{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:41Z","timestamp":1750309541320,"version":"3.41.0"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:00Z","timestamp":1740182400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62072204"],"award-info":[{"award-number":["62072204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,4,30]]},"abstract":"<jats:p>\n            Learning a good similarity measure for large-scale high-dimensional data is a crucial task in machine learning applications, yet it poses a significant challenge. Distributed minibatch Stochastic Gradient Descent (SGD) serves as an efficient optimization method in large-scale distributed training, allowing linear speedup in proportion to the number of workers. However, communication efficiency in distributed SGD requires a sufficiently large minibatch size, presenting two distinct challenges. Firstly, a large minibatch size leads to high memory usage and computational complexity during parallel training of high-dimensional models. Second, a larger batch size of data reduces the convergence rate. To overcome these challenges, we propose an Efficient Distributed Sparse Relative Similarity Learning (\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(\\mathbf{\\mathsf{EDSRSL}}\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            ) framework. This framework integrates two strategies: local minibatch SGD and sparse relative similarity learning. By effectively reducing the number of updates through synchronous delay while maintaining a large batch size, we address the issue of high computational cost. Additionally, we incorporate sparse model learning into the training process, significantly reducing computational cost. This article also provides theoretical proof that the convergence rate does not decrease significantly with increasing batch size. Various experiments on six high-dimensional real-world datasets demonstrate the efficacy and efficiency of the proposed algorithms, with a communication cost reduction of up to\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(90.89\\%\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            and a maximum wall time speedup of\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(5.66\\times\\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            compared to the baseline methods.\n          <\/jats:p>","DOI":"10.1145\/3712603","type":"journal-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T11:37:22Z","timestamp":1737027442000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Distributed Sparse Relative Similarity Learning"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0336-0522","authenticated-orcid":false,"given":"Dezhong","family":"Yao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2938-9861","authenticated-orcid":false,"given":"Sanmu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4641-3903","authenticated-orcid":false,"given":"Zhiwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8543-3953","authenticated-orcid":false,"given":"Peilin","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tencent AI Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6615-0699","authenticated-orcid":false,"given":"Gang","family":"Wu","sequence":"additional","affiliation":[{"name":"National Super Computing Center in Zhengzhou, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0782-0450","authenticated-orcid":false,"given":"Chen","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-7605","authenticated-orcid":false,"given":"Hai","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,2,22]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"1109","article-title":"Large scale online learning of image similarity through ranking","volume":"11","author":"Chechik Gal","year":"2010","unstructured":"Gal Chechik, Varun Sharma, Uri Shalit, and Samy Bengio. 2010. Large scale online learning of image similarity through ranking. Journal of Machine Learning Research 11 (2010), 1109\u20131135.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467210"},{"issue":"7","key":"e_1_3_2_4_2","first-page":"92:1","article-title":"Multi-level visual similarity based personalized tourist attraction recommendation using geo-tagged photos","volume":"17","author":"Chen Ling","year":"2023","unstructured":"Ling Chen, Dandan Lyu, Shanshan Yu, and Gencai Chen. 2023. Multi-level visual similarity based personalized tourist attraction recommendation using geo-tagged photos. ACM Transactions on Knowledge Discovery from Data 17, 7 (2023), 92:1\u201392:18.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2020.06.011"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248566"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273523"},{"key":"e_1_3_2_8_2","first-page":"248","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 248\u2013255."},{"key":"e_1_3_2_9_2","first-page":"2568","volume-title":"Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI)","author":"Ding Yi","year":"2015","unstructured":"Yi Ding, Peilin Zhao, Steven C. H. Hoi, and Yew-Soon Ong. 2015. An adaptive gradient method for online AUC maximization. In Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI), 2568\u20132574."