基于知识增强自适应原型网络的小样本关系分类

doi:10.19678/j.issn.1000-3428.0068855

摘要/Abstract

摘要：

小样本关系分类(FSRC)是指在任务中使用少量标注实例对各种关系进行分类, 可快速适用于对全新的类别进行归类。然而, 当测试域与训练域之间存在分布差异时, 现有的小样本分类算法泛化能力有限, 导致分类性能下降。针对该问题, 提出一种适用于领域适应任务的知识增强自适应原型网络。通过探索实例之间的联系以提高模型的鲁棒性, 同时学习关于关系的先验知识和内在语义以获得可解释原型。通过引入交互注意力机制来捕捉支持实例与查询实例之间的相关性, 突出关键实例, 并生成交互实例。同时, 自适应原型融合机制以关系信息为锚点生成自适应混合系数, 通过特征融合将实例与关系信息相结合, 从而生成混合原型。在公开数据集FewRel 1.0和FewRel 2.0上的实验结果验证了该网络的有效性。实验结果表明, 与基线模型相比, 所提网络模型的分类准确率取得了显著提升, 具有更好的分类效果与稳定性。

关键词: 关系分类, 小样本学习, 小样本关系分类, 原型网络, 知识增强

Abstract:

Few-Shot Relation Classification (FSRC) refers to the use of a small number of labeled instances to classify various relations within a task, and it can be quickly applied to categorize completely new classes. However, existing few-shot classification algorithms show limited generalization capabilities when distributional differences exist between the test and training domains, which leads to significant performance degradation. Therefore, a knowledge-enhanced adaptive prototyping network is proposed for domain adaptation tasks, which helps improve the robustness of the model by exploring connections between instances while learning a priori knowledge about relations and intrinsic semantics to obtain interpretable prototypes. Specifically, the correlations between supporting and query instances are captured by introducing an interactive attention mechanism to highlight key instances and generate interactive instances. The adaptive prototype fusion mechanism generates adaptive hybrid coefficients using relational information as anchors and combines instances with relational information through feature fusion to generate hybrid prototypes. Experiments are conducted on FewRel 1.0 and FewRel 2.0 datasets, and the effectiveness of the method is demonstrated. The experimental results show that the classification accuracy of the proposed network model is significantly higher compared to that of the baseline model. The proposed model has better classification performance and stability.

Key words: Relation Classification (RC), few-shot learning, Few-Shot Relation Classification (FSRC), prototype networks, knowledge-enhanced

张河萍, 方志军, 卢俊鑫, 高永彬. 基于知识增强自适应原型网络的小样本关系分类[J]. 计算机工程, 2025, 51(4): 129-136.

ZHANG Heping, FANG Zhijun, LU Junxin, GAO Yongbin. Few-Shot Relation Classification Based on Knowledge-Enhanced Adaptive Prototype Networks[J]. Computer Engineering, 2025, 51(4): 129-136.

