{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:18:00Z","timestamp":1777706280123,"version":"3.51.4"},"reference-count":35,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Hunan Province of China","doi-asserted-by":"publisher","award":["No.2021GK5014"],"award-info":[{"award-number":["No.2021GK5014"]}],"id":[{"id":"10.13039\/501100019091","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>Graph neural networks (GNNs) have achieved excellent results in various graph-based learning tasks. However, the redundant parameters of GNNs and the large-scale graphs used as inputs have prevented GNNs from scaling up to real-world large-scale graph applications. To solve this problem, the graph lottery hypothesis claims the existence of graph lottery tickets (GLT), a combination of sparse core subgraph and subnetwork, which can be retrained to achieve performance similar to the original input graphs and dense networks. However, the GLT identified in the existing work lose valuable information due to irreversible pruning schemes. In addition, the performance of GNNs drops significantly when the graph sparsity is high. In this paper, we propose a gradual pruning and knowledge distillation (GPKD) framework to compensate for the loss caused by pruning and eventually identify GLT efficiently. Specifically, we first prune the input graph and model parameters according to the gradual iterative magnitude pruning strategy and then reset the remaining parameters. After each round of pruning, the pre-trained and pruned networks are considered teacher and student models, respectively. We employ a knowledge distillation scheme to allow students to mimic the output of the teacher model. The experimental results demonstrate that our proposed GPKD framework significantly outperforms the state-of-the-art unified GNNs sparsification (UGS) framework.<\/jats:p>","DOI":"10.1177\/18758967251376788","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:00:30Z","timestamp":1758301230000},"page":"1137-1149","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint Gradual Pruning and Knowledge Distillation for Identifying Graph Lottery Tickets"],"prefix":"10.1177","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6744-2960","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Hunan Normal University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyi","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Hunan Normal University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghao","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Hunan Normal University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijian","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Hunan Normal University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3486618"},{"key":"e_1_3_2_4_1","unstructured":"Chen T. Sui Y. Chen X. Zhang A. Wang Z. (2021). A unified lottery ticket hypothesis for graph neural networks."},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.084"},{"key":"e_1_3_2_6_1","unstructured":"Frankle J. Carbin M. (2019). The lottery ticket hypothesis: Finding sparse trainable neural networks. In 7th International conference on learning representations ICLR 2019 New Orleans LA USA May 6\u20139 2019."},{"key":"e_1_3_2_7_1","unstructured":"Frankle J. Dziugaite G. K. Roy D. M. Carbin M. (2019). Stabilizing the lottery ticket hypothesis. arXiv preprint arXiv:1903.01611."},{"key":"e_1_3_2_8_1","unstructured":"Han S. Mao H. Dally W. J. (2016). Deep compression: Compressing deep neural network with pruning trained quantization and huffman coding. In 4th International conference on learning representations ICLR 2016 San Juan Puerto Rico May 2\u20134 2016 Conference Track Proceedings."},{"key":"e_1_3_2_9_1","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume":"1","author":"Han S.","year":"2015","unstructured":"Han S., Pool J., Tran J. (2015). Learning both weights and connections for efficient neural networks. Proceedings of the 29th International Conference on Neural Information Processing Systems, 1, 1135\u20131143.","journal-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_2_10_1","doi-asserted-by":"crossref","unstructured":"Harn P. Yeddula S. D. Hui B. Zhang J. Sun L. Sun M. Ku W. (2022). IGRP: Iterative gradient rank pruning for finding graph lottery ticket. In IEEE International conference on big data big data 2022 Osaka Japan December 17\u201320 2022 (pp. 931\u2013941). IEEE.","DOI":"10.1109\/BigData55660.2022.10020964"},{"key":"e_1_3_2_11_1","unstructured":"Hinton G. Vinyals O. Dean J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531."},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-200771"},{"key":"e_1_3_2_13_1","unstructured":"Hui B. Yan D. Ma X. Ku W. S. (2023). Rethinking graph lottery tickets: Graph sparsity matters. arXiv preprint arXiv:2305.02190."},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106816"},{"key":"e_1_3_2_15_1","unstructured":"Kipf T. N. Welling M. (2017). Semi-supervised classification with graph convolutional networks. In 5th International conference on learning representations ICLR 2017 Toulon France April 24\u201326 2017 Conference Track Proceedings."