《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (3): 732-740.DOI: 10.11772/j.issn.1001-9081.2025030371
收稿日期:2025-04-10
修回日期:2025-05-23
接受日期:2025-05-28
发布日期:2025-06-12
出版日期:2026-03-10
通讯作者:
李贯峰
作者简介:肖毓航(1999—),男,福建莆田人,硕士研究生,CCF会员,主要研究方向:关系抽取基金资助:
Yuhang XIAO1, Guanfeng LI1,2(
), Yuyin CHEN1, Jing QIN1
Received:2025-04-10
Revised:2025-05-23
Accepted:2025-05-28
Online:2025-06-12
Published:2026-03-10
Contact:
Guanfeng LI
About author:XIAO Yuhang, born in 1999, M. S. candidate. His research interests include relation extraction.Supported by:摘要:
小样本关系抽取(FSRE)任务旨在从有限的标注数据中识别文本中实体间的语义关系。针对现有方法因采用单一视角的对比学习和静态图结构而导致的特征对齐不足与任务适配性差等问题,提出一种融合多视角对比学习与动态图生成机制的FSRE模型SAGM(Synergistic Anchored Graph-based Model)。该模型在预训练阶段,通过多视角对比学习引入句子锚定和标签锚定策略,从而优化实例与关系标签特征的对齐效果;在任务生成阶段,利用图生成模块构建任务特定的图结构,并结合多头注意力引导层动态调整特征重要性,从而提升模型在小样本和跨领域任务中的适应性。在FewRel 1.0、FewRel 2.0以及NYT-25数据集上的实验结果表明,所提模型在多个N-way K-shot设置下取得了较高的准确率,表现出良好的泛化能力和任务适应性,验证了它在小样本和跨领域场景中的有效性。
中图分类号:
肖毓航, 李贯峰, 陈昱胤, 秦晶. 基于图的多视角对比学习小样本关系抽取模型[J]. 计算机应用, 2026, 46(3): 732-740.
Yuhang XIAO, Guanfeng LI, Yuyin CHEN, Jing QIN. Few-shot relation extraction model with graph-based multi-view contrastive learning[J]. Journal of Computer Applications, 2026, 46(3): 732-740.
| 数据集 | 数据来源 | 训练集类别数 | 验证集类别数 | 测试集类别数 | 实例数 |
|---|---|---|---|---|---|
| FewRel 1.0 | Wiki | 64 | 16 | 20 | 700 |
| FewRel 2.0 | Wiki SEmEval PubMed | 64 | 10 | 15 | 100 |
| NYT-25 | NewYork Times | 10 | 5 | 10 | 100 |
表1 数据集的基本信息
Tab. 1 Basic information of datasets
| 数据集 | 数据来源 | 训练集类别数 | 验证集类别数 | 测试集类别数 | 实例数 |
|---|---|---|---|---|---|
| FewRel 1.0 | Wiki | 64 | 16 | 20 | 700 |
| FewRel 2.0 | Wiki SEmEval PubMed | 64 | 10 | 15 | 100 |
| NYT-25 | NewYork Times | 10 | 5 | 10 | 100 |
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| Proto-CNN | 72.65 | 72.63 | 86.15 | 85.75 | 60.13 | 58.11 | 76.20 | 74.20 |
| Proto-BERT | 82.92 | 82.91 | 91.32 | 91.32 | 73.24 | 73.24 | 83.68 | 82.68 |
| BERT-PAIR | 85.66 | 85.66 | 89.48 | 89.48 | 76.84 | 76.84 | 81.76 | 80.16 |
| REGRAB | 87.95 | 87.95 | 92.54 | 92.54 | 80.26 | 80.24 | 86.72 | 85.74 |
| HCRP | 90.90 | 90.90 | 93.22 | 93.21 | 84.11 | 84.11 | 87.79 | 87.79 |
| SimpleFSRE | 91.29 | 90.39 | 94.05 | 94.05 | 86.09 | 86.09 | 89.68 | 89.68 |
| GM_GEN | 92.65 | 92.45 | 95.62 | 95.61 | 86.81 | 86.51 | 91.27 | 91.27 |
| AdapAug | 90.90 | 88.34 | 93.22 | 93.12 | 84.11 | 84.11 | 87.79 | 87.79 |
| MultiRep | 92.73 | 92.13 | 93.79 | 93.79 | 86.13 | 86.13 | 88.80 | 86.80 |