https://www.ecice06.com/CN/Y2025/V51/I4/129

图/表 6

参考文献 28

1	TRISEDYA B D, WEIKUM G, QI J Z, et al. Neural relation extraction for knowledge base enrichment[C]//Proceedings of Annual Meeting of the Association for Computational Linguistics. [S. l. ]: Association for Computational Linguistics, 2019: 229-240.
2	LI Z F , LIU H , ZHANG Z L , et al. Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33 (8): 3961- 3973. doi: 10.1109/TNNLS.2021.3055147
3	胡晗, 刘鹏远. 小样本关系分类研究综述. 中文信息学报, 2022, 36 (2): 1- 11. doi: 10.3969/j.issn.1003-0077.2022.02.001
	HU H , LIU P Y . Few-shot relation classification: a survey. Journal of Chinese Information Processing, 2022, 36 (2): 1- 11. doi: 10.3969/j.issn.1003-0077.2022.02.001
4	YUAN J B, GUO H, JINzW, et al. One-shot learning for fine-grained relation extraction via convolutional siamese neural network[C]//Proceedings of 2017 IEEE International Conference on Big Data. Washington D. C., USA: IEEE Press, 2017: 21-35.
5	SUNG F, YANG Y X, ZHANG L, et al. Learning to compare: relation network for few-shot learning[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 1199-1208.
6	HAN X, ZHU H, YUPF, et al. FewRel: a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation[EB/OL]. [2023-10-12]. https://arxiv.org/pdf/1810.10147.
7	MUNKHDALAI T, YU H. Meta networks[C]//Proceedings of International Conference on Machine Learning. New York, USA: ACM Press, 2017: 102-109.
8	SNELL J, SWERSKY K, ZEMELRS. Prototypical networks for few-shot learning[EB/OL]. [2023-10-12]. https://arxiv.org/pdf/1703.05175.
9	HOSPEDALES T , ANTONIOU A , MICAELLI P , et al. Meta-learning in neural networks: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44, 5149- 5169.
10	ZHANG S C , LI X L , ZONG M , et al. Efficient kNN classification with different numbers of nearest neighbors. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29 (5): 1774- 1785. doi: 10.1109/TNNLS.2017.2673241
11	ZHAO A, DING M Y, LUzW, et al. Domain-adaptive few-shot learning[C]//Proceedings of 2021 IEEE Winter Conference on Applications of Computer Vision. Washington D. C., USA: IEEE Press, 2021: 1389-1398.
12	GAO T Y, HAN X, ZHU H, et al. FewRel 2.0: towards more challenging few-shot relation classification[EB/OL]. [2023-10-12]. https://arxiv.org/abs/1910.07124v1.
13	TIAN Y J , ZHAO X X , HUANG W . Meta-learning approaches for learning-to-learn in deep learning: a survey. Neurocomputing, 2022, 44, 203- 223.
14	JIANG W , HUANG K , GENG J , et al. Multi-scale metric learning for few-shot learning. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31 (3): 1091- 1102. doi: 10.1109/TCSVT.2020.2995754
15	RAVI S, LAROCHELLE H. Optimization as a model for few-shot learning[C]//Proceedings of International Conference on Learning Representations. New York, USA: ACM Press, 2017: 135-139.
16	FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[EB/OL]. [2023-10-12]. https://arxiv.org/pdf/1703.03400.
17	GAO T Y, HAN X, LIUzY, et al. Hybrid attention-based prototypical networks for noisy few-shot relation classification[C]//Proceedings of AAAI Conference on Artificial Intelligence. [S. l. ]: AAAI Press, 2019: 6187-6195.
18	YEzX, LINGzH. Multi-level matching and aggregation network for few-shot relation classification[EB/OL]. [2023-10-12]. https://arxiv.org/abs/1906.06678.
19	QU M, GAO T, XHONNEUX L P, et al. Few-shot relation extraction via bayesian meta-learning on relation graphs[C]//Proceedings of International Conference on Machine Learning. New York, USA: ACM Press, 2020: 7867-7876.
20	HAN J L, CHENG B, LU W. Exploring task difficulty for few-shot relation extraction[EB/OL]. [2023-10-12]. https://arxiv.org/abs/2109.05473?context=cs.CL.
21	YANG S, ZHANG Y F, NIU G L, et al. Entity concept-enhanced few-shot relation extraction[EB/OL]. [2023-10-12]. https://arxiv.org/abs/2106.02401?context=cs.AI.
22	YANG K, ZHENG N, DAI X, et al. Enhance prototypical network with text descriptions for few-shot relation classification[C]//Proceedings of the 29th ACM International Conference on Information&Knowledge Management. New York, USA: ACM Press, 2020: 2273-2276.
23	DONG M P, PANcG, LUOzP. MapRE: an effective semantic mapping approach for low-resource relation extraction[EB/OL]. [2023-10-12]. https://arxiv.org/abs/2109.04108?context=cs.
24	SOARES L B, FITZGERALD N, LING J, et al. Matching the blanks: distributional similarity for relation learning[EB/OL]. [2023-10-12]. https://arxiv.org/abs/1906.03158.
25	CONG X, YU B W, LIU T W, et al. Inductive unsupervised domain adaptation for few-shot classification via clustering[C]//Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Germany: Springer, 2021: 624-639.
26	DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional Transformers for language understanding[C]//Proceedings of Conference on the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. San Diego, USA: Association for Computational Linguistic, 2019: 4171-4186.
27	LIU Y, HU J, WAN X, et al. Learn from relation information: towards prototype representation rectification for few-shot relation extraction[C]//Proceedings of the Association for Computational Linguistics. San Diego, USA: Association for Computational Linguistic, 2022: 1822-1831.
28	刘昊鑫, 董超, 勾智楠, 等. 融合混合表征的小样本关系抽取方法. 计算机工程, 2023, 49 (8): 63- 68. doi: 10.19678/j.issn.1000-3428.0065258
	LIU H X , DONG C , GOU Z N , et al. Few-shot relation extraction method fusing with hybrid representation. Computing Engineering, 2023, 49 (8): 63- 68. doi: 10.19678/j.issn.1000-3428.0065258

