{"type":"ScholarlyArticle","title":"Cross-Interaction Hierarchical Attention Networks for Urban Anomaly Prediction","authors":[{"name":"Chao Huang","slug":"chao-huang","given":"Chao","family":"Huang","affiliation":"JD Finance America Corporation"},{"name":"Chuxu Zhang","slug":"chuxu-zhang","given":"Chuxu","family":"Zhang","affiliation":"Brandeis University"},{"name":"Peng Dai","slug":"peng-dai","given":"Peng","family":"Dai","affiliation":"JD Finance America Corporation"},{"name":"Liefeng Bo","slug":"liefeng-bo","given":"Liefeng","family":"Bo","affiliation":"JD Finance America Corporation"}],"abstract":"Predicting anomalies (e.g., blocked driveway and vehicle collisions) in urban space plays an important role in assisting governments and communities for building smart city applications, ranging from intelligent transportation to public safety. However, predicting urban anomalies is not trivial due to the following two factors: i) The sequential transition regularities of anomaly occurrences is complex, which exhibit with high-order and dynamic correlations. ii) The Interactions between region, time and anomaly category is multi-dimensional in real-world urban anomaly forecasting scenario. How to fuse multiple relations from spatial, temporal and categorical dimensions in the predictive framework remains a significant challenge. To address these two challenges, we propose a Cross-Interaction Hierarchical Attention network model (CHAT) which uncovers the dynamic occurrence patterns of time-stamped urban anomaly data. Our CHAT framework could automatically capture the relevance of past anomaly occurrences across different time steps, and discriminates which types of cross-modal interactions are more important for making future predictions. Experiment results demonstrate the superiority of CHAT framework over state-of-the-art baselines.","doi":"10.24963/ijcai.2020/601","url":"https://ijcai.org/proceedings/2020/601","pdf":"https://ijcai.org/proceedings/2020/0601.pdf","markdown":"https://ijcai.org/proceedings/2020/601.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/601","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Special track on AI for CompSust and Human well-being","track":"Special track on AI for CompSust and Human well-being","number":601,"pages":{"first":4359,"last":4365},"keywords":["Data Mining: Mining Data Streams","Data Mining: Applications","Data Mining: Mining Spatial, Temporal Data"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25815/file_25815.m3u8","length_sec":266,"provider":"hls"}],"references":[{"position":1,"raw":"[Bishop, 1995] Christopher M Bishop. Neural networks for pattern recognition. Oxford university press, 1995.","title":"Neural networks for pattern recognition","authors":"M Christopher, Bishop","year":"1995","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Doan et al., 2015] Minh Tuan Doan, Sutharshan Ra- jasegarar, et al. Profiling pedestrian distribution and anomaly detection in a dynamic environment. In CIKM, pages 1827-1830. ACM, 2015.","title":"Profiling pedestrian distribution and anomaly detection in a dynamic environment","authors":"Doan","year":"2015","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Esling and Agon, 2012] Philippe Esling and Carlos Agon. Time-series data mining. CSUR, page 12, 2012.","title":"Time-series data mining","authors":"Agon Esling, Philippe Esling, Carlos Agon","year":"2012","venue":"CSUR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Feng et al., 2018] Jie Feng, Yong Li, and etc. Deepmove: Predicting human mobility with attentional recurrent net- works. In WWW, pages 1459-1468. ACM, 2018.","title":"Deepmove: Predicting human mobility with attentional recurrent networks","authors":"Jie Feng, Yong Li, Etc","year":"2018","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Graves, 2013] Alex Graves. Generating sequences with re- current neural networks. arXiv preprint:1308.0850, 2013.","title":"Generating sequences with recurrent neural networks","authors":"Alex Graves","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hosmer Jr et al., 2013] David W Hosmer Jr, Stanley Lemeshow, and Rodney X Sturdivant. Applied logistic regression, volume 398. John Wiley & Sons, 2013.","title":"Applied logistic regression","authors":"David W Hosmer, Stanley Lemeshow, Rodney X Sturdivant","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hu et al., 2017] Linmei Hu, Juanzi Li, Liqiang Nie, Xiao-Li Li, and Chao Shao. What happens