[1]郑文萍,苏蕊,刘扬.基于任务子图感知的少样本节点分类算法[J].智能系统学报,2026,21(3):666-674.[doi:10.11992/tis.202506037]
ZHENG Wenping,SU Rui,LIU Yang.Few-shot node classification based on task-aware subgraphs[J].CAAI Transactions on Intelligent Systems,2026,21(3):666-674.[doi:10.11992/tis.202506037]
点击复制
ZHENG Wenping,SU Rui,LIU Yang.Few-shot node classification based on task-aware subgraphs[J].CAAI Transactions on Intelligent Systems,2026,21(3):666-674.[doi:10.11992/tis.202506037]
基于任务子图感知的少样本节点分类算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第3期
页码:
666-674
栏目:
学术论文—机器学习
出版日期:
2026-05-05
- Title:
- Few-shot node classification based on task-aware subgraphs
- Keywords:
- graph neural networks; node classification; graph representation learning; few shot learning; meta learning; complex network; prototypical network; deep learning
- 分类号:
- TP30
- 文献标志码:
- 2026-3-24
- 摘要:
- 目前基于图神经网络的节点分类方法依赖大量标记数据，且长尾标签分布降低了学习效率。在低资源场景下，基于元学习的少样本学习是图表示学习的有效途径，然而，全局图学习会引入任务无关噪声，且现有原型网络方法直接计算节点与类原型的相似性以对节点分类，在少样本条件下难以准确计算类原型。针对此，提出了基于任务子图感知的少样本节点分类算法(few-shot node classification based on task-aware subgraphs, TAS-FNC)。该方法通过结构裁剪与拓扑增强，为当前任务构建高连通性子图，在其上学习特定任务的节点表示以减轻无关噪声影响；进而学习查询节点与类原型的关系以进行节点分类。在4个数据集上与11种基线方法进行比较实验表明，TAS-FNC能在标记样本稀缺的场景下有效提高节点分类的准确度。
- Abstract:
- Current graph neural network-based node classification methods rely on large amounts of labeled data and are limited by long-tailed label distributions. In low-resource settings, meta-learning-based few-shot learning is effective for graph representation. However, global graph learning introduces task-irrelevant noise, and current prototypical networks, which classify nodes by directly computing similarities between nodes and class prototypes, struggle to estimate accurate prototypes under few-shot conditions. To address these issues, we propose a task-aware subgraph-based few-shot node classification method (TAS-FNC). This method constructs high-connectivity subgraphs for each task through structural pruning and topological enhancement, enabling task-specific node representation learning and reducing noise. It then models the relationships between query nodes and class prototypes for classification. Experiments on four datasets against 11 baselines show that TAS-FNC effectively improves node classification accuracy in label-scarce scenarios.
- 参考文献/References:
-
[1] WANG Weiqing, YIN Hongzhi, DU Xingzhong, et al. Online user representation learning across heterogeneous social networks[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2019: 545-554.
[2] FOUT A, BYRD J, SHARIAT B, et al. Protein interface prediction using graph convolutional networks[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 6533-6542.
[3] 于浩淼, 刘炜, 孟流畅, 等. RWK-GNN: 基于特征增强与子核分解的非平衡图欺诈检测算法[J]. 电子学报, 2024, 52(10): 3382-3391 YU Haomiao, LIU Wei, MENG Liuchang, et al. RWK-GNN: fraud detection for imbalanced graphs with feature enhancement and subkernel decomposition[J]. Acta electronica sinica, 2024, 52(10): 3382-3391
[4] 刘晓光, 李梅. 基于深度学习的药物-靶标相互作用预测研究综述[J]. 智能系统学报, 2024, 19(3): 494-524 LIU Xiaoguang, LI Mei. A survey of deep learning-based drug-target interaction prediction[J]. CAAI transactions on intelligent systems, 2024, 19(3): 494-524
[5] DING Kaize, WANG Jianling, CAVERLEE J, et al. Meta propagation networks for graph few-shot semi-supervised learning[J]. Proceedings of the AAAI conference on artificial intelligence, 2022, 36(6): 6524-6531
[6] DONG Chuanqi, LI Wenbin, HUO Jing, et al. Learning task-aware local representations for few-shot learning[C]//Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. New York: ACM, 2021: 716-722.
[7] WANG Ning, LUO Minnan, DING Kaize, et al. Graph few-shot learning with attribute matching[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. New York: ACM, 2020: 1545-1554.
[8] WANG Song, CHEN Chen, LI Jundong. Graph few-shot learning with task-specific structures[C]//Proceedings of the 36th International Conference on Neural Information Processing Systems. New York: ACM, 2022: 38925-38936.