[1]	王月昊, 周若华. 低资源环境下的语音唤醒研究综述[J]. 计算机工程, 2025, 51(2): 35-53.
[2]	陈佳玉, 王元龙, 张虎. 基于文本知识增强的问题生成模型[J]. 计算机工程, 2024, 50(6): 86-93.
[3]	司明悦, 齐斌, 张文胜, 张雷. 基于张量计算的智慧交通多维数据计算与小样本学习[J]. 计算机工程, 2024, 50(4): 41-49.
[4]	刘昊鑫, 董超, 勾智楠, 高凯. 融合混合表征的小样本关系抽取方法[J]. 计算机工程, 2023, 49(8): 63-68.
[5]	杨燕燕, 谢明轩, 曹江峡, 王学宾, 柳厅文, 杜彦辉. 基于原型网络的中文分类模型对抗样本生成[J]. 计算机工程, 2023, 49(8): 54-62.
[6]	刘金硕, 王代辰, 邓娟, 王丽娜. 基于长尾分类算法的网络不良信息分类[J]. 计算机工程, 2023, 49(8): 13-19, 28.
[7]	孔博, 韩虎, 陈景景, 白雪, 邓飞. 基于虚拟依存关系与知识增强的方面级情感分析[J]. 计算机工程, 2023, 49(10): 53-63.
[8]	仇真, 奚雪峰, 崔志明, 盛胜利, 胡伏原. 基于多分辨率自蒸馏网络的小样本图像分类[J]. 计算机工程, 2022, 48(12): 232-240.
[9]	陈良臣, 傅德印. 面向小样本数据的机器学习方法研究综述[J]. 计算机工程, 2022, 48(11): 1-13.
[10]	王会勇, 卢超, 张晓明. 基于小样本学习和语义信息的图像描述模型[J]. 计算机工程, 2021, 47(8): 260-270.
[11]	汪荣贵, 汤明空, 杨娟, 薛丽霞, 胡敏. 语义匹配网络的小样本学习[J]. 计算机工程, 2021, 47(5): 244-250,259.
[12]	叶萌, 杨娟, 汪荣贵, 薛丽霞, 李懂. 基于特征聚合网络的小样本学习方法[J]. 计算机工程, 2021, 47(3): 77-82.
[13]	胡新棒, 于溆乔, 李邵梅, 张建朋. 基于知识增强的中文命名实体识别[J]. 计算机工程, 2021, 47(11): 84-92.
[14]	伍杰华. 基于RReliefF特征选择算法的复杂网络链接分类[J]. 计算机工程, 2017, 43(8): 208-214.
[15]	潘洁珠, 周晓, 吴共庆, 胡学钢. 基于小样本学习的垃圾邮件过滤方法[J]. 计算机工程, 2010, 36(21): 245-247.

选择文件类型/文献管理软件名称

选择包含的内容