{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:24Z","timestamp":1786120824733,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818499","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"8575-8584","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TSLoc: Self-Supervised Faulty Node Localization Framework in Large-scale Training Clusters"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3961-8877","authenticated-orcid":false,"given":"Quan","family":"Zhou","sequence":"first","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9288-4787","authenticated-orcid":false,"given":"Changhua","family":"Pei","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2554-6490","authenticated-orcid":false,"given":"Yuanwei","family":"Lu","sequence":"additional","affiliation":[{"name":"Stepfun, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0364-1681","authenticated-orcid":false,"given":"Difeng","family":"Ma","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8534-4909","authenticated-orcid":false,"given":"Zexin","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6253-9808","authenticated-orcid":false,"given":"Jianhui","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Suzhou, Jiangshu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9113-2660","authenticated-orcid":false,"given":"Yibo","family":"Zhu","sequence":"additional","affiliation":[{"name":"StepFun, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6657-5806","authenticated-orcid":false,"given":"Daxin","family":"Jiang","sequence":"additional","affiliation":[{"name":"StepFun, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5113-838X","authenticated-orcid":false,"given":"Dan","family":"Pei","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0146-7257","authenticated-orcid":false,"given":"Jingjing","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4964-1135","authenticated-orcid":false,"given":"Gaogang","family":"Xie","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Principal component analysis","author":"Abdi H.","year":"2010","unstructured":"Abdi, H., and Williams, L. J. Principal component analysis. Wiley interdisciplinary reviews: computational statistics 2, 4 (2010), 433-459."},{"key":"e_1_3_2_1_2_1","first-page":"10","article-title":"Sand: streaming subsequence anomaly detection","volume":"14","author":"Boniol P.","year":"2021","unstructured":"Boniol, P., Paparrizos, J., Palpanas, T., and Franklin, M. J. Sand: streaming subsequence anomaly detection. Proceedings of the VLDB Endowment 14, 10 (2021), 1717-1729.","journal-title":"Proceedings of the VLDB Endowment"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"e_1_3_2_1_4_1","volume-title":"Revisiting distributed synchronous sgd. arXiv preprint arXiv:1604.00981","author":"Chen J.","year":"2016","unstructured":"Chen, J., Pan, X., Monga, R., Bengio, S., and Jozefowicz, R. Revisiting distributed synchronous sgd. arXiv preprint arXiv:1604.00981 (2016)."},{"key":"e_1_3_2_1_5_1","volume-title":"The mahalanobis distance. Chemometrics and intelligent laboratory systems 50, 1","author":"De Maesschalck R.","year":"2000","unstructured":"De Maesschalck, R., Jouan-Rimbaud, D., and Massart, D. L. The mahalanobis distance. Chemometrics and intelligent laboratory systems 50, 1 (2000), 1-18."},{"key":"e_1_3_2_1_6_1","volume-title":"Deepseek-v3 technical report. CoRR abs\/2412.19437","author":"DeepSeek AI","year":"2024","unstructured":"DeepSeek-AI, Liu, A., Feng, B., Xue, B., et al. Deepseek-v3 technical report. CoRR abs\/2412.19437 (2024)."},{"key":"e_1_3_2_1_7_1","first-page":"505","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Deng Y.","year":"2025","unstructured":"Deng, Y., Shi, X., Jiang, Z., Zhang, X., Zhang, L., Zhang, Z., Li, B., Song, Z., Zhu, H., Liu, G., et al. Minder: Faulty machine detection for large-scale distributed model training. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25) (2025), pp. 505-521."},{"key":"e_1_3_2_1_8_1","first-page":"505","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI '25)","author":"Deng Y.","year":"2025","unstructured":"Deng, Y., Shi, X., Jiang, Z., Zhang, X., Zhang, L., Zhang, Z., Li, B., Song, Z., Zhu, H., Liu, G., Li, F., Wang, S., Lin, H., Ye, J., and Yu, M. Minder: Faulty machine detection for large-scale distributed model training. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI '25) (2025), pp. 505-521."},{"key":"e_1_3_2_1_9_1","volume-title":"Boosting large-scale parallel training efficiency with c4: A communication-driven approach. arXiv preprint arXiv:2406.04594","author":"Dong J.","year":"2024","unstructured":"Dong, J., Luo, B., Zhang, J., Zhang, P., Feng, F., Zhu, Y., Liu, A., Chen, Z., Shi, Y., Jiao, H., et al. Boosting large-scale parallel training efficiency with c4: A communication-driven approach. arXiv preprint arXiv:2406.04594 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"The llama 3 herd of models. arXiv preprint arXiv:2407.21783","author":"Grattafiori A.","year":"2024","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Vaughan, A., et al. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter S.","year":"1997","unstructured":"Hochreiter, S., and Schmidhuber, J. Long short-term memory. Neural computation 9, 8 (1997), 1735-1780."},{"key":"e_1_3_2_1_12_1","volume-title":"Adaptive mixtures of local experts. Neural computation 3, 1","author":"Jacobs R. A.","year":"1991","unstructured":"Jacobs, R. A., Jordan, M. I., Nowlan, S. J., and Hinton, G. E. Adaptive mixtures of local experts. Neural computation 3, 1 (1991), 79-87."},{"key":"e_1_3_2_1_13_1","first-page":"745","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Z.","year":"2024","unstructured":"Jiang, Z., Lin, H., Zhong, Y., Huang, Q., Chen, Y., Zhang, Z., Peng, Y., Li, X., Xie, C., Nong, S., et al. : Scaling large language model training to more than 10,000 . In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24) (2024), pp. 745-760."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2494232.2465753"},{"key":"e_1_3_2_1_15_1","volume-title":"Auto-encoding variational bayes","author":"Kingma D. P.","year":"2013","unstructured":"Kingma, D. P., Welling, M., et al. Auto-encoding variational bayes, 2013."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539041"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP52600.2021.00043"},{"key":"e_1_3_2_1_18_1","first-page":"15","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Liu K.","year":"2023","unstructured":"Liu, K., Jiang, Z., Zhang, J., Wei, H., Zhong, X., Tan, L., Pan, T., and Huang, T. Hostping: Diagnosing intra-host network bottlenecks in servers. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23) (2023), pp. 15-29."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00014"},{"key":"e_1_3_2_1_20_1","first-page":"793","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI '20)","author":"Ma M.","year":"2020","unstructured":"Ma, M., Kang, Y., Zhang, S., Wu, Z., Liu, H., Chen, Z., and Pei, D. Dejavu: Actionable and interpretable fault localization for recurring failures in online service systems. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI '20) (2020), pp. 793-811."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCCC.2016.7820614"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330680"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CloudIntelligence52565.2021.00011"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098144"},{"key":"e_1_3_2_1_25_1","volume-title":"Learning structured output representation using deep conditional generative models. Advances in neural information processing systems 28","author":"Sohn K.","year":"2015","unstructured":"Sohn, K., Lee, H., and Yan, X. Learning structured output representation using deep conditional generative models. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514067"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSOS49614.2020.00041"},{"key":"e_1_3_2_1_28_1","volume-title":"Kolmogorov-arnold networks (kans) for time series analysis. arXiv preprint arXiv:2405.08790","author":"Vaca-Rubio C. J.","year":"2024","unstructured":"Vaca-Rubio, C. J., Blanco, L., Pereira, R., and Caus, M. Kolmogorov-arnold networks (kans) for time series analysis. arXiv preprint arXiv:2405.08790 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678708"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645710"},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Learning Representations","author":"Wu H.","year":"2023","unstructured":"Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., and Long, M. Timesnet: Temporal 2d-variation modeling for general time series analysis. In International Conference on Learning Representations (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185996"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449905"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616249"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510180"},{"key":"e_1_3_2_1_36_1","volume-title":"Forty-second International Conference on Machine Learning","author":"Zhou Q.","year":"2025","unstructured":"Zhou, Q., Pei, C., Sun, F., Han, J., Gao, Z., Pei, D., Zhang, H., Xie, G., and Li, J. KAN-AD: Time series anomaly detection with kolmogorov-arnold networks. In Forty-second International Conference on Machine Learning (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:15:49Z","timestamp":1786065349000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":36,"alternative-id":["10.1145\/3770855.3818499","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818499","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}