{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:14:46Z","timestamp":1770815686552,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s00607-023-01235-0","type":"journal-article","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T13:02:49Z","timestamp":1699966969000},"page":"2211-2237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Incorporating self-attentions into robust spatial-temporal graph representation learning against dynamic graph perturbations"],"prefix":"10.1007","volume":"106","author":[{"given":"Zhuo","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0877-1064","authenticated-orcid":false,"given":"Chengliang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xusheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinrun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,14]]},"reference":[{"key":"1235_CR1","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proceedings of the international conference on learning representations"},{"key":"1235_CR2","unstructured":"Velikovi P et al (2018) Graph attention networks. In: International conference on learning representations"},{"issue":"7","key":"1235_CR3","doi-asserted-by":"publisher","first-page":"485","DOI":"10.3390\/ijgi10070485","volume":"10","author":"J Bai","year":"2021","unstructured":"Bai J et al (2021) A3T-GCN: attention temporal graph convolutional network for traffic forecasting. ISPRS Int J Geo Inf 10(7):485","journal-title":"ISPRS Int J Geo Inf"},{"key":"1235_CR4","doi-asserted-by":"crossref","unstructured":"Pareja A et al (2020) Evolvegcn: evolving graph convolutional networks for dynamic graphs. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, no 04","DOI":"10.1609\/aaai.v34i04.5984"},{"issue":"7","key":"1235_CR5","doi-asserted-by":"publisher","first-page":"7513","DOI":"10.1007\/s10489-021-02518-9","volume":"52","author":"J Chen","year":"2022","unstructured":"Chen J, Wang X, Xu X (2022) GC-LSTM: graph convolution embedded LSTM for dynamic network link prediction. Appl Intell 52(7):7513\u20137528","journal-title":"Appl Intell"},{"key":"1235_CR6","doi-asserted-by":"crossref","unstructured":"Fan Y, Yao Y, Joe-Wong C (2021) Gcn-se: attention as explainability for node classification in dynamic graphs. In: 2021 IEEE international conference on data mining (ICDM). IEEE","DOI":"10.1109\/ICDM51629.2021.00123"},{"key":"1235_CR7","unstructured":"Zhu L et al (2021) Adversarial diffusion attacks on graph-based traffic prediction models. arXiv preprint arXiv:2104.09369"},{"key":"1235_CR8","first-page":"4756","volume":"33","author":"Jiaqi Ma","year":"2020","unstructured":"Ma Jiaqi, Ding Shuangrui, Mei Qiaozhu (2020) Towards more practical adversarial attacks on graph neural networks. Adv Neural Inf Process Syst 33:4756\u20134766","journal-title":"Adv Neural Inf Process Syst"},{"key":"1235_CR9","unstructured":"Liu F, Moreno LM, Sun L (2021) One vertex attack on graph neural networks-based spatiotemporal forecasting. In: ICLR Conference OpenReview"},{"key":"1235_CR10","first-page":"7637","volume":"34","author":"S Geisler","year":"2021","unstructured":"Geisler S et al (2021) Robustness of graph neural networks at scale. Adv Neural Inf Process Syst 34:7637\u20137649","journal-title":"Adv Neural Inf Process Syst"},{"key":"1235_CR11","doi-asserted-by":"crossref","unstructured":"Li H et al (2022) Black-box adversarial attack and defense on graph neural networks. In: 2022 IEEE 38th international conference on data engineering (ICDE). IEEE","DOI":"10.1109\/ICDE53745.2022.00081"},{"key":"1235_CR12","doi-asserted-by":"crossref","unstructured":"Wang B, Li Y, Zhou P (2022) Bandits for structure perturbation-based black-box attacks to graph neural networks with theoretical guarantees. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52688.2022.01302"},{"key":"1235_CR13","doi-asserted-by":"crossref","unstructured":"Xu K et al (2019) Topology attack and defense for graph neural networks: An optimization perspective. In: 28th International joint conference on artificial intelligence, IJCAI 2019. International joint conferences on artificial intelligence","DOI":"10.24963\/ijcai.2019\/550"},{"key":"1235_CR14","doi-asserted-by":"crossref","unstructured":"Z\u00fcgner D, G\u00fcnnemann S (2019) Adversarial attacks on graph neural networks via meta learning. arXiv preprint arXiv:1902.08412","DOI":"10.24963\/ijcai.2019\/872"},{"key":"1235_CR15","doi-asserted-by":"crossref","unstructured":"Chang et al (2020) A restricted black-box adversarial framework towards attacking graph embedding models. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, no. 04","DOI":"10.1609\/aaai.v34i04.5741"},{"key":"1235_CR16","doi-asserted-by":"crossref","unstructured":"Sharma K et al (2022) Imperceptible adversarial attacks on discrete-time dynamic graph models. In: NeurIPS 2022 temporal graph learning workshop","DOI":"10.1145\/3580305.3599517"},{"key":"1235_CR17","unstructured":"The dblp team: dblp computer science bibliography. Monthly snapshot release of November 2019. https:\/\/dblp.org\/xml\/release\/dblp-2019-11-01.xml.gz"},{"key":"1235_CR18","doi-asserted-by":"crossref","unstructured":"Zhuang J, Al Hasan M (2022) Defending graph convolutional networks against dynamic graph perturbations via Bayesian self-supervision. In: AAAI","DOI":"10.1609\/aaai.v36i4.20362"},{"key":"1235_CR19","doi-asserted-by":"crossref","unstructured":"Sankar A et al (2020) Dysat: deep neural representation learning on dynamic graphs via self-attention networks. In: Proceedings of the 13th international conference on web search and data mining","DOI":"10.1145\/3336191.3371845"},{"key":"1235_CR20","doi-asserted-by":"crossref","unstructured":"Zhu D et al (2019) Robust graph convolutional networks against adversarial attacks. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","DOI":"10.1145\/3292500.3330851"},{"key":"1235_CR21","doi-asserted-by":"crossref","unstructured":"Jin W et al (2021) Node similarity preserving graph convolutional networks. In: Proceedings of the 14th ACM international conference on web search and data mining","DOI":"10.1145\/3437963.3441735"},{"key":"1235_CR22","unstructured":"Zhao X et al (2021) Expressive 1-Lipschitz neural networks for robust multiple graph learning against adversarial attacks. In: International conference on machine learning. PMLR"},{"key":"1235_CR23","unstructured":"Vaswani A et al (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"1235_CR24","doi-asserted-by":"crossref","unstructured":"Wu H et al (2019) Adversarial examples on graph data: Deep insights into attack and defense. arXiv preprint arXiv:1903.01610","DOI":"10.24963\/ijcai.2019\/669"},{"key":"1235_CR25","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s00607-020-00849-y","volume":"103","author":"Liu Duen-Ren","year":"2021","unstructured":"Duen-Ren Liu et al (2021) Air pollution prediction based on factory-aware attentional LSTM neural network. Computing 103:75\u201398","journal-title":"Computing"},{"issue":"1","key":"1235_CR26","doi-asserted-by":"publisher","first-page":"20137","DOI":"10.1038\/s41598-020-76799-4","volume":"10","author":"Ahmad Zareie","year":"2020","unstructured":"Zareie Ahmad, Sakellariou Rizos (2020) Similarity-based link prediction in social networks using latent relationships between the users. Sci Rep 10(1):20137","journal-title":"Sci Rep"},{"key":"1235_CR27","unstructured":"He T et al (2022) Not all neighbors are worth attending to: graph selective attention networks for semi-supervised learning. arXiv:2210.07715"},{"key":"1235_CR28","doi-asserted-by":"crossref","unstructured":"Ning K-P et al (2021) Improving model robustness by adaptively correcting perturbation levels with active queries. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, no. 10","DOI":"10.1609\/aaai.v35i10.17106"},{"key":"1235_CR29","doi-asserted-by":"crossref","unstructured":"Shanthamallu US et al (2018) A regularized attention mechanism for graph attention networks. In: ICASSP 2020\u20142020 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 3372\u20133376","DOI":"10.1109\/ICASSP40776.2020.9054363"},{"key":"1235_CR30","doi-asserted-by":"crossref","unstructured":"Tang X et al (2020) Transferring robustness for graph neural network against poisoning attacks. In: Proceedings of the 13th international conference on web search and data mining","DOI":"10.1145\/3336191.3371851"},{"key":"1235_CR31","doi-asserted-by":"crossref","unstructured":"Yang Z et al (2020) Understanding negative sampling in graph representation learning. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining","DOI":"10.1145\/3394486.3403218"},{"key":"1235_CR32","doi-asserted-by":"publisher","first-page":"2587","DOI":"10.1007\/s00607-020-00842-5","volume":"102","author":"Wang Kai","year":"2020","unstructured":"Kai Wang et al (2020) Enhancing knowledge graph embedding by composite neighbors for link prediction. Computing 102:2587\u20132606","journal-title":"Computing"},{"key":"1235_CR33","doi-asserted-by":"crossref","unstructured":"Nair AB et al (2022) Comparative study of centrality based adversarial attacks on graph convolutional network model for node classification. In: 2022 7th International conference on communication and electronics systems (ICCES). IEEE","DOI":"10.1109\/ICCES54183.2022.9835948"},{"key":"1235_CR34","doi-asserted-by":"crossref","unstructured":"Ma J, Deng J, Mei Q (2022) Adversarial attack on graph neural networks as an influence maximization problem. In: Proceedings of the fifteenth ACM international conference on web search and data mining","DOI":"10.1145\/3488560.3498497"},{"key":"1235_CR35","unstructured":"Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. Adv Neural Inf Process Syst 30"},{"issue":"1","key":"1235_CR36","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1137\/16M1066142","volume":"15","author":"D Taylor","year":"2017","unstructured":"Taylor D et al (2017) Eigenvector-based centrality measures for temporal networks. Multiscale Model Simul 15(1):537\u2013574","journal-title":"Multiscale Model Simul"},{"key":"1235_CR37","doi-asserted-by":"crossref","unstructured":"Rozemberczki B et al (2021) Pytorch geometric temporal: Spatiotemporal signal processing with neural machine learning models. In: Proceedings of the 30th ACM international conference on information & knowledge management","DOI":"10.1145\/3459637.3482014"},{"key":"1235_CR38","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization. Comput Sci"},{"key":"1235_CR39","unstructured":"UpAndRunning. HCP Protocols. Human Connectome Project. https:\/\/www.humanconnectome.org\/hcp-protocols. Accessed 31 Dec 2022"},{"key":"1235_CR40","doi-asserted-by":"crossref","unstructured":"Torra V, Salas J (2019) Graph perturbation as noise graph addition: a new perspective for graph anonymization","DOI":"10.1007\/978-3-030-31500-9_8"},{"key":"1235_CR41","unstructured":"Hay M, Miklau G, Jensen D, Weis P, Srivastava S. Anonymizing social networks, Technical report No. 07-19, Computer Science Department, University of Massachusetts Amherst, UMass Amherst"},{"key":"1235_CR42","doi-asserted-by":"crossref","unstructured":"Li Y et al (2021) DeepRobust: a platform for adversarial attacks and defenses. In: AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v35i18.18017"},{"key":"1235_CR43","unstructured":"Bojchevski A, G\u00fcnnemann S (2019) Adversarial attacks on node embeddings via graph poisoning. In: International conference on machine learning. PMLR"},{"key":"1235_CR44","unstructured":"Li Y et al (2017) Diffusion convolutional recurrent neural network: data-driven traffic forecasting"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-023-01235-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-023-01235-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-023-01235-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T07:05:16Z","timestamp":1719212716000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-023-01235-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,14]]},"references-count":44,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1235"],"URL":"https:\/\/doi.org\/10.1007\/s00607-023-01235-0","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,14]]},"assertion":[{"value":"26 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors in this work declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"RSTGNN model code is public to researchers for further exploration in robust dynamic-graph based models. There are available at .","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}]}}