{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T08:08:30Z","timestamp":1774685310886,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665938","type":"print"},{"value":"9789819665945","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-96-6594-5_15","type":"book-chapter","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T07:38:30Z","timestamp":1753083510000},"page":"194-209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge Distillation with\u00a0Differentiable Optimal Transport on\u00a0Graph Neural Networks"],"prefix":"10.1007","author":[{"given":"Mengyao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,22]]},"reference":[{"issue":"9","key":"15_CR1","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1109\/TKDE.2018.2807452","volume":"30","author":"H Cai","year":"2018","unstructured":"Cai, H., Zheng, V.W., Chang, K.: A comprehensive survey of graph embedding: problems, techniques, and applications. IEEE Trans. Knowl. Data Eng. 30(9), 1616\u20131637 (2018)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Chen, D., et al.: Cross-layer distillation with semantic calibration. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 7028\u20137036 (2021)","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"15_CR3","unstructured":"Chen, L., et al.: Improving sequence-to-sequence learning via optimal transport. arXiv preprint arXiv:1901.06283 (2019)"},{"key":"15_CR4","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Advances in Neural Information Processing Systems, vol. 26 (2013)"},{"key":"15_CR5","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Kim, K., Ji, B., Yoon, D., Hwang, S.: Self-knowledge distillation with progressive refinement of targets. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6567\u20136576 (2021)","DOI":"10.1109\/ICCV48922.2021.00650"},{"key":"15_CR7","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"15_CR8","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Lassance, C., Bontonou, M., Hacene, G.B., Gripon, V., Tang, J., Ortega, A.: Deep geometric knowledge distillation with graphs. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8484\u20138488. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053986"},{"key":"15_CR10","unstructured":"Lee, S., Song, B.C.: Graph-based knowledge distillation by multi-head attention network. arXiv preprint arXiv:1907.02226 (2019)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Curriculum temperature for knowledge distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1504\u20131512 (2023)","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Knowledge distillation via instance relationship graph. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7096\u20137104 (2019)","DOI":"10.1109\/CVPR.2019.00726"},{"key":"15_CR13","unstructured":"Miles, R., Rodriguez, A.L., Mikolajczyk, K.: Information theoretic representation distillation. arXiv preprint arXiv:2112.00459 (2021)"},{"key":"15_CR14","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3967\u20133976 (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Passalis, N., Tefas, A.: Learning deep representations with probabilistic knowledge transfer. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 268\u2013284 (2018)","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Peng, B., et al.: Correlation congruence for knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5007\u20135016 (2019)","DOI":"10.1109\/ICCV.2019.00511"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Peyr\u00e9, G., Cuturi, M., et\u00a0al.: Computational optimal transport: With applications to data science. Found. Trends\u00ae in Mach. Learn. 11(5-6), 355\u2013607 (2019)","DOI":"10.1561\/9781680835519"},{"key":"15_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Sun, S., Ren, W., Li, J., Wang, R., Cao, X.: Logit standardization in knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15731\u201315740 (2024)","DOI":"10.1109\/CVPR52733.2024.01489"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Tang, J., Zhao, K., Li, J.: A fused gromov-wasserstein framework for unsupervised knowledge graph entity alignment. arXiv preprint arXiv:2305.06574 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.205"},{"key":"15_CR22","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. arXiv preprint arXiv:1910.10699 (2019)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1365\u20131374 (2019)","DOI":"10.1109\/ICCV.2019.00145"},{"key":"15_CR24","doi-asserted-by":"publisher","unstructured":"Villani, C., et\u00a0al.: Optimal Transport: Old and New, vol.\u00a0338. Springer (2009). https:\/\/doi.org\/10.1007\/978-3-540-71050-9","DOI":"10.1007\/978-3-540-71050-9"},{"key":"15_CR25","unstructured":"Xu, H., Luo, D., Zha, H., Duke, L.C.: Gromov-wasserstein learning for graph matching and node embedding. In: International Conference on Machine Learning, pp. 6932\u20136941. PMLR (2019)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Yang, C., Xie, L., Su, C., Yuille, A.L.: Snapshot distillation: teacher-student optimization in one generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2859\u20132868 (2019)","DOI":"10.1109\/CVPR.2019.00297"},{"key":"15_CR27","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., Liang, J.: Decoupled knowledge distillation. arXiv preprint arXiv:2203.08679 (2022)","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"15_CR29","unstructured":"Zheng, K., Yang, E.H.: Knowledge distillation based on transformed teacher matching. arXiv preprint arXiv:2402.11148 (2024)"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Distilling holistic knowledge with graph neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10387\u201310396 (2021)","DOI":"10.1109\/ICCV48922.2021.01022"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, J., et al.: Complementary relation contrastive distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9260\u20139269 (2021)","DOI":"10.1109\/CVPR46437.2021.00914"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6594-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T07:47:23Z","timestamp":1774684043000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6594-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,22]]},"ISBN":["9789819665938","9789819665945"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6594-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,22]]},"assertion":[{"value":"22 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}