{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:59:13Z","timestamp":1775815153978,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"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":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714963","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:52:18Z","timestamp":1745362338000},"page":"3160-3170","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6750-9002","authenticated-orcid":false,"given":"Zhixun","family":"Li","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3123-6572","authenticated-orcid":false,"given":"Dingshuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5292-0541","authenticated-orcid":false,"given":"Tong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9841-8605","authenticated-orcid":false,"given":"Daixin","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7273-3486","authenticated-orcid":false,"given":"Hongrui","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2321-7259","authenticated-orcid":false,"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6033-6102","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9738-827X","authenticated-orcid":false,"given":"Jeffrey Xu","family":"Yu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Pseudo-labeling and confirmation bias in deep semi-supervised learning. In 2020 International joint conference on neural networks (IJCNN)","author":"Arazo Eric","unstructured":"Eric Arazo, Diego Ortego, Paul Albert, Noel E O'Connor, and Kevin McGuinness. 2020. Pseudo-labeling and confirmation bias in deep semi-supervised learning. In 2020 International joint conference on neural networks (IJCNN). IEEE, 1--8."},{"key":"e_1_3_2_1_2_1","first-page":"29885","article-title":"Topology-imbalance learning for semi-supervised node classification","volume":"34","author":"Chen Deli","year":"2021","unstructured":"Deli Chen, Yankai Lin, Guangxiang Zhao, Xuancheng Ren, Peng Li, Jie Zhou, and Xu Sun. 2021. Topology-imbalance learning for semi-supervised node classification. Advances in Neural Information Processing Systems, Vol. 34 (2021), 29885--29897.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671798"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20605"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411903"},{"key":"e_1_3_2_1_7_1","first-page":"3290","article-title":"A unified view of label shift estimation","volume":"33","author":"Garg Saurabh","year":"2020","unstructured":"Saurabh Garg, Yifan Wu, Sivaraman Balakrishnan, and Zachary Lipton. 2020. A unified view of label shift estimation. Advances in Neural Information Processing Systems, Vol. 33 (2020), 3290--3300.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_8_1","volume-title":"Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997","author":"Gasteiger Johannes","year":"2018","unstructured":"Johannes Gasteiger, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. 2018. Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00656"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00763"},{"key":"e_1_3_2_1_11_1","volume-title":"The class imbalance problem: A systematic study. Intelligent data analysis","author":"Japkowicz Nathalie","year":"2002","unstructured":"Nathalie Japkowicz and Shaju Stephen. 2002. The class imbalance problem: A systematic study. Intelligent data analysis, Vol. 6, 5 (2002), 429--449."},{"key":"e_1_3_2_1_12_1","volume-title":"Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217","author":"Kang Bingyi","year":"2019","unstructured":"Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, and Yannis Kalantidis. 2019. Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217 (2019)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599374"},{"key":"e_1_3_2_1_15_1","volume-title":"A survey of graph meets large language model: Progress and future directions. arXiv preprint arXiv:2311.12399","author":"Li Yuhan","year":"2023","unstructured":"Yuhan Li, Zhixun Li, Peisong Wang, Jia Li, Xiangguo Sun, Hong Cheng, and Jeffrey Xu Yu. 2023a. A survey of graph meets large language model: Progress and future directions. arXiv preprint arXiv:2311.12399 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671982"},{"key":"e_1_3_2_1_17_1","volume-title":"Victor Wai Kin Chan, and Jia Li. 2024 d. Glbench: A comprehensive benchmark for graph with large language models. arXiv preprint arXiv:2407.07457","author":"Li Yuhan","year":"2024","unstructured":"Yuhan Li, Peisong Wang, Xiao Zhu, Aochuan Chen, Haiyun Jiang, Deng Cai, Victor Wai Kin Chan, and Jia Li. 2024 d. Glbench: A comprehensive benchmark for graph with large language models. arXiv preprint arXiv:2407.07457 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00131"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671826"},{"key":"e_1_3_2_1_20_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Li Zhixun","year":"2024","unstructured":"Zhixun Li, Xin Sun, Yifan Luo, Yanqiao Zhu, Dingshuo Chen, Yingtao Luo, Xiangxin Zhou, Qiang Liu, Shu Wu, Liang Wang, et al. 2024b. GSLB: the graph structure learning benchmark. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Focal Loss for Dense Object Detection. arXiv preprint arXiv:1708.02002","author":"Lin T","year":"2017","unstructured":"T Lin. 2017. Focal Loss for Dense Object Detection. arXiv preprint arXiv:1708.02002 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512172"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403076"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599410"},{"key":"e_1_3_2_1_25_1","volume-title":"Topological augmentation for class-imbalanced node classification. arXiv preprint arXiv:2308.14181","author":"Liu Zhining","year":"2023","unstructured":"Zhining Liu, Zhichen Zeng, Ruizhong Qiu, Hyunsik Yoo, David Zhou, Zhe Xu, Yada Zhu, Kommy Weldemariam, Jingrui He, and Hanghang Tong. 2023b. Topological augmentation for class-imbalanced node classification. arXiv preprint arXiv:2308.14181 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification. arXiv preprint arXiv:2406.08993","author":"Luo Yuankai","year":"2024","unstructured":"Yuankai Luo, Lei Shi, and Xiao-Ming Wu. 2024. Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification. arXiv preprint arXiv:2406.08993 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671929"},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on learning representations.","author":"Park Joonhyung","year":"2021","unstructured":"Joonhyung Park, Jaeyun Song, and Eunho Yang. 2021. Graphens: Neighbor-aware ego network synthesis for class-imbalanced node classification. In International conference on learning representations."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467334"},{"key":"e_1_3_2_1_30_1","unstructured":"Jiawei Ren Cunjun Yu Xiao Ma Haiyu Zhao Shuai Yi et al. 2020. Balanced meta-softmax for long-tailed visual recognition. Advances in neural information processing systems Vol. 33 (2020) 4175--4186."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/398"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Song Jaeyun","year":"2022","unstructured":"Jaeyun Song, Joonhyung Park, and Eunho Yang. 2022. TAM: topology-aware margin loss for class-imbalanced node classification. In International Conference on Machine Learning. PMLR, 20369--20383."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6048"},{"key":"e_1_3_2_1_34_1","first-page":"6316","article-title":"Contrastive graph poisson networks: Semi-supervised learning with extremely limited labels","volume":"34","author":"Wan Sheng","year":"2021","unstructured":"Sheng Wan, Yibing Zhan, Liu Liu, Baosheng Yu, Shirui Pan, and Chen Gong. 2021. Contrastive graph poisson networks: Semi-supervised learning with extremely limited labels. Advances in Neural Information Processing Systems, Vol. 34 (2021), 6316--6327.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635793"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671766"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"e_1_3_2_1_38_1","volume-title":"International conference on machine learning. PMLR, 6861--6871","author":"Wu Felix","year":"2019","unstructured":"Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In International conference on machine learning. PMLR, 6861--6871."},{"key":"e_1_3_2_1_39_1","volume-title":"Alleviating the sample selection bias in few-shot learning by removing projection to the centroid. Advances in neural information processing systems","author":"Xu Jing","year":"2022","unstructured":"Jing Xu, Xu Luo, Xinglin Pan, Yanan Li, Wenjie Pei, and Zenglin Xu. 2022. Alleviating the sample selection bias in few-shot learning by removing projection to the centroid. Advances in neural information processing systems, Vol. 35 (2022), 21073--21086."},{"key":"e_1_3_2_1_40_1","volume-title":"International Conference on Machine Learning. PMLR, 24851--24871","author":"Xue Yihao","year":"2022","unstructured":"Yihao Xue, Kyle Whitecross, and Baharan Mirzasoleiman. 