next? future subevent prediction using contextual hierarchical lstm. In AAAI, pages 3450-3456, 2017.","title":"What happens next? future subevent prediction using contextual hierarchical lstm","authors":"Linmei Hu, Juanzi Li, Liqiang Nie, Xiao-Li Li, Chao Shao","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang et al., 2016] Chao Huang, Xian Wu, and Dong Wang. Crowdsourcing-based urban anomaly prediction system for smart cities. In CIKM. ACM, 2016.","title":"Crowdsourcing-based urban anomaly prediction system for smart cities","authors":"Chao Huang, Xian Wu, Dong Wang","year":"2016","venue":"CIKM. ACM","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huang et al., 2017] Chao Huang, Dong Wang, and Sheng- long Zhu. Where are you from: Home location profiling of crowd sensors from noisy and sparse crowdsourcing data. In INFOCOM, pages 1-9. IEEE, 2017.","title":"Where are you from: Home location profiling of crowd sensors from noisy and sparse crowdsourcing data","authors":"Chao Huang, Dong Wang, Shenglong Zhu","year":"2017","venue":"INFOCOM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Huang et al., 2018] Chao Huang, Junbo Zhang, Yu Zheng, and Nitesh V Chawla. Deepcrime: Attentive hierarchical recurrent networks for crime prediction. In CIKM, pages 1423-1432. ACM, 2018.","title":"Deepcrime: Attentive hierarchical recurrent networks for crime prediction","authors":"Chao Huang, Junbo Zhang, Yu Zheng, Nitesh V Chawla","year":"2018","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Huang et al., 2019] Chao Huang, Chuxu Zhang, Jiashu Zhao, Xian Wu, Dawei Yin, and Nitesh Chawla. Mist: A multiview and multimodal spatial-temporal learning framework for citywide abnormal event forecasting. In WWW, pages 717-728, 2019.","title":"Mist: A multiview and multimodal spatial-temporal learning framework for citywide abnormal event forecasting","authors":"Chao Huang, Chuxu Zhang, Jiashu Zhao, Xian Wu, Dawei Yin, Nitesh Chawla","year":"2019","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Iordanidou et al., 2017] Georgia-Roumpini Iordanidou, Ioannis Papamichail, et al. Feedback-based integrated motorway traffic flow control with delay balancing. TITS, 18(9):2319-2329, 2017.","title":"Georgia-Roumpini Iordanidou, Ioannis Papamichail, et al. Feedback-based integrated motorway traffic flow control with delay balancing","authors":"Iordanidou","year":"2017","venue":"TITS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kingma and Ba, 2015] Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"Diederik Kingma, Jimmy Ba","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Le et al., 2013] Viet Duc Le, Hans Scholten, and Paul Havinga. Flead: Online frequency likelihood estimation anomaly detection for mobile sensing. In Ubicomp, pages 1159-1166. ACM, 2013.","title":"Flead: Online frequency likelihood estimation anomaly detection for mobile sensing","authors":"Le","year":"2013","venue":"Ubicomp","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2016] Qiang Liu, Shu Wu, et al. Predicting the next location: A recurrent model with spatial and temporal contexts. In AAAI, pages 194-200, 2016.","title":"Predicting the next location: A recurrent model with spatial and temporal contexts","authors":"Qiang Liu, Shu Wu","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ni et al., 2018] Jingchao Ni, Shiyu Chang, Xiao Liu, Wei Cheng, et al. Co-regularized deep multi-network embed- ding. In WWW, pages 469-478. ACM, 2018.","title":"Co-regularized deep multi-network embedding","authors":"Ni","year":"2018","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Pan et al., 2013] Bei Pan, Yu Zheng, et al. Crowd sensing of traffic anomalies based on human mobility and social media. In SIGSPATIAL, pages 344-353. ACM, 2013.","title":"Crowd sensing of traffic anomalies based on human mobility and social media","authors":"Pan","year":"2013","venue":"SIGSPATIAL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rendle and Schmidt-Thieme, 2010] Steffen Rendle and Lars Schmidt-Thieme. Pairwise interaction tensor factor- ization for personalized tag recommendation. In WSDM, pages 81-90. ACM, 2010.","title":"Pairwise interaction tensor factorization for personalized tag recommendation","authors":"Steffen Rendle, Lars Schmidt-Thieme","year":"2010","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Schuster and Paliwal, 1997] Mike Schuster and Kuldip K Paliwal. Bidirectional recurrent neural networks. TSP, 45(11):2673-2681, 