},{"issue":"7","key":"e_1_3_2_10_2","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research 12, 7 (2011), 2121\u20132159.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_11_2","first-page":"76:1","article-title":"GADMM: Fast and communication efficient framework for distributed machine learning","volume":"21","author":"Elgabli Anis","year":"2020","unstructured":"Anis Elgabli, Jihong Park, Amrit S. Bedi, Mehdi Bennis, and Vaneet Aggarwal. 2020. GADMM: Fast and communication efficient framework for distributed machine learning. Journal of Machine Learning Research 21 (2020), 76:1\u201376:39.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_12_2","volume-title":"Caltech-256 Object Category Dataset","author":"Griffin Gregory","year":"2007","unstructured":"Gregory Griffin, Alex Holub, and Pietro Perona. 2007. Caltech-256 Object Category Dataset. Technical Report. California Institute of Technology."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052639"},{"issue":"1","key":"e_1_3_2_14_2","doi-asserted-by":"crossref","first-page":"110203","DOI":"10.1007\/s11432-021-3341-y","article-title":"Label propagation dictionary learning based process monitoring method for industrial process with between-mode similarity","volume":"65","author":"Huang Keke","year":"2022","unstructured":"Keke Huang, Shijun Tao, Yishun Liu, Chunhua Yang, and Weihua Gui. 2022. Label propagation dictionary learning based process monitoring method for industrial process with between-mode similarity. Science China Information Sciences 65, 1 (2022), 110203.","journal-title":"Science China Information Sciences"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/978-3-030-96896-0_6","volume-title":"Federated Learning - A Comprehensive Overview of Methods and Applications","author":"Joshi Gauri","year":"2022","unstructured":"Gauri Joshi and Shiqiang Wang. 2022. Communication-efficient distributed optimization algorithms. In Federated Learning - A Comprehensive Overview of Methods and Applications. Heiko Ludwig and Nathalie Baracaldo (Eds.), Springer, 125\u2013143."},{"key":"e_1_3_2_16_2","first-page":"4519","volume-title":"Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Khaled Ahmed","year":"2020","unstructured":"Ahmed Khaled, Konstantin Mishchenko, and Peter Richt\u00e1rik. 2020. Tighter theory for local SGD on identical and heterogeneous data. In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 4519\u20134529."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.77"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_20_2","first-page":"2834","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS)","author":"Lee Seunghak","year":"2014","unstructured":"Seunghak Lee, Jin Kyu Kim, Xun Zheng, Qirong Ho, Garth A. Gibson, and Eric P. Xing. 2014. On model parallelization and scheduling strategies for distributed machine learning. In Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS), 2834\u20132842."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.5555\/1005332.1005345"},{"key":"e_1_3_2_22_2","first-page":"4634","volume-title":"Proceedings of the 34th Conference on Artificial Intelligence (AAAI)","author":"Li Mingming","year":"2020","unstructured":"Mingming Li, Shuai Zhang, Fuqing Zhu, Wanhui Qian, Liangjun Zang, Jizhong Han, and Songlin Hu. 2020. Symmetric metric learning with adaptive margin for recommendation. In Proceedings of the 34th Conference on Artificial Intelligence (AAAI), 4634\u20134641."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"e_1_3_2_24_2","first-page":"2694","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR)","author":"Lin Tao","year":"2020","unstructured":"Tao Lin, Sebastian U. Stich, Kumar Kshitij Patel, and Martin Jaggi. 2020. Don\u2019t use large mini-batches, use local SGD. In Proceedings of the 8th International Conference on Learning Representations (ICLR), 2694\u20132733."},{"key":"e_1_3_2_25_2","first-page":"38:653","volume-title":"Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Liu Kuan","year":"2015","unstructured":"Kuan Liu, Aur\u00e9lien Bellet, and Fei Sha. 2015. Similarity learning for high-dimensional sparse data. In Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS). PMLR, 38:653\u201338:662."},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe David","year":"2004","unstructured":"David Lowe. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60 (2004), 91\u2013110.","journal-title":"International Journal of Computer Vision"},{"key":"e_1_3_2_27_2","first-page":"41","volume-title":"Proceedings of AAAI-98 Workshop on Learning for Text Categorization","author":"McCallum Andrew","year":"1998","unstructured":"Andrew McCallum and Kamal Nigam. 1998. A comparison of event models for naive Bayes text classification. In Proceedings of AAAI-98 Workshop on Learning for Text Categorization, 41\u201348."},{"issue":"2","key":"e_1_3_2_28_2","first-page":"16:1","article-title":"Systematic review of clustering high-dimensional and large datasets","volume":"12","author":"Pandove Divya","year":"2018","unstructured":"Divya Pandove, Shivani Goel, and Rinkle Rani. 2018. Systematic review of clustering high-dimensional and large datasets. ACM Transactions on Knowledge Discovery from Data 12, 2 (2018), 16:1\u201316:68.