{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,9]],"date-time":"2026-11-09T10:05:18Z","timestamp":1794218718100,"version":"4.8.0"},"reference-count":44,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"Shenzhen Science and Technology Program","award":["SYSPG20241211173609009"],"award-info":[{"award-number":["SYSPG20241211173609009"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62472091"],"award-info":[{"award-number":["62472091"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,4,2]]},"abstract":"<jats:p>\n                    Detecting anomalies in system logs effectively is crucial for ensuring software reliability. However, most existing log anomaly detection methods operate under the assumption that anomalous patterns remain consistent between the training and testing phases. This limitation hinders their ability to identify previously unseen anomalies. In real-world scenarios, software upgrades may introduce novel anomalous patterns that deviate from the training distribution, a challenge we refer to as anomaly shift. To address this, we propose\n                    <jats:italic toggle=\"yes\">UnseenLog,<\/jats:italic>\n                    a novel log anomaly detection framework designed to identify anomalous code files whose representations shift from the training distribution.\n                    <jats:italic toggle=\"yes\">UnseenLog<\/jats:italic>\n                    introduces a MinMax strategy to select augmented anomaly samples that strike a balance between reliability and novelty, enriching the training set with additional pseudo-label samples. Furthermore, we propose Recurrent Iterative Selection and Enhancement (RISE), a training scheme that progressively enhances the graph model through competitive model selection and adaptive data enhancement, thereby improving robustness against novel anomalies. Extensive experiments on real-world datasets demonstrate that\n                    <jats:italic toggle=\"yes\">UnseenLog<\/jats:italic>\n                    significantly outperforms state-of-the-art baselines, achieving consistent improvements in multiple real-world datasets. The code is available at https:\/\/github.com\/ZhuoxingZhang\/UnseenLog.\n                  <\/jats:p>","DOI":"10.1145\/3786705","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:54:13Z","timestamp":1775584453000},"page":"1-23","source":"Crossref","is-referenced-by-count":2,"title":["Unseen Anomaly Detection from System Logs"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0163-554X","authenticated-orcid":false,"given":"Yanni","family":"Tang","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Auckland, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6736-4501","authenticated-orcid":false,"given":"Zhuoxing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Auckland, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1374-395X","authenticated-orcid":false,"given":"Lanting","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1816-2863","authenticated-orcid":false,"given":"Sebastian","family":"Link","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Auckland, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5041-6122","authenticated-orcid":false,"given":"Wu","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer and Information Science, Southwest University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0984-1629","authenticated-orcid":false,"given":"Kaiqi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shenzhen Key Laboratory of Internet Information Collaboration, Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00013"},{"key":"e_1_2_1_2_1","first-page":"22131","article-title":"Learning causally invariant representations for out-of-distribution generalization on graphs","volume":"35","author":"Chen Yongqiang","year":"2022","unstructured":"Yongqiang Chen, Yonggang Zhang, Yatao Bian, Han Yang, MA Kaili, Binghui Xie, Tongliang Liu, Bo Han, and James Cheng. 2022. Learning causally invariant representations for out-of-distribution generalization on graphs. Advances in Neural Information Processing Systems, Vol. 35 (2022), 22131-22148.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134015"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583268"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27764"},{"key":"e_1_2_1_6_1","first-page":"1","article-title":"Logbert: Log anomaly detection via bert. In International joint conference on neural networks","author":"Guo Haixuan","year":"2021","unstructured":"Haixuan Guo, Shuhan Yuan, and Xintao Wu. 2021. Logbert: Log anomaly detection via bert. In International joint conference on neural networks. IEEE, 1-8.","journal-title":"IEEE"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3053371"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2017.2762673"},{"key":"e_1_2_1_9_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510155"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654966"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00018"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3722212.3724427"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2007.46"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2889160.2889232"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS60937.2023.00014"},{"key":"e_1_2_1_17_1","volume-title":"TP-GNN: Continuous Dynamic Graph Neural Network for Graph Classification. IEEE 40th International Conference on Data Engineering (ICDE)","author":"Liu Jie","year":"2024","unstructured":"Jie Liu, Yanni Tang, Kaiqi Zhao, Jiamou Liu, and Wu Chen. 2024. TP-GNN: Continuous Dynamic Graph Neural Network for Graph Classification. IEEE 40th International Conference on Data Engineering (ICDE) (2024)."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2843336"},{"key":"e_1_2_1_19_1","volume-title":"2010 USENIX Annual Technical Conference (USENIX ATC 10)","author":"Lou Jian-Guang","year":"2010","unstructured":"Jian-Guang Lou, Qiang Fu, Shenqi Yang, Ye Xu, and Jiang Li. 2010. Mining invariants from console logs for system problem detection. In 2010 USENIX Annual Technical Conference (USENIX ATC 10)."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3393109"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3677139"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/658"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00148"},{"key":"e_1_2_1_24_1","first-page":"133","volume-title":"LISA","volume":"4","author":"Rouillard John P","year":"2004","unstructured":"John P Rouillard. 2004. Real-time Log File Analysis Using the Simple Event Correlator (SEC).. In LISA, Vol. 4. 133-150."},{"key":"e_1_2_1_25_1","volume-title":"Distributionally Robust Neural Networks. In International Conference on Learning Representations.","author":"Sagawa Shiori","year":"2020","unstructured":"Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang. 2020. Distributionally Robust Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/214"},{"key":"e_1_2_1_27_1","volume-title":"International Conference on Machine Learning. PMLR, 21076-21089","author":"Tang Jianheng","year":"2022","unstructured":"Jianheng Tang, Jiajin Li, Ziqi Gao, and Jia Li. 2022. Rethinking graph neural networks for anomaly detection. In International Conference on Machine Learning. PMLR, 21076-21089."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3705829.3705840"},{"key":"e_1_2_1_29_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Veli\u010dkovi\u0107 Petar","year":"2017","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75762-5_6"},{"key":"e_1_2_1_31_1","volume-title":"Open-World Semi-Supervised Learning for Node Classification. In 2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2723-2736","author":"Wang Yanling","year":"2024","unstructured":"Yanling Wang, Jing Zhang, Lingxi Zhang, Lixin Liu, Yuxiao Dong, Cuiping Li, Hong Chen, and Hongzhi Yin. 2024. Open-World Semi-Supervised Learning for Node Classification. In 2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2723-2736."},{"key":"e_1_2_1_32_1","volume-title":"Discovering invariant rationales for graph neural networks. arXiv preprint arXiv:2201.12872","author":"Wu Ying-Xin","year":"2022","unstructured":"Ying-Xin Wu, Xiang Wang, An Zhang, Xiangnan He, and Tat-Seng Chua. 2022. Discovering invariant rationales for graph neural networks. arXiv preprint arXiv:2201.12872 (2022)."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS.2019.00033"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/QRS57517.2022.00039"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629587"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119576"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00130"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523649.2523670"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01118"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26318"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510180"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671725"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3338931"},{"key":"e_1_2_1_44_1","volume-title":"From stars to subgraphs: Uplifting any GNN with local structure awareness. arXiv preprint arXiv:2110.03753","author":"Zhao Lingxiao","year":"2021","unstructured":"Lingxiao Zhao, Wei Jin, Leman Akoglu, and Neil Shah. 2021. From stars to subgraphs: Uplifting any GNN with local structure awareness. arXiv preprint arXiv:2110.03753 (2021)."}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:02:24Z","timestamp":1775592144000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,4,2]]}},"alternative-id":["10.1145\/3786705"],"URL":"https:\/\/doi.org\/10.1145\/3786705","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]}}}