| RAPS | 92.26 | 92.06 | 94.08 | 93.68 | 87.23 | 87.23 | 89.87 | 88.37 |
| SAGM | 93.17 | 92.77 | 96.13 | 96.12 | 87.21 | 87.03 | 91.69 | 91.67 |
表2 不同FSRE模型在FewRel 1.0验证集上的性能对比 (%)
Tab. 2 Performance comparison of different FSRE models on FewRel 1.0 validation set
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| Proto-CNN | 72.65 | 72.63 | 86.15 | 85.75 | 60.13 | 58.11 | 76.20 | 74.20 |
| Proto-BERT | 82.92 | 82.91 | 91.32 | 91.32 | 73.24 | 73.24 | 83.68 | 82.68 |
| BERT-PAIR | 85.66 | 85.66 | 89.48 | 89.48 | 76.84 | 76.84 | 81.76 | 80.16 |
| REGRAB | 87.95 | 87.95 | 92.54 | 92.54 | 80.26 | 80.24 | 86.72 | 85.74 |
| HCRP | 90.90 | 90.90 | 93.22 | 93.21 | 84.11 | 84.11 | 87.79 | 87.79 |
| SimpleFSRE | 91.29 | 90.39 | 94.05 | 94.05 | 86.09 | 86.09 | 89.68 | 89.68 |
| GM_GEN | 92.65 | 92.45 | 95.62 | 95.61 | 86.81 | 86.51 | 91.27 | 91.27 |
| AdapAug | 90.90 | 88.34 | 93.22 | 93.12 | 84.11 | 84.11 | 87.79 | 87.79 |
| MultiRep | 92.73 | 92.13 | 93.79 | 93.79 | 86.13 | 86.13 | 88.80 | 86.80 |
| RAPS | 92.26 | 92.06 | 94.08 | 93.68 | 87.23 | 87.23 | 89.87 | 88.37 |
| SAGM | 93.17 | 92.77 | 96.13 | 96.12 | 87.21 | 87.03 | 91.69 | 91.67 |
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| Proto-CNN | 74.52 | 74.51 | 88.40 | 87.40 | 62.38 | 61.78 | 80.45 | 77.45 |
| Proto-BERT | 80.68 | 80.68 | 89.60 | 89.60 | 71.48 | 71.48 | 82.89 | 81.49 |
| BERT-PAIR | 88.32 | 88.32 | 93.22 | 93.22 | 80.63 | 80.63 | 87.02 | 85.02 |
| REGRAB | 90.30 | 90.30 | 94.25 | 94.25 | 84.09 | 84.08 | 89.93 | 88.83 |
| HCRP | 93.76 | 93.76 | 95.66 | 95.66 | 89.95 | 89.95 | 92.10 | 92.10 |
| SimpleFSRE | 94.42 | 93.52 | 96.37 | 96.37 | 90.73 | 90.73 | 93.47 | 93.47 |
| GM_GEN | 94.89 | 94.67 | 96.96 | 96.94 | 91.23 | 91.11 | 94.30 | 94.30 |
| AdapAug | 93.76 | 92.56 | 95.66 | 95.56 | 89.95 | 89.95 | 92.10 | 92.10 |
| MultiRep | 94.18 | 93.48 | 96.29 | 96.29 | 91.07 | 91.07 | 91.98 | 90.98 |
| RAPS | 94.93 | 94.43 | 96.92 | 95.52 | 90.65 | 90.65 | 93.72 | 92.52 |
| SAGM | 95.11 | 94.81 | 97.21 | 97.11 | 92.11 | 91.21 | 94.77 | 94.57 |
表3 不同FSRE模型在FewRel 1.0测试集上的性能对比 (%)
Tab. 3 Performance comparison of different FSRE models on FewRel 1.0 test set
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| Proto-CNN | 74.52 | 74.51 | 88.40 | 87.40 | 62.38 | 61.78 | 80.45 | 77.45 |
| Proto-BERT | 80.68 | 80.68 | 89.60 | 89.60 | 71.48 | 71.48 | 82.89 | 81.49 |
| BERT-PAIR | 88.32 | 88.32 | 93.22 | 93.22 | 80.63 | 80.63 | 87.02 | 85.02 |
| REGRAB | 90.30 | 90.30 | 94.25 | 94.25 | 84.09 | 84.08 | 89.93 | 88.83 |