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"issue":"112","key":"e_1_3_2_29_2","first-page":"1","article-title":"Measuring the effects of data parallelism on neural network training","volume":"20","author":"Shallue Christopher J.","year":"2019","unstructured":"Christopher J. Shallue, Jaehoon Lee, Joseph Antognini, Jascha Sohl-Dickstein, Roy Frostig, and George E. Dahl. 2019. Measuring the effects of data parallelism on neural network training. Journal of Machine Learning Research 20, 112 (2019), 1\u201349.","journal-title":"Journal of Machine Learning Research"},{"issue":"9","key":"e_1_3_2_30_2","first-page":"4591","article-title":"Adaptive neighborhood metric learning","volume":"44","author":"Song Kun","year":"2021","unstructured":"Kun Song, Junwei Han, Gong Cheng, Jiwen Lu, and Feiping Nie. 2021. Adaptive neighborhood metric learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2021), 4591\u20134604.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_31_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR)","author":"Stich Sebastian U.","year":"2019","unstructured":"Sebastian U. Stich. 2019. Local SGD converges fast and communicates little. In Proceedings of the 7th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_32_2","first-page":"4447","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS)","author":"Stich Sebastian U.","year":"2018","unstructured":"Sebastian U. Stich, Jean-Baptiste Cordonnier, and Martin Jaggi. 2018. Sparsified SGD with memory. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS), 4447\u20134458."},{"issue":"2","key":"e_1_3_2_33_2","first-page":"29:1","article-title":"Scheduling hyperparameters to improve generalization: From centralized SGD to asynchronous SGD","volume":"17","author":"Sun Jianhui","year":"2023","unstructured":"Jianhui Sun, Ying Yang, Guangxu Xun, and Aidong Zhang. 2023. Scheduling hyperparameters to improve generalization: From centralized SGD to asynchronous SGD. ACM Transactions on Knowledge Discovery from Data 17, 2 (2023), 29:1\u201329:37.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"issue":"3","key":"e_1_3_2_34_2","first-page":"34:1","article-title":"Partitioned similarity search with cache-conscious data traversal","volume":"11","author":"Tang Xun","year":"2017","unstructured":"Xun Tang, Maha Alabduljalil, Xin Jin, and Tao Yang. 2017. Partitioned similarity search with cache-conscious data traversal. ACM Transactions on Knowledge Discovery from Data 11, 3 (2017), 34:1\u201334:38.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_2_35_2","first-page":"161","volume-title":"Proceedings of the 36th Annual Conference on Learning Theory (COLT)","author":"Wang Bohan","year":"2023","unstructured":"Bohan Wang, Huishuai Zhang, Zhiming Ma, and Wei Chen. 2023. Convergence of AdaGrad for non-convex objectives: Simple proofs and relaxed assumptions. In Proceedings of the 36th Annual Conference on Learning Theory (COLT), 161\u2013190."},{"key":"e_1_3_2_36_2","first-page":"365","volume-title":"Proceedings of the 4th Conference on Machine Learning and Systems (MLSys)","author":"Wang Hongyi","year":"2021","unstructured":"Hongyi Wang, Saurabh Agarwal, and Dimitris Papailiopoulos. 2021. Pufferfish: Communication-efficient models at no extra cost. In Proceedings of the 4th Conference on Machine Learning and Systems (MLSys), 365\u2013386."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455230"},{"key":"e_1_3_2_38_2","first-page":"212","volume-title":"Proceedings of the 2nd Conference on Machine Learning and Systems (MLSys)","author":"Wang Jianyu","year":"2019","unstructured":"Jianyu Wang and Gauri Joshi. 2019. Adaptive communication strategies to achieve the best error-runtime trade-off in local-update SGD. In Proceedings of the 2nd Conference on Machine Learning and Systems (MLSys), 212\u2013229."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"issue":"219","key":"e_1_3_2_40_2","first-page":"1","article-title":"Adagrad stepsizes: Sharp convergence over nonconvex landscapes","volume":"21","author":"Ward Rachel","year":"2020","unstructured":"Rachel Ward, Xiaoxia Wu, and Leon Bottou. 2020. Adagrad stepsizes: Sharp convergence over nonconvex landscapes. Journal of Machine Learning Research 21, 219 (2020), 1\u201330.","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"e_1_3_2_41_2","first-page":"36:1","article-title":"Heterogeneous translated hashing: A scalable solution towards multi-modal similarity search","volume":"10","author":"Wei Ying","year":"2016","unstructured":"Ying Wei, Yangqiu Song, Yi Zhen, Bo Liu, and Qiang Yang. 2016. Heterogeneous translated hashing: A scalable solution towards multi-modal similarity search. ACM Transactions on Knowledge Discovery from Data 10, 4 (2016), 36:1\u201336:28.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.5555\/2976248.2976433"},{"key":"e_1_3_2_43_2","first-page":"2142","volume-title":"Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI)","author":"Wu Pengcheng","year":"2014","unstructured":"Pengcheng Wu, Yi Ding, Peilin Zhao, Chunyan Miao, and Steven C. H. Hoi. 2014. Learning relative similarity by stochastic dual coordinate ascent. In Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI), 2142\u20132148."