{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:47:50Z","timestamp":1781279270992,"version":"3.54.1"},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T00:00:00Z","timestamp":1631491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["1755850"],"award-info":[{"award-number":["1755850"]}]},{"name":"Intelligence Advanced Research Projects Activity (IARPA) via DoI\/NBC","award":["D12PC000337"],"award-info":[{"award-number":["D12PC000337"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2022,4,30]]},"abstract":"<jats:p>\n            The forecasting of significant societal events such as civil unrest and economic crisis is an interesting and challenging problem which requires both timeliness, precision, and comprehensiveness. Significant societal events are influenced and indicated jointly by multiple aspects of a society, including its economics, politics, and culture. Traditional forecasting methods based on a single data source find it hard to cover all these aspects comprehensively, thus limiting model performance. Multi-source event forecasting has proven promising but still suffers from several challenges, including (1) geographical hierarchies in multi-source data features, (2) hierarchical missing values, (3) characterization of structured feature sparsity, and (4) difficulty in model\u2019s online update with incomplete multiple sources. This article proposes a novel feature learning model that concurrently addresses all the above challenges. Specifically, given multi-source data from different geographical levels, we design a new forecasting model by characterizing the lower-level features\u2019 dependence on higher-level features. To handle the correlations amidst structured feature sets and deal with missing values among the coupled features, we propose a novel feature learning model based on an\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"TeX\" version=\"MathJax\">N<\/jats:tex-math>\n            <\/jats:inline-formula>\n            th-order strong hierarchy and fused-overlapping group Lasso. An efficient algorithm is developed to optimize model parameters and ensure global optima. More importantly, to enable the model update in real time, the online learning algorithm is formulated and active set techniques are leveraged to resolve the crucial challenge when new patterns of missing features appear in real time. Extensive experiments on 10 datasets in different domains demonstrate the effectiveness and efficiency of the proposed models.\n          <\/jats:p>","DOI":"10.1145\/3464976","type":"journal-article","created":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T23:08:09Z","timestamp":1631574489000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Spatio-Temporal Event Forecasting Using Incremental Multi-Source Feature Learning"],"prefix":"10.1145","volume":"16","author":[{"given":"Liang","family":"Zhao","sequence":"first","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Gao","sequence":"additional","affiliation":[{"name":"Emory University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Texas, Dallas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfang","family":"Ye","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Tien","family":"Lu","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naren","family":"Ramakrishnan","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,9,13]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Francis Bach. 2008. Exploring large feature spaces with hierarchical multiple kernel learning. arXiv:0809.1493. Retrieved from https:\/\/arxiv.org\/abs\/0809.1493.  Francis Bach. 2008. Exploring large feature spaces with hierarchical multiple kernel learning. arXiv:0809.1493. Retrieved from https:\/\/arxiv.org\/abs\/0809.1493."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2010.12.007"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/ecin.12506"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.30"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2010.tm08281"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248566"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.09.127"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2746107"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2021068"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.830985"},{"key":"e_1_2_1_12_1","unstructured":"Fuli Feng Xiangnan He Hanwang Zhang and Tat-Seng Chua. 2020. Cross-GCN: Enhancing graph convolutional network with k-Order feature interactions. arXiv:2003.02587. Retrieved from https:\/\/arxiv.org\/abs\/2003.02587.  Fuli Feng Xiangnan He Hanwang Zhang and Tat-Seng Chua. 2020. Cross-GCN: Enhancing graph convolutional network with k-Order feature interactions. arXiv:2003.02587. Retrieved from https:\/\/arxiv.org\/abs\/2003.02587."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1710"},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a0 32","author":"Gao Yuyang","year":"2018","unstructured":"Yuyang Gao and Liang Zhao . 2018 . Incomplete label multi-task ordinal regression for spatial event scale forecasting . In Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a0 32 . Yuyang Gao and Liang Zhao. 2018. Incomplete label multi-task ordinal regression for spatial event scale forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a0 32."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013638"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2014.02.003"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.2008.02168.x"},{"key":"e_1_2_1_18_1","unstructured":"Asad Haris Daniela Witten and Noah Simon. 2014. Convex modeling of interactions with strong heredity. arXiv:1410.3517. Retrieved from https:\/\/arxiv.org\/abs\/1410.3517.  Asad Haris Daniela Witten and Noah Simon. 2014. Convex modeling of interactions with strong heredity. arXiv:1410.3517. Retrieved from https:\/\/arxiv.org\/abs\/1410.3517."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1196963"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3045061"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313730"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2789292"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1198\/004017005000000652"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2579233"},{"key":"e_1_2_1_25_1","volume-title":"Kingma and Jimmy Ba","author":"P.","year":"2014","unstructured":"Diederik\u00a0 P. Kingma and Jimmy Ba . 