| HCRP | 93.76 | 93.76 | 95.66 | 95.66 | 89.95 | 89.95 | 92.10 | 92.10 |
| SimpleFSRE | 94.42 | 93.52 | 96.37 | 96.37 | 90.73 | 90.73 | 93.47 | 93.47 |
| GM_GEN | 94.89 | 94.67 | 96.96 | 96.94 | 91.23 | 91.11 | 94.30 | 94.30 |
| AdapAug | 93.76 | 92.56 | 95.66 | 95.56 | 89.95 | 89.95 | 92.10 | 92.10 |
| MultiRep | 94.18 | 93.48 | 96.29 | 96.29 | 91.07 | 91.07 | 91.98 | 90.98 |
| RAPS | 94.93 | 94.43 | 96.92 | 95.52 | 90.65 | 90.65 | 93.72 | 92.52 |
| SAGM | 95.11 | 94.81 | 97.21 | 97.11 | 92.11 | 91.21 | 94.77 | 94.57 |
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| Proto-CNN | 35.09 | 33.23 | 49.37 | 49.36 | 22.98 | 22.22 | 35.22 | 32.47 |
| Proto-BERT | 40.12 | 38.12 | 51.50 | 51.51 | 26.45 | 26.45 | 36.93 | 34.92 |
| BERT-PAIR | 67.41 | 66.92 | 78.57 | 78.57 | 54.89 | 54.63 | 66.85 | 66.37 |
| HCRP | 76.34 | 75.86 | 83.03 | 82.97 | 63.77 | 63.52 | 72.94 | 72.23 |
| GM_GEN | 76.67 | 76.34 | 91.28 | 91.12 | 64.19 | 63.27 | 84.84 | 83.64 |
| SAGM | 77.53 | 77.41 | 92.12 | 92.10 | 65.11 | 63.91 | 85.66 | 84.46 |
表4 FewRel 2.0测试集上FSRE模型的性能对比 (%)
Tab. 4 Performance comparison of FSRE models on FewRel 2.0 test set
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| Proto-CNN | 35.09 | 33.23 | 49.37 | 49.36 | 22.98 | 22.22 | 35.22 | 32.47 |
| Proto-BERT | 40.12 | 38.12 | 51.50 | 51.51 | 26.45 | 26.45 | 36.93 | 34.92 |
| BERT-PAIR | 67.41 | 66.92 | 78.57 | 78.57 | 54.89 | 54.63 | 66.85 | 66.37 |
| HCRP | 76.34 | 75.86 | 83.03 | 82.97 | 63.77 | 63.52 | 72.94 | 72.23 |
| GM_GEN | 76.67 | 76.34 | 91.28 | 91.12 | 64.19 | 63.27 | 84.84 | 83.64 |
| SAGM | 77.53 | 77.41 | 92.12 | 92.10 | 65.11 | 63.91 | 85.66 | 84.46 |
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| Proto-CNN | 35.09 | 31.98 | 49.37 | 47.23 | 22.98 | 21.11 | 35.22 | 33.22 |
| Proto-BERT | 77.63 | 75.32 | 87.25 | 86.13 | 66.49 | 65.32 | 79.51 | 76.12 |
| BERT-PAIR | 80.78 | 79.56 | 88.13 | 87.32 | 72.65 | 71.32 | 79.68 | 76.34 |
| HCRP | 91.46 | 90.76 | 95.76 | 94.32 | 86.40 | 86.11 | 92.66 | 91.32 |
| AdapAug | 92.56 | 91.21 | 96.33 | 95.67 | 87.76 | 86.32 | 93.68 | 92.93 |
| SAGM | 93.12 | 92.17 | 96.95 | 96.87 | 88.31 | 88.30 | 94.03 | 93.21 |
表5 NYT-25域适应测试集上FSRE模型的性能对比 (%)
Tab. 5 Performance comparison of FSRE models on NYT-25 domain adaptation test set
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| Proto-CNN | 35.09 | 31.98 | 49.37 | 47.23 | 22.98 | 21.11 | 35.22 | 33.22 |