[9] LIU Zemin, FANG Yuan, LIU Chenghao, et al. Relative and absolute location embedding for few-shot node classification on graph[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(5): 4267-4275
[10] ZHOU Fan, CAO Chengtai, ZHANG Kunpeng, et al. Meta-GNN: on few-shot node classification in graph meta-learning[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York: ACM, 2019: 2357-2360.
[11] WU F, ZHANG Tianyi, DE SOUZA A H, et al. Simplifying graph convolutional networks[C]//International Conference on Machine Learning. Long Beach: PMLR, 2019: 6861-6871.
[12] VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. New York: ACM, 2016: 3637-3645.
[13] YU Xingtong, FANG Yuan, LIU Zemin, et al. A survey of few-shot learning on graphs: from meta-learning to pre-training and prompt learning[EB/OL]. (2024-03-15)[2025-12-22]. https://arxiv.org/abs/2402.01440.
[14] 刘美麟, 李华, 郑文萍. 模体感知的多视图协同聚类优化算法[J]. 计算机研究与发展, 2026, 63(2): 324-337 LIU Meilin, LI Hua, ZHENG Wenping. Motif-aware multi-view cooperative clustering optimization algorithm[J]. Journal of computer research and development, 2026, 63(2): 324-337
[15] 郑文萍, 王英楠, 杨贵. 基于双监督网络嵌入的社区发现算法[J]. 模式识别与人工智能, 2022, 35(3): 283-290 ZHENG Wenping, WANG Yingnan, YANG Gui. Dual supervised network embedding based community detection algorithm[J]. Pattern recognition and artificial intelligence, 2022, 35(3): 283-290
[16] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. (2016-09-09)[2025-12-22]. https://arxiv.org/abs/1609.02907.
[17] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 1025-1035.
[18] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]//Proceedings of the 6th International Conference on Learning Representations. Vancouver: ICLR, 2018: 1-12.
[19] 周凯锐, 刘鑫, 景丽萍, 等. 概念驱动的小样本判别特征学习方法[J]. 智能系统学报, 2023, 18(1): 162-172 ZHOU Kairui, LIU Xin, JING Liping, et al. Concept-driven discriminative feature learning for few-shot learning[J]. CAAI transactions on intelligent systems, 2023, 18(1): 162-172
[20] GHAROUN H, MOMENIFAR F, CHEN Fang, et al. Meta-learning approaches for few-shot learning: a survey of recent advances[J]. ACM computing surveys, 2024, 56(12): 1-41
[21] SNELL J, SWERSKY K, ZEMEL R S. Prototypical networks for few-shot learning[C]//Neural Information Processing Systems. Red Hook: Curran Associates, 2017: 4077-4087.
[22] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proceedings of the 34th International Conference on Machine Learning-Volume 70. Sydney: PMLR, 2017: 1126-1135.
[23] WANG Song, DING Kaize, ZHANG Chuxu, et al. Task-adaptive few-shot node classification[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2022: 1910-1919.
[24] WANG Song, DONG Yushun, DING Kaize, et al. Few-shot node classification with extremely weak supervision[C]//Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. New York: ACM, 2023: 276-284.
[25] DING Kaize, WANG Jianling, LI Jundong, et al. Graph prototypical networks for few-shot learning on attributed networks[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. New York: ACM, 2020: 295-304.
[26] LAN L, WANG P, DU X, et al. Node classification on graphs with few-shot novel labels via meta transformed network embedding[J]. Advances in Neural Information Processing Systems, 2020, 33: 16520-16531
[27] WANG Ningrui, LAI Yujing, CHEN Chuan, et al. Prototypical networks with unlabeled data for few-shot node classification[J]. Engineering applications of artificial intelligence, 2025, 145: 110088
[28] 刘鑫磊, 冯林, 廖凌湘, 等. 基于元学习的图卷积网络少样本学习模型[J]. 电子学报, 2024, 52(3): 885-897 LIU Xinlei, FENG Lin, LIAO Lingxiang, et al. Few-shot learning on graph convolutional network based on meta learning[J]. Acta electronica sinica, 2024, 52(3): 885-897
[29] MCAULEY J, PANDEY R, LESKOVEC J. Inferring networks of substitutable and complementary products[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2015: 785-794.
[30] TANG Jie, ZHANG Jing, YAO Limin, et al. ArnetMiner: extraction and mining of academic social networks[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2008: 990-998.
[31] HU W, FEY M, ZITNIK M, et al. Open graph benchmark: datasets for machine learning on graphs[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2020: 1-12.
