{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T14:39:33Z","timestamp":1787841573144,"version":"build-2784847793"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T00:00:00Z","timestamp":1630627200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2022,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Effectively detecting anomalous nodes in attributed networks is crucial for the success of many real-world applications such as fraud and intrusion detection. Existing approaches have difficulties with three major issues: sparsity and nonlinearity capturing, residual modeling, and network smoothing. We propose Residual Graph Convolutional Network (ResGCN), an attention-based deep residual modeling approach that can tackle these issues: modeling the attributed networks with GCN allows to capture the sparsity and nonlinearity, utilizing a deep neural network allows direct residual ing from the input, and a residual-based attention mechanism reduces the adverse effect from anomalous nodes and prevents over-smoothing. Extensive experiments on several real-world attributed networks demonstrate the effectiveness of ResGCN in detecting anomalies.<\/jats:p>","DOI":"10.1007\/s10994-021-06044-0","type":"journal-article","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T18:53:10Z","timestamp":1630695190000},"page":"519-541","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":92,"title":["ResGCN: attention-based deep residual modeling for anomaly detection on attributed networks"],"prefix":"10.1007","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3739-5627","authenticated-orcid":false,"given":"Yulong","family":"Pei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianjin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Werner","family":"van Ipenburg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mykola","family":"Pechenizkiy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,3]]},"reference":[{"issue":"3","key":"6044_CR1","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1007\/s10618-014-0365-y","volume":"29","author":"L Akoglu","year":"2015","unstructured":"Akoglu, L., Tong, H., & Koutra, D. (2015). Graph based anomaly detection and description: a survey. Data mining and knowledge discovery, 29(3), 626\u2013688.","journal-title":"Data mining and knowledge discovery"},{"key":"6044_CR2","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1609\/aaai.v33i01.330112","volume":"33","author":"S Bandyopadhyay","year":"2019","unstructured":"Bandyopadhyay, S., Lokesh, N., & Murty, M. N. (2019). Outlier aware network embedding for attributed networks. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 12\u201319.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"6044_CR3","doi-asserted-by":"crossref","unstructured":"Bandyopadhyay, S., Vivek, S. V., & Murty, M. (2020). Outlier resistant unsupervised deep architectures for attributed network embedding. (pp. 25\u201333)","DOI":"10.1145\/3336191.3371788"},{"key":"6044_CR4","doi-asserted-by":"crossref","unstructured":"Barbieri, N., Bonchi, F., & Manco, G. (2014). Who to follow and why: link prediction with explanations. (pp. 1266\u20131275)","DOI":"10.1145\/2623330.2623733"},{"issue":"1","key":"6044_CR5","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/SURV.2013.052213.00046","volume":"16","author":"MH Bhuyan","year":"2013","unstructured":"Bhuyan, M. H., Bhattacharyya, D. K., & Kalita, J. K. (2013). Network anomaly detection: methods, systems and tools. IEEE Communications Surveys & Tutorials, 16(1), 303\u2013336.","journal-title":"IEEE Communications Surveys & Tutorials"},{"key":"6044_CR6","doi-asserted-by":"crossref","unstructured":"Breunig, M. M., Kriegel, H. P., Ng, R. T., & Sander, J. (2000). Lof: identifying density-based local outliers. (pp. 93\u2013104)","DOI":"10.1145\/335191.335388"},{"key":"6044_CR7","doi-asserted-by":"crossref","unstructured":"Brochier, R., Guille, A., & Velcin, J. (2019). Link prediction with mutual attention for text-attributed networks. (pp. 283\u2013284)","DOI":"10.1145\/3308560.3316587"},{"issue":"5","key":"6044_CR8","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1109\/TKDE.2018.2849727","volume":"31","author":"P Cui","year":"2018","unstructured":"Cui, P., Wang, X., Pei, J., & Zhu, W. (2018). A survey on network embedding. IEEE Transactions on Knowledge and Data Engineering, 31(5), 833\u2013852.