{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:43:05Z","timestamp":1772300585256,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679586","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"2554-2563","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Teach Harder, Learn Poorer: Rethinking Hard Sample Distillation for GNN-to-MLP Knowledge Distillation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5551-3194","authenticated-orcid":false,"given":"Lirong","family":"Wu","sequence":"first","affiliation":[{"name":"Westlake University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1639-5855","authenticated-orcid":false,"given":"Yunfan","family":"Liu","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3153-7746","authenticated-orcid":false,"given":"Haitao","family":"Lin","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8184-4529","authenticated-orcid":false,"given":"Yufei","family":"Huang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2961-8096","authenticated-orcid":false,"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"international conference on machine learning. PMLR, 21--29","author":"Abu-El-Haija Sami","year":"2019","unstructured":"Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, and Aram Galstyan. 2019. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In international conference on machine learning. PMLR, 21--29."},{"key":"e_1_3_2_1_2_1","unstructured":"Anonymous. 2023. Double Wins: Boosting Accuracy and Efficiency of Graph Neural Networks by Reliable Knowledge Distillation. In Submitted to The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NGIFt6BNvLe under review."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"e_1_3_2_1_4_1","volume-title":"On self-distilling graph neural network. arXiv preprint arXiv:2011.02255","author":"Chen Yuzhao","year":"2020","unstructured":"Yuzhao Chen, Yatao Bian, Xi Xiao, Yu Rong, Tingyang Xu, and Junzhou Huang. 2020. On self-distilling graph neural network. arXiv preprint arXiv:2011.02255 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539320"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/276675.276685"},{"key":"e_1_3_2_1_7_1","unstructured":"Will Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in neural information processing systems. 1024--1034."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539315"},{"key":"e_1_3_2_1_9_1","volume-title":"Open graph benchmark: Datasets for machine learning on graphs. arXiv preprint arXiv:2005.00687","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. arXiv preprint arXiv:2005.00687 (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"Annealing knowledge distillation. arXiv preprint arXiv:2104.07163","author":"Jafari Aref","year":"2021","unstructured":"Aref Jafari, Mehdi Rezagholizadeh, Pranav Sharma, and Ali Ghodsi. 2021. Annealing knowledge distillation. arXiv preprint arXiv:2104.07163 (2021)."},{"key":"e_1_3_2_1_11_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_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053986"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_1_15_1","volume-title":"Better teacher better student: Dynamic prior knowledge for knowledge distillation. arXiv preprint arXiv:2206.06067","author":"Qiu Zengyu","year":"2022","unstructured":"Zengyu Qiu, Xinzhu Ma, Kunlin Yang, Chunya Liu, Jun Hou, Shuai Yi, and Wanli Ouyang. 2022. Better teacher better student: Dynamic prior knowledge for knowledge distillation. arXiv preprint arXiv:2206.06067 (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"Multi-task Self-distillation for Graph-based Semi-Supervised Learning. arXiv preprint arXiv:2112.01174","author":"Ren Yating","year":"2021","unstructured":"Yating Ren, Junzhong Ji, Lingfeng Niu, and Minglong Lei. 2021. Multi-task Self-distillation for Graph-based Semi-Supervised Learning. arXiv preprint arXiv:2112.01174 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Collective classification in network data. AI magazine","author":"Sen Prithviraj","year":"2008","unstructured":"Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI magazine, Vol. 29, 3 (2008), 93--93."},{"key":"e_1_3_2_1_18_1","volume-title":"Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868","author":"Shchur Oleksandr","year":"2018","unstructured":"Oleksandr Shchur, Maximilian Mumme, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. 2018. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868 (2018)."},{"key":"e_1_3_2_1_19_1","volume-title":"Is label smoothing truly incompatible with knowledge distillation: An empirical study. arXiv preprint arXiv:2104.00676","author":"Shen Zhiqiang","year":"2021","unstructured":"Zhiqiang Shen, Zechun Liu, Dejia Xu, Zitian Chen, Kwang-Ting Cheng, and Marios Savvides. 2021. Is label smoothing truly incompatible with knowledge distillation: An empirical study. arXiv preprint arXiv:2104.00676 (2021)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00926"},{"key":"e_1_3_2_1_21_1","first-page":"6906","article-title":"Does knowledge distillation really work","volume":"34","author":"Stanton Samuel","year":"2021","unstructured":"Samuel Stanton, Pavel Izmailov, Polina Kirichenko, Alexander A Alemi, and Andrew G Wilson. 2021. Does knowledge distillation really work? Advances in Neural Information Processing Systems, Vol. 34 (2021), 6906--6919.