2014 . Adam : A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980. Diederik\u00a0P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.010"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.11.006"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975321.33"},{"key":"e_1_2_1_29_1","unstructured":"Michael Lim and Trevor Hastie. 2013. Learning interactions through hierarchical group-lasso regularization. arXiv:1308.2719. Retrieved from https:\/\/arxiv.org\/abs\/1308.2719.  Michael Lim and Trevor Hastie. 2013. Learning interactions through hierarchical group-lasso regularization. arXiv:1308.2719. Retrieved from https:\/\/arxiv.org\/abs\/1308.2719."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.021"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1756008"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339577"},{"key":"e_1_2_1_33_1","volume-title":"ICML Workshop on Learning and Reasoning with Graph-Structured Data","author":"Mirtaheri Mehrnoosh","year":"2019","unstructured":"Mehrnoosh Mirtaheri , Sami Abu-El-Haija , Tozammel Hossain , et\u00a0al. 2019 . Tensor-based method fortemporal geopolitical event forecasting . ICML Workshop on Learning and Reasoning with Graph-Structured Data (2019). Mehrnoosh Mirtaheri, Sami Abu-El-Haija, Tozammel Hossain, et\u00a0al. 2019. Tensor-based method fortemporal geopolitical event forecasting. ICML Workshop on Learning and Reasoning with Graph-Structured Data (2019)."},{"key":"e_1_2_1_34_1","volume-title":"Retrieved from","year":"2016","unstructured":"MITRE.[n.d.]. Retrieved from Feb 2016 from http:\/\/www.mitre.org\/. MITRE.[n.d.]. Retrieved from Feb 2016 from http:\/\/www.mitre.org\/."},{"key":"e_1_2_1_35_1","volume-title":"Smith","author":"O\u2019Connor Brendan","year":"2010","unstructured":"Brendan O\u2019Connor , Ramnath Balasubramanyan , Bryan R. Routledge , and Noah A . Smith . 2010 . From tweets to polls: Linking text sentiment to public opinion time series.International AAAI Conference on Weblogs and Social Media 11(2010), 122\u2013129. Brendan O\u2019Connor, Ramnath Balasubramanyan, Bryan R. Routledge, and Noah A. Smith. 2010. From tweets to polls: Linking text sentiment to public opinion time series.International AAAI Conference on Weblogs and Social Media 11(2010), 122\u2013129."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1186\/1753-6561-6-S2-S10"},{"key":"e_1_2_1_37_1","unstructured":"Hristo Paskov Alex Paskov and Robert West. 2020. Learning high order feature interactions with fine control kernels. arXiv:2002.03298. Retrieved from https:\/\/arxiv.org\/abs\/2002.03298.  Hristo Paskov Alex Paskov and Robert West. 2020. Learning high order feature interactions with fine control kernels. arXiv:2002.03298. Retrieved from https:\/\/arxiv.org\/abs\/2002.03298."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0103408"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3041838.3041913"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70087-8_49"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623373"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.09.010"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772777"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052588"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2675839"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.3390\/fi12020039"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.93"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"e_1_2_1_50_1","unstructured":"Fei Xue and Annie Qu. 2019. Integrating multi-source block-wise missing data in model selection. arXiv:1901.03797. Retrieved from https:\/\/arxiv.org\/abs\/1901.03797.  Fei Xue and Annie Qu. 2019. Integrating multi-source block-wise missing data in model selection. arXiv:1901.03797. Retrieved from https:\/\/arxiv.org\/abs\/1901.03797."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939881"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2014.63"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339710"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219922"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450287"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0110206"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974010.108"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.39"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783377"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2719039"},{"key":"e_1_2_1_61_1","volume-title":"Proceedings of the 32nd AAAI Conference on Artificial Intelligence.4498\u20134505","author":"Zhao Liang","year":"2018","unstructured":"Liang Zhao , Junxiang Wang , and Xiaojie Guo . 2018 . Distant-supervision of heterogeneous multitask learning for social event forecasting with multilingual indicators . In Proceedings of the 32nd AAAI Conference on Artificial Intelligence.4498\u20134505 . Liang Zhao, Junxiang Wang, and Xiaojie Guo. 2018. Distant-supervision of heterogeneous multitask learning for social event forecasting with multilingual indicators. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence.4498\u20134505."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939847"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3044812"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1081870.1081914"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.10.021"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3464976","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3464976","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3464976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:25Z","timestamp":1750191505000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3464976"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,13]]},"references-count":65,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4,30]]}},"alternative-id":["10.1145\/3464976"],"URL":"https:\/\/doi.org\/10.1145\/3464976","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,13]]},"assertion":[{"value":"2020-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-05-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}