abs\/2407.14022"},{"key":"e_1_3_2_72_2","volume-title":"Proceedings of 4th International Conference on Learning Representations","author":"Welling Max","year":"2016","unstructured":"Max Welling and Thomas N. Kipf. 2016. Semi-supervised classification with graph convolutional networks. In Proceedings of 4th International Conference on Learning Representations."},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3321893"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00184"},{"key":"e_1_3_2_75_2","unstructured":"Hechuan Wen Tong Chen Mingming Gong Li Kheng Chai Shazia Sadiq and Hongzhi Yin. 2025. Enhancing treatment effect estimation via active learning: A counterfactual covering perspective. arXiv:2505.05242. Retrieved from https:\/\/arxiv.org\/abs\/2505.05242"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709305"},{"key":"e_1_3_2_77_2","unstructured":"Da Xu Chuanwei Ruan Evren Korpeoglu Sushant Kumar and Kannan Achan. 2020. Inductive representation learning on temporal graphs. arXiv:2002.07962. Retrieved from https:\/\/arxiv.org\/abs\/2002.07962"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3444944"},{"key":"e_1_3_2_79_2","unstructured":"Yu Zhu Zehang Richard Li Yang Su and Zhenyu Zhao. 2024. Treatment effect estimation amidst dynamic network interference in online gaming experiments. arXiv:2402.05336. Retrieved from https:\/\/arxiv.org\/abs\/2402.05336"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3796240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T12:50:49Z","timestamp":1773233449000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3796240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":78,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3796240"],"URL":"https:\/\/doi.org\/10.1145\/3796240","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]},"assertion":[{"value":"2025-08-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}