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","volume-title":"Knowledge Distillation on Graphs: A Survey. arXiv preprint arXiv:2302.00219","author":"Tian Yijun","year":"2023","unstructured":"Yijun Tian, Shichao Pei, Xiangliang Zhang, Chuxu Zhang, and Nitesh V Chawla. 2023. Knowledge Distillation on Graphs: A Survey. arXiv preprint arXiv:2302.00219 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Cs3r5KLdoj","author":"Tian Yijun","year":"2023","unstructured":"Yijun Tian, Chuxu Zhang, Zhichun Guo, Xiangliang Zhang, and Nitesh Chawla. 2023. Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Cs3r5KLdoj"},{"key":"e_1_3_2_1_24_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Velivckovi\u0107 Petar","year":"2017","unstructured":"Petar Velivckovi\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_3_2_1_25_1","volume-title":"Highly-Performant Package for Graph Neural Networks. arXiv preprint arXiv:1909.01315","author":"Wang Minjie","year":"2019","unstructured":"Minjie Wang, Da Zheng, Zihao Ye, Quan Gan, Mufei Li, Xiang Song, Jinjing Zhou, Chao Ma, Lingfan Yu, Yu Gai, Tong He, George Karypis, Jinyang Li, and Zheng Zhang. 2019. Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks. arXiv preprint arXiv:1909.01315 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3374773"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26232"},{"key":"e_1_3_2_1_28_1","unstructured":"Lirong Wu Haitao Lin Yufei Huang and Stan Z Li. 2022. Knowledge Distillation Improves Graph Structure Augmentation for Graph Neural Networks. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_29_1","volume-title":"Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs. arXiv preprint arXiv:2306.05628","author":"Wu Lirong","year":"2023","unstructured":"Lirong Wu, Haitao Lin, Yufei Huang, and Stan Z Li. 2023. Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs. arXiv preprint arXiv:2306.05628 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Homophily-Enhanced Self-Supervision for Graph Structure Learning: Insights and Directions","author":"Wu Lirong","year":"2023","unstructured":"Lirong Wu, Haitao Lin, Zihan Liu, Zicheng Liu, Yufei Huang, and Stan Z Li. 2023. Homophily-Enhanced Self-Supervision for Graph Structure Learning: Insights and Directions. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Self-supervised learning on graphs: Contrastive, generative, or predictive","author":"Wu Lirong","year":"2021","unstructured":"Lirong Wu, Haitao Lin, Cheng Tan, Zhangyang Gao, and Stan Z Li. 2021. Self-supervised learning on graphs: Contrastive, generative, or predictive. IEEE Transactions on Knowledge and Data Engineering (2021)."},{"key":"e_1_3_2_1_32_1","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 519--535","author":"Wu Lirong","year":"2022","unstructured":"Lirong Wu, Jun Xia, Zhangyang Gao, Haitao Lin, Cheng Tan, and Stan Z Li. 2022. Graphmixup: Improving class-imbalanced node classification by reinforcement mixup and self-supervised context prediction. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 519--535."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403236"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00169"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450068"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00710"},{"key":"e_1_3_2_1_38_1","volume-title":"Iterative graph self-distillation. arXiv preprint arXiv:2010.12609","author":"Zhang Hanlin","year":"2020","unstructured":"Hanlin Zhang, Shuai Lin, Weiyang Liu, Pan Zhou, Jian Tang, Xiaodan Liang, and Eric P Xing. 2020. Iterative graph self-distillation. arXiv preprint arXiv:2010.12609 (2020)."},{"key":"e_1_3_2_1_39_1","volume-title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks Via Distillation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=4p6_5HBWPCw","author":"Zhang Shichang","year":"2022","unstructured":"Shichang Zhang, Yozen Liu, Yizhou Sun, and Neil Shah. 2022. Graph-less Neural Networks: Teaching Old MLPs New Tricks Via Distillation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=4p6_5HBWPCw"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389706"},{"key":"e_1_3_2_1_41_1","volume-title":"Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective. arXiv preprint arXiv:2102.00650","author":"Zhou Helong","year":"2021","unstructured":"Helong Zhou, Liangchen Song, Jiajie Chen, Ye Zhou, Guoli Wang, Junsong Yuan, and Qian Zhang. 2021. Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective. arXiv preprint arXiv:2102.00650 (2021)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"e_1_3_2_1_43_1","volume-title":"Teach Less","author":"Zhu Yichen","unstructured":"Yichen Zhu, Ning Liu, Zhiyuan Xu, Xin Liu, Weibin Meng, Louis Wang, Zhicai Ou, and Jian Tang. 2022. Teach Less, Learn More: On the Undistillable Classes in Knowledge Distillation. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00501"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679586","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:23Z","timestamp":1750294703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679586"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":44,"alternative-id":["10.1145\/3627673.3679586","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679586","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}