1997.","title":"Bidirectional recurrent neural networks","authors":"Mike Schuster, Kuldip K Paliwal","year":"1997","venue":"TSP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Shuai et al., 2017] Bing Shuai, Zhen Zuo, Bing Wang, and Gang Wang. Scene segmentation with dag-recurrent neu- ral networks. TPAMI, 2017.","title":"Scene segmentation with dag-recurrent neural networks","authors":"Shuai","year":"2017","venue":"TPAMI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wiesel et al., 2013] Ami Wiesel, Ofir Bibi, et al. Time vary- ing autoregressive moving average models for covariance estimation. TSP, pages 2791-2801, 2013.","title":"Time varying autoregressive moving average models for covariance estimation","authors":"Ami Wiesel, Ofir Bibi","year":"2013","venue":"TSP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2017] Xian Wu, Yuxiao Dong, et al. Uapd: Pre- dicting urban anomalies from spatial-temporal data. In ECML/PKDD. Springer, 2017.","title":"Uapd: Predicting urban anomalies from spatial-temporal data","authors":"Xian Wu, Yuxiao Dong","year":"2017","venue":"ECML/PKDD","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wu et al., 2020] Xian Wu, Chao Huang, Chuxu Zhang, and Nitesh V Chawla. Hierarchically structured transformer networks for fine-grained spatial event forecasting. In WWW, pages 2320-2330, 2020.","title":"Hierarchically structured transformer networks for fine-grained spatial event forecasting","authors":"Xian Wu, Chao Huang, Chuxu Zhang, Nitesh V Chawla","year":"2020","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xiao et al., 2017] Chunyang Xiao, Marc Dymetman, and Claire Gardent. Symbolic priors for rnn-based seman- tic parsing. In IJCAI, pages 4186-4192. Association for Computational Linguistics, 2017.","title":"Symbolic priors for rnn-based semantic parsing","authors":"Chunyang Xiao, Marc Dymetman, Claire Gardent","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/585"},{"position":26,"raw":"[Yang et al., 2016] Zichao Yang, Diyi Yang, Chris Dyer, et al. Hierarchical attention networks for document classi- fication. In NAACL, pages 1480-1489. ACL, 2016.","title":"Hierarchical attention networks for document classification","authors":"Yang","year":"2016","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yu et al., 2017] Rose Yu, Yaguang Li, Cyrus Shahabi, and Yan Liu. Deep learning: A generic approach for extreme condition traffic forecasting. In SDM, 2017.","title":"Deep learning: A generic approach for extreme condition traffic forecasting","authors":"Rose Yu, Yaguang Li, Cyrus Shahabi, Yan Liu","year":"2017","venue":"SDM","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2017] Chao Zhang, Keyang Zhang, Quan Yuan, et al. Regions, periods, activities: Uncovering ur- ban dynamics via cross-modal representation learning. In WWW, pages 361-370. ACM, 2017.","title":"Regions, periods, activities: Uncovering urban dynamics via cross-modal representation learning","authors":"Chao Zhang, Keyang Zhang, Quan Yuan","year":"2017","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2018] Huichu Zhang, Yu Zheng, and Yong Yu. Detecting urban anomalies using multiple spatio-temporal data sources. Ubicomp, 2(1):54, 2018.","title":"Detecting urban anomalies using multiple spatio-temporal data sources","authors":"Zhang","year":"2018","venue":"Ubicomp","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang et al., 2019] Chuxu Zhang, Dongjin Song, Yuncong Chen, et al. A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time se- ries data. In AAAI, volume 33, pages 1409-1416, 2019.","title":"A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data","authors":"Zhang","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zheng et al., 2014] Yu Zheng, Tong Liu, Yilun Wang, et al. Diagnosing new york city's noises with ubiquitous data. In Ubicomp, pages 715-725. ACM, 2014.","title":"Diagnosing new york city's noises with ubiquitous data","authors":"Yu Zheng, Tong Liu, Yilun Wang","year":"2014","venue":"Ubicomp","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zheng et al., 2015] Yu Zheng, Huichu Zhang, and Yong Yu. Detecting collective anomalies from multiple spatio- temporal datasets across different domains. In SIGSPA- TIAL. ACM, 2015.","title":"Detecting collective anomalies from multiple spatiotemporal datasets across different domains","authors":"Yu Zheng, Huichu Zhang, Yong Yu","year":"2015","venue":"SIGSPA-TIAL","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}