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"6044_CR9","unstructured":"Dabkowski P, Gal Y (2017) Real time image saliency for black box classifiers. In: Advances in Neural Information Processing Systems, pp 6967\u20136976"},{"key":"6044_CR10","doi-asserted-by":"crossref","unstructured":"Ding, K., Li, J., Bhanushali, R., & Liu, H. (2019a). Deep anomaly detection on attributed networks. (pp. 594\u2013602)","DOI":"10.1137\/1.9781611975673.67"},{"key":"6044_CR11","doi-asserted-by":"crossref","unstructured":"Ding, K., Li, J., & Liu, H. (2019b). Interactive anomaly detection on attributed networks. (pp. 357\u2013365)","DOI":"10.1145\/3289600.3290964"},{"key":"6044_CR12","doi-asserted-by":"crossref","unstructured":"Eberle W, Holder L (2007) Discovering structural anomalies in graph-based data. In: Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007), IEEE, pp 393\u2013398","DOI":"10.1109\/ICDMW.2007.91"},{"key":"6044_CR13","doi-asserted-by":"crossref","unstructured":"Falih, I., Grozavu, N., Kanawati, R., & Bennani, Y. (2018). Community detection in attributed network. (pp. 1299\u20131306)","DOI":"10.1145\/3184558.3191570"},{"key":"6044_CR14","doi-asserted-by":"crossref","unstructured":"Gao, J., Liang, F., Fan, W., Wang, C., Sun, Y., & Han, J. (2010). On community outliers and their efficient detection in information networks. (pp. 813\u2013822)","DOI":"10.1145\/1835804.1835907"},{"issue":"9","key":"6044_CR15","doi-asserted-by":"crossref","first-page":"2250","DOI":"10.1109\/TKDE.2013.184","volume":"26","author":"M Gupta","year":"2013","unstructured":"Gupta, M., Gao, J., Aggarwal, C. C., & Han, J. (2013). Outlier detection for temporal data: A survey. IEEE Transactions on Knowledge and Data Engineering, 26(9), 2250\u20132267.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"6044_CR16","doi-asserted-by":"crossref","unstructured":"Guti\u00e9rrez-G\u00f3mez L, Bovet A, Delvenne JC (2019) Multi-scale anomaly detection on attributed networks. arXiv preprint arXiv:191204144","DOI":"10.1609\/aaai.v34i01.5409"},{"key":"6044_CR17","unstructured":"Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, pp 1024\u20131034"},{"key":"6044_CR18","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, J., & Hu, X. (2017a). Accelerated attributed network embedding. (pp. 633\u2013641)","DOI":"10.1137\/1.9781611974973.71"},{"key":"6044_CR19","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, J., & Hu, X. (2017b). Label informed attributed network embedding. (pp. 731\u2013739)","DOI":"10.1145\/3018661.3018667"},{"key":"6044_CR20","doi-asserted-by":"crossref","unstructured":"Kannan, R., Woo, H., Aggarwal, C. C., & Park, H. (2017). Outlier detection for text data. (pp. 489\u2013497)","DOI":"10.1137\/1.9781611974973.55"},{"key":"6044_CR21","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980"},{"key":"6044_CR22","unstructured":"Kipf TN, Welling M (2016a) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:160902907"},{"key":"6044_CR23","unstructured":"Kipf TN, Welling M (2016b) Variational graph auto-encoders. arXiv preprint arXiv:161107308"},{"key":"6044_CR24","doi-asserted-by":"crossref","unstructured":"Li J, Dani H, Hu X, Liu H (2017) Radar: Residual analysis for anomaly detection in attributed networks. In: IJCAI, pp 2152\u20132158","DOI":"10.24963\/ijcai.2017\/299"},{"key":"6044_CR25","doi-asserted-by":"crossref","unstructured":"Li, J., Cheng, K., Wu, L., & Liu, H. (2018a). Streaming link prediction on dynamic attributed networks. (pp. 369\u2013377)","DOI":"10.1145\/3159652.3159674"},{"key":"6044_CR26","doi-asserted-by":"crossref","unstructured":"Li Q, Han Z, Wu XM (2018b) Deeper insights into graph convolutional networks for semi-supervised learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol\u00a032","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"6044_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Sha, C., Huang, X., & Zhang, Y. (2018c). Community detection in attributed graphs: An embedding approach.","DOI":"10.1609\/aaai.v32i1.11274"},{"key":"6044_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, X., Li, J., Du, M., & Zou, N. (2019). Specae: Spectral autoencoder for anomaly detection in attributed networks. (pp. 2233\u20132236)","DOI":"10.1145\/3357384.3358074"},{"key":"6044_CR29","doi-asserted-by":"crossref","unstructured":"Liang, J., Jacobs, P., Sun, J., & Parthasarathy, S. (2018). Semi-supervised embedding in attributed networks with outliers. (pp. 153\u2013161)","DOI":"10.1137\/1.9781611975321.18"},{"key":"6044_CR30","unstructured":"Ma, J., Cui, P., Kuang, K., Wang, X., & Zhu, W. (2019). Disentangled graph convolutional networks. (pp. 4212\u20134221)"},{"issue":"1","key":"6044_CR31","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1146\/annurev.soc.27.1.415","volume":"27","author":"M McPherson","year":"2001","unstructured":"McPherson, M., Smith-Lovin, L., & Cook, J. M. (2001). Birds of a feather: Homophily in social networks. Annual review of sociology, 27(1), 415\u2013444.","journal-title":"Annual review of