},{"key":"e_1_3_2_16_1","doi-asserted-by":"crossref","unstructured":"Li B. Wang Z. Huang S. Bragin M. A. Li J. Ding C. (2023). Towards lossless head pruning through automatic peer distillation for language models. In Proceedings of the Thirty-Second international joint conference on artificial intelligence IJCAI 2023 19th-25th August 2023 Macao SAR China (pp. 5113\u20135121). ijcai.org.","DOI":"10.24963\/ijcai.2023\/568"},{"key":"e_1_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Li J. Zhang T. Tian H. Jin S. Fardad M. Zafarani R. (2020). Sgcn: A graph sparsifier based on graph convolutional networks. In Advances in knowledge discovery and data mining: 24th Pacific-Asia Conference PAKDD 2020 Singapore May 11\u201314 2020 Proceedings Part I 24 (pp. 275\u2013287). Springer.","DOI":"10.1007\/978-3-030-47426-3_22"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3282049"},{"key":"e_1_3_2_19_1","unstructured":"Liu J. Zheng T. Zhang G. Hao Q. (2023b). Graph-based knowledge distillation: A survey and experimental evaluation. arXiv preprint arXiv:2302.14643."},{"key":"e_1_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Park J. No A. (2022). Prune your model before distill it. In Computer Vision - ECCV 2022 - 17th European conference Tel Aviv Israel October 23\u201327 2022 Proceedings Part XI Lecture Notes in Computer Science (Vol. 13671 pp. 120\u2013136). Springer.","DOI":"10.1007\/978-3-031-20083-0_8"},{"key":"e_1_3_2_21_1","unstructured":"Rong Y. Huang W. Xu T. Huang J. (2020). Dropedge: Towards deep graph convolutional networks on node classification. In 8th International conference on learning representations ICLR 2020 Addis Ababa Ethiopia April 26\u201330 2020."},{"key":"e_1_3_2_22_1","unstructured":"Savarese P. Silva H. Maire M. (2020). Winning the lottery with continuous sparsification. In Advances in neural information processing systems 33: Annual conference on neural information processing systems 2020 NeurIPS 2020 December 6\u201312 2020 virtual."},{"key":"e_1_3_2_23_1","doi-asserted-by":"crossref","unstructured":"Shen X. Kong Z. Qin M. Dong P. Yuan G. Meng X. Tang H. Ma X. Wang Y. (2022). The lottery ticket hypothesis for vision transformers. arXiv preprint arXiv:2211.01484.","DOI":"10.24963\/ijcai.2023\/153"},{"key":"e_1_3_2_24_1","unstructured":"Velickovic P. Cucurull G. Casanova A. Romero A. Li\u00f2 P. Bengio Y. (2018). Graph attention networks. In 6th International conference on learning representations ICLR 2018 Vancouver BC Canada April 30 \u2013 May 3 2018 Conference Track Proceedings."},{"key":"e_1_3_2_25_1","unstructured":"Wang K. Liang Y. Wang P. Wang X. Gu P. Fang J. Wang Y. (2023a). Searching lottery tickets in graph neural networks: A dual perspective. In The Eleventh international conference on learning representations ICLR 2023 Kigali Rwanda May 1\u20135 2023."},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-023-01036-0"},{"key":"e_1_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Wang Y. Liu S. Chen K. Zhu T. Qiao J. Shi M. Wan Y. Song M. (2023c). Adversarial erasing with pruned elements: Towards better graph lottery ticket. arXiv preprint arXiv:2308.02916.","DOI":"10.3233\/FAIA230564"},{"key":"e_1_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/int.22827"},{"key":"e_1_3_2_29_1","unstructured":"Xu K. Hu W. Leskovec J. Jegelka S. (2019). How powerful are graph neural networks? In 7th International conference on learning representations ICLR 2019 New Orleans LA USA May 6\u20139 2019."},{"key":"e_1_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Yan B. Wang C. Guo G. Lou Y. (2020). Tinygnn: Learning efficient graph neural networks. In KDD \u201920: The 26th ACM SIGKDD conference on knowledge discovery and data mining virtual event CA USA August 23\u201327 2020 (pp. 1848\u20131856). ACM.","DOI":"10.1145\/3394486.3403236"},{"key":"e_1_3_2_31_1","doi-asserted-by":"crossref","unstructured":"Yang Y. Qiu J. Song M. Tao D. Wang X. (2020). Distilling knowledge from graph convolutional networks. In 2020 IEEE\/CVF Conference on computer vision and pattern recognition CVPR 2020 Seattle WA USA June 13\u201319 2020 (pp. 7072\u20137081). Computer Vision Foundation \/ IEEE.","DOI":"10.1109\/CVPR42600.2020.00710"},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3072345"},{"key":"e_1_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Yeo S. Jang Y. Sohn J. Y. Han D. Yoo J. (2023). Can we find strong lottery tickets in generative models? In Proceedings of the AAAI conference on artificial intelligence (Vol. 37 pp. 3267\u20133275).","DOI":"10.1609\/aaai.v37i3.25433"},{"key":"e_1_3_2_34_1","article-title":"Hierarchical graph representation learning with differentiable pooling","volume":"31","author":"Ying Z.","year":"2018","unstructured":"Ying Z., You J., Morris C., Ren X., Hamilton W., Leskovec J. (2018). Hierarchical graph representation learning with differentiable pooling. Advances in Neural Information Processing Systems, 31.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_35_1","unstructured":"Zhang M. Chen Y. (2020). Inductive matrix completion based on graph neural networks. In 8th International conference on learning representations ICLR 2020 Addis Ababa Ethiopia April 26-30 2020."},{"key":"e_1_3_2_36_1","unstructured":"Zhu M. Gupta S. (2018). To prune or not to prune: Exploring the efficacy of pruning for model compression. In 6th International conference on learning representations ICLR 2018 Vancouver BC Canada April 30 \u2013 May 3 2018 Workshop Track Proceedings."}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18758967251376788","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/18758967251376788","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18758967251376788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:46:28Z","timestamp":1777455988000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/18758967251376788"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"references-count":35,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/18758967251376788"],"URL":"https:\/\/doi.org\/10.1177\/18758967251376788","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]}}}