2022. Investigating why contrastive learning benefits robustness against label noise. In International Conference on Machine Learning. PMLR, 24851--24871."},{"key":"e_1_3_2_1_41_1","volume-title":"UNREAL: Unlabeled Nodes Retrieval and Labeling for Heavily-imbalanced Node Classification. arXiv preprint arXiv:2303.10371","author":"Yan Liang","year":"2023","unstructured":"Liang Yan, Shengzhong Zhang, Bisheng Li, Min Zhou, and Zengfeng Huang. 2023. UNREAL: Unlabeled Nodes Retrieval and Labeling for Heavily-imbalanced Node Classification. arXiv preprint arXiv:2303.10371 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"International conference on machine learning. PMLR, 40--48","author":"Yang Zhilin","year":"2016","unstructured":"Zhilin Yang, William Cohen, and Ruslan Salakhudinov. 2016. Revisiting semi-supervised learning with graph embeddings. In International conference on machine learning. PMLR, 40--48."},{"key":"e_1_3_2_1_43_1","volume-title":"GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning. arXiv preprint arXiv:2410.13761","author":"Zhang Guibin","year":"2024","unstructured":"Guibin Zhang, Haonan Dong, Yuchen Zhang, Zhixun Li, Dingshuo Chen, Kai Wang, Tianlong Chen, Yuxuan Liang, Dawei Cheng, and Kun Wang. 2024a. GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning. arXiv preprint arXiv:2410.13761 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Graph sparsification via mixture of graphs. arXiv preprint arXiv:2405.14260","author":"Zhang Guibin","year":"2024","unstructured":"Guibin Zhang, Xiangguo Sun, Yanwei Yue, Chonghe Jiang, Kun Wang, Tianlong Chen, and Shirui Pan. 2024c. Graph sparsification via mixture of graphs. arXiv preprint arXiv:2405.14260 (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"2024 d. Two heads are better than one: Boosting graph sparse training via semantic and topological awareness. arXiv preprint arXiv:2402.01242","author":"Zhang Guibin","year":"2024","unstructured":"Guibin Zhang, Yanwei Yue, Kun Wang, Junfeng Fang, Yongduo Sui, Kai Wang, Yuxuan Liang, Dawei Cheng, Shirui Pan, and Tianlong Chen. 2024 d. Two heads are better than one: Boosting graph sparse training via semantic and topological awareness. arXiv preprint arXiv:2402.01242 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models. arXiv preprint arXiv:2501.13958","author":"Zhang Qinggang","year":"2025","unstructured":"Qinggang Zhang, Shengyuan Chen, Yuanchen Bei, Zheng Yuan, Huachi Zhou, Zijin Hong, Junnan Dong, Hao Chen, Yi Chang, and Xiao Huang. 2025. A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models. arXiv preprint arXiv:2501.13958 (2025)."},{"key":"e_1_3_2_1_47_1","volume-title":"BIM: Improving Graph Neural Networks with Balanced Influence Maximization. In 2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2931--2944","author":"Zhang Wentao","year":"2024","unstructured":"Wentao Zhang, Xinyi Gao, Ling Yang, Meng Cao, Ping Huang, Jiulong Shan, Hongzhi Yin, and Bin Cui. 2024b. BIM: Improving Graph Neural Networks with Balanced Influence Maximization. In 2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 2931--2944."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539374"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615058"},{"key":"e_1_3_2_1_50_1","volume-title":"Collaborative Knowledge Fusion: A Novel Approach for Multi-task Recommender Systems via LLMs. arXiv preprint arXiv:2410.20642","author":"Zhao Chuang","year":"2024","unstructured":"Chuang Zhao, Xing Su, Ming He, Hongke Zhao, Jianping Fan, and Xiaomeng Li. 2024. Collaborative Knowledge Fusion: A Novel Approach for Multi-task Recommender Systems via LLMs. arXiv preprint arXiv:2410.20642 (2024)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441720"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25622"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3271771"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714963","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714963","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:54Z","timestamp":1750295934000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714963"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":53,"alternative-id":["10.1145\/3696410.3714963","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714963","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}