sociology"},{"key":"6044_CR32","doi-asserted-by":"crossref","unstructured":"Meng, Z., Liang, S., Bao, H., & Zhang, X. (2019). Co-embedding attributed networks. (pp. 393\u2013401)","DOI":"10.1145\/3289600.3291015"},{"key":"6044_CR33","first-page":"28","volume":"17","author":"V Metsis","year":"2006","unstructured":"Metsis, V., Androutsopoulos, I., & Paliouras, G. (2006). Spam filtering with naive bayes-which naive bayes? CEAS, Mountain View, CA, 17, 28\u201369.","journal-title":"CEAS, Mountain View, CA"},{"key":"6044_CR34","doi-asserted-by":"crossref","unstructured":"M\u00fcller, E., S\u00e1nchez, P. I., M\u00fclle, Y., & B\u00f6hm, K. (2013). Ranking outlier nodes in subspaces of attributed graphs. (pp. 216\u2013222)","DOI":"10.1109\/ICDEW.2013.6547453"},{"key":"6044_CR35","doi-asserted-by":"crossref","unstructured":"Noble, C. C., & Cook, D. J. (2003). Graph-based anomaly detection. (pp. 631\u2013636)","DOI":"10.1145\/956750.956831"},{"key":"6044_CR36","unstructured":"Pei, Y., Chakraborty, N., & Sycara, K. (2015). Nonnegative matrix tri-factorization with graph regularization for community detection in social networks."},{"key":"6044_CR37","doi-asserted-by":"crossref","unstructured":"Pei, Y., Du, X., Zhang, J., Fletcher, G., & Pechenizkiy, M. (2020). struc2gauss: Structural role preserving network embedding via gaussian embedding.","DOI":"10.1007\/s10618-020-00684-x"},{"key":"6044_CR38","doi-asserted-by":"crossref","unstructured":"Peng Z, Luo M, Li J, Liu H, Zheng Q (2018) Anomalous: A joint modeling approach for anomaly detection on attributed networks. In: IJCAI, pp 3513\u20133519","DOI":"10.24963\/ijcai.2018\/488"},{"key":"6044_CR39","doi-asserted-by":"crossref","unstructured":"Perozzi, B., & Akoglu, L. (2016). Scalable anomaly ranking of attributed neighborhoods. (pp. 207\u2013215)","DOI":"10.1137\/1.9781611974348.24"},{"key":"6044_CR40","doi-asserted-by":"crossref","unstructured":"Perozzi, B., Akoglu, L., Iglesias S\u00e1nchez, P., & M\u00fcller, E. (2014). Focused clustering and outlier detection in large attributed graphs. (pp. 1346\u20131355)","DOI":"10.1145\/2623330.2623682"},{"key":"6044_CR41","doi-asserted-by":"crossref","unstructured":"Ruff, L., Zemlyanskiy, Y., Vandermeulen, R., Schnake, T., & Kloft, M. (2019). Self-attentive, multi-context one-class classification for unsupervised anomaly detection on text. (pp. 4061\u20134071)","DOI":"10.18653\/v1\/P19-1398"},{"key":"6044_CR42","doi-asserted-by":"crossref","unstructured":"Skillicorn, D. B. (2007). Detecting anomalies in graphs. (pp. 209\u2013216)","DOI":"10.1109\/ISI.2007.379473"},{"issue":"5","key":"6044_CR43","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1109\/TKDE.2007.1009","volume":"19","author":"X Song","year":"2007","unstructured":"Song, X., Wu, M., Jermaine, C., & Ranka, S. (2007). Conditional anomaly detection. IEEE Transactions on knowledge and Data Engineering, 19(5), 631\u2013645.","journal-title":"IEEE Transactions on knowledge and Data Engineering"},{"key":"6044_CR44","unstructured":"Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv preprint arXiv:171010903 1(2)"},{"key":"6044_CR45","unstructured":"Xu, K., Li, C., Tian, Y., Sonobe, T., Ki, Kawarabayashi, & Jegelka, S. (2018). Representation learning on graphs with jumping knowledge networks. (pp. 5453\u20135462)"},{"key":"6044_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, D., He, J., Yang, H., & Fan, W. (2018). Sparc: Self-paced network representation for few-shot rare category characterization. (pp. 2807\u20132816)","DOI":"10.1145\/3219819.3219968"},{"key":"6044_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, D., Cui, P., Wang, D., & Zhu, W. (2018). Deep variational network embedding in wasserstein space. (pp. 2827\u20132836)","DOI":"10.1145\/3219819.3220052"},{"key":"6044_CR48","doi-asserted-by":"crossref","unstructured":"Zhu, D., Zhang, Z., Cui, P., & Zhu, W. (2019). Robust graph convolutional networks against adversarial attacks. (pp. 1399\u20131407)","DOI":"10.1145\/3292500.3330851"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06044-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06044-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06044-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T10:49:56Z","timestamp":1673174996000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06044-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,3]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,2]]}},"alternative-id":["6044"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06044-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,3]]},"assertion":[{"value":"30 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest\/competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}