- 相似文献/References:
-
[1]张潇鲲,刘琰,陈静.引入外部词向量的文本信息网络表示学习[J].智能系统学报,2019,14(5):1056.[doi:10.11992/tis.201809037]
ZHANG Xiaokun,LIU Yan,CHEN Jing.Representation learning using network embedding based on external word vectors[J].CAAI Transactions on Intelligent Systems,2019,14():1056.[doi:10.11992/tis.201809037]
[2]张蕾,钱峰,赵姝,等.基于多粒度结构的网络表示学习[J].智能系统学报,2019,14(6):1233.[doi:10.11992/tis.201905045]
ZHANG Lei,QIAN Feng,ZHAO Shu,et al.Network representation learning based on multi-granularity structure[J].CAAI Transactions on Intelligent Systems,2019,14():1233.[doi:10.11992/tis.201905045]
[3]吴国栋,查志康,涂立静,等.图神经网络推荐研究进展[J].智能系统学报,2020,15(1):14.[doi:10.11992/tis.201908034]
WU Guodong,ZHA Zhikang,TU Lijing,et al.Research advances in graph neural network recommendation[J].CAAI Transactions on Intelligent Systems,2020,15():14.[doi:10.11992/tis.201908034]
[4]张勇,高大林,巩敦卫,等.用于关系抽取的注意力图长短时记忆神经网络[J].智能系统学报,2021,16(3):518.[doi:10.11992/tis.202008036]
ZHANG Yong,GAO Dalin,GONG Dunwei,et al.Attention graph long short-term memory neural network for relation extraction[J].CAAI Transactions on Intelligent Systems,2021,16():518.[doi:10.11992/tis.202008036]
[5]周俊,张志强,曹月恬,等.地理位置和时间感知的表示学习框架[J].智能系统学报,2021,16(5):909.[doi:10.11992/tis.202104011]
ZHOU Jun,ZHANG Zhiqiang,CAO Yuetian,et al.A geography and time aware representation learning framework[J].CAAI Transactions on Intelligent Systems,2021,16():909.[doi:10.11992/tis.202104011]
[6]卢毅,陈亚冉,赵冬斌,等.关键点图对比图像分类方法[J].智能系统学报,2023,18(1):36.[doi:10.11992/tis.202112001]
LU Yi,CHEN Yaran,ZHAO Dongbin,et al.Keypoint-based graph contrastive neural network for image classification[J].CAAI Transactions on Intelligent Systems,2023,18():36.[doi:10.11992/tis.202112001]
[7]车飞虎,张大伟,邵朋朋,等.基于四元数门控图神经网络的脚本事件预测[J].智能系统学报,2023,18(1):138.[doi:10.11992/tis.202203042]
CHE Feihu,ZHANG Dawei,SHAO Pengpeng,et al.Script event prediction based on a quaternion-gated graph neural network[J].CAAI Transactions on Intelligent Systems,2023,18():138.[doi:10.11992/tis.202203042]
[8]孟祥福,温晶,李子函,等.多重注意力指导下的异构图嵌入方法[J].智能系统学报,2023,18(4):688.[doi:10.11992/tis.202204006]
MENG Xiangfu,WEN Jing,LI Zihan,et al.Heterogeneous graph embedding method guided by the multi-attention mechanism[J].CAAI Transactions on Intelligent Systems,2023,18():688.[doi:10.11992/tis.202204006]
[9]周贤琛,马扬,程光权,等.战场目标实体类型识别的鲁棒图神经网络方法[J].智能系统学报,2023,18(6):1156.[doi:10.11992/tis.202111025]
ZHOU Xianchen,MA Yang,CHENG Guangquan,et al.Robust graph neural network method for target entity type recognition in a battlefield environment[J].CAAI Transactions on Intelligent Systems,2023,18():1156.[doi:10.11992/tis.202111025]
[10]曹汉童,陈璟.融合Doc2vec与GCN的多类型蛋白质相互作用预测方法[J].智能系统学报,2023,18(6):1165.[doi:10.11992/tis.202212029]
CAO Hantong,CHEN Jing.Prediction of multitype protein interactions combining Doc2vec and GCN[J].CAAI Transactions on Intelligent Systems,2023,18():1165.[doi:10.11992/tis.202212029]
[11]李旭,蔡彪,胡能兵.基于三元互信息的图对比学习方法研究[J].智能系统学报,2024,19(5):1257.[doi:10.11992/tis.202308004]
LI Xu,CAI Biao,HU Nengbing.Research on graph contrastive learning method based on ternary mutual information[J].CAAI Transactions on Intelligent Systems,2024,19():1257.[doi:10.11992/tis.202308004]
备注/Memo
收稿日期:2025-6-30。
基金项目:国家自然科学基金项目(62072292)；山西省1331工程项目.
作者简介:郑文萍，教授，博士生导师，主要研究方向为网络数据分析、生物信息学。发表学术论文30余篇。E-mail：wpzheng@sxu.edu.cn。;苏蕊，硕士研究生，主要研究方向为复杂网络分析。E-mail：3257549994@qq.com。;刘扬，博士研究生，主要研究方向为复杂网络分析。E-mail：yliu0522@163.com。
通讯作者:郑文萍. E-mail：wpzheng@sxu.edu.cn
更新日期/Last Update:
1900-01-01