| Proto-BERT | 77.63 | 75.32 | 87.25 | 86.13 | 66.49 | 65.32 | 79.51 | 76.12 |
| BERT-PAIR | 80.78 | 79.56 | 88.13 | 87.32 | 72.65 | 71.32 | 79.68 | 76.34 |
| HCRP | 91.46 | 90.76 | 95.76 | 94.32 | 86.40 | 86.11 | 92.66 | 91.32 |
| AdapAug | 92.56 | 91.21 | 96.33 | 95.67 | 87.76 | 86.32 | 93.68 | 92.93 |
| SAGM | 93.12 | 92.17 | 96.95 | 96.87 | 88.31 | 88.30 | 94.03 | 93.21 |
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| w/o syn | 93.21 | 93.20 | 95.12 | 95.11 | 90.26 | 90.26 | 93.13 | 93.11 |
| w/o mask | 92.17 | 92.15 | 93.23 | 93.22 | 88.12 | 88.12 | 91.19 | 91.17 |
| w/o att | 94.91 | 94.91 | 96.96 | 96.54 | 91.87 | 91.73 | 94.12 | 94.11 |
| w/o synatt | 92.89 | 92.87 | 94.96 | 94.32 | 90.23 | 89.65 | 92.30 | 92.23 |
| SAGM | 95.11 | 94.81 | 97.21 | 97.11 | 92.11 | 91.21 | 94.77 | 94.57 |
表 6 消融实验结果 (%)
Tab. 6 Ablation experimental results
| 模型 | 5-way 1-shot | 5-way 5-shot | 10-way 1-shot | 10-way 5-shot | ||||
|---|---|---|---|---|---|---|---|---|
| Acc | F1 | Acc | F1 | Acc | F1 | Acc | F1 | |
| w/o syn | 93.21 | 93.20 | 95.12 | 95.11 | 90.26 | 90.26 | 93.13 | 93.11 |
| w/o mask | 92.17 | 92.15 | 93.23 | 93.22 | 88.12 | 88.12 | 91.19 | 91.17 |
| w/o att | 94.91 | 94.91 | 96.96 | 96.54 | 91.87 | 91.73 | 94.12 | 94.11 |
| w/o synatt | 92.89 | 92.87 | 94.96 | 94.32 | 90.23 | 89.65 | 92.30 | 92.23 |
| SAGM | 95.11 | 94.81 | 97.21 | 97.11 | 92.11 | 91.21 | 94.77 | 94.57 |
| [1] | WANG H, QIN K, ZAKARI R Y, et al. Deep neural network-based relation extraction: an overview [J]. Neural Computing and Applications, 2022, 34(6): 4781-4801. |
| [2] | LIU C, SUN W, CHAO W, et al. Convolution neural network for relation extraction [C]// Proceedings of the 2013 International Conference on Advanced Data Mining and Applications, LNCS 8347. Berlin: Springer, 2013: 231-242. |
| [3] | ZHANG D, WANG D. Relation classification via recurrent neural network [EB/OL]. [2024-08-13].. |
| [4] | NAYAK T, NG H T. Effective modeling of encoder-decoder architecture for joint entity and relation extraction [C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2020: 8528-8535. |
| [5] | XUE F, SUN A, ZHANG H, et al. GDPNet: refining latent multi-view graph for relation extraction [C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2021: 14194-14202. |
| [6] | YE D, LIN Y, LI P, et al. Packed levitated marker for entity and relation extraction [C]// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg: ACL, 2022: 4904-4917. |
| [7] | 胡晗,刘鹏远. 小样本关系分类研究综述[J]. 中文信息学报, 2020, 36