},{"issue":"4","key":"e_1_3_2_44_2","first-page":"48:1","article-title":"Large-scale online feature selection for ultra-high dimensional sparse data","volume":"11","author":"Wu Yue","year":"2017","unstructured":"Yue Wu, Steven C. H. Hoi, Tao Mei, and Nenghai Yu. 2017. Large-scale online feature selection for ultra-high dimensional sparse data. ACM Transactions on Knowledge Discovery from Data 11, 4 (2017), 48:1\u201348:22.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_2_45_2","first-page":"505","volume-title":"Proceedings of the 16th International Conference on Neural Information Processing Systems (NIPS)","author":"Xing Eric P.","year":"2002","unstructured":"Eric P. Xing, Andrew Y. Ng, Michael I. Jordan, and Stuart J. Russell. 2002. Distance metric learning with application to clustering with side-information. In Proceedings of the 16th International Conference on Neural Information Processing Systems (NIPS), 505\u2013512."},{"key":"e_1_3_2_46_2","first-page":"6631","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Yang Peng","year":"2020","unstructured":"Peng Yang and Ping Li. 2020. Distributed primal-dual optimization for online multi-task learning. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 6631\u20136638."},{"key":"e_1_3_2_47_2","first-page":"3655","volume-title":"Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI)","author":"Yang Yang","year":"2016","unstructured":"Yang Yang, Shengcai Liao, Zhen Lei, and Stan Z. Li. 2016. Large scale similarity learning using similar pairs for person verification. In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI), 3655\u20133661."},{"key":"e_1_3_2_48_2","first-page":"529","volume-title":"Proceedings of the IEEE International Conference on Data Mining (ICDM)","author":"Yao Dezhong","year":"2015","unstructured":"Dezhong Yao, Peilin Zhao, Chen Yu, Hai Jin, and Bin Li. 2015. Sparse online relative similarity learning. In Proceedings of the IEEE International Conference on Data Mining (ICDM), 529\u2013538."},{"key":"e_1_3_2_49_2","first-page":"84:1998","volume-title":"Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Yin Dong","year":"2018","unstructured":"Dong Yin, Ashwin Pananjady, Max Lam, Dimitris Papailiopoulos, Kannan Ramchandran, and Peter Bartlett. 2018. Gradient diversity: A key ingredient for scalable distributed learning. In Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS). PMLR 84:1998\u201384:2007."},{"key":"e_1_3_2_50_2","first-page":"5693","volume-title":"Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI)","author":"Yu Hao","year":"2019","unstructured":"Hao Yu, Sen Yang, and Shenghuo Zhu. 2019. Parallel restarted SGD with faster convergence and less communication: Demystifying why model averaging works for deep learning. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), 5693\u20135700."},{"issue":"1","key":"e_1_3_2_51_2","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1007\/s10489-022-03419-1","article-title":"Low-rank robust online distance\/similarity learning based on the rescaled hinge loss","volume":"53","author":"Zabihzadeh Davood","year":"2023","unstructured":"Davood Zabihzadeh, Amar Tuama, Ali Karami-Mollaee, and Seyed Jalaleddin Mousavirad. 2023. Low-rank robust online distance\/similarity learning based on the rescaled hinge loss. Applied Intelligence 53, 1 (2023), 634\u2013657.","journal-title":"Applied Intelligence"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2563424"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548072"},{"issue":"6","key":"e_1_3_2_54_2","first-page":"64:1","article-title":"Recurrent meta-structure for robust similarity measure in heterogeneous information networks","volume":"13","author":"Zhou Yu","year":"2019","unstructured":"Yu Zhou, Jianbin Huang, Heli Sun, Yizhou Sun, Shaojie Qiao, and Stephen Manko Wambura. 2019. Recurrent meta-structure for robust similarity measure in heterogeneous information networks. ACM Transactions on Knowledge Discovery from Data 13, 6 (2019), 64:1\u201364:33.","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"e_1_3_2_55_2","first-page":"2595","volume-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems (NeurIPS)","author":"Zinkevich Martin","year":"2010","unstructured":"Martin Zinkevich, Markus Weimer, Alexander J. Smola, and Lihong Li. 2010. Parallelized stochastic gradient descent. In Proceedings of the 24th International Conference on Neural Information Processing Systems (NeurIPS), 2595\u20132603."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712603","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:37Z","timestamp":1750295917000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,22]]},"references-count":54,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,4,30]]}},"alternative-id":["10.1145\/3712603"],"URL":"https:\/\/doi.org\/10.1145\/3712603","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2025,2,22]]},"assertion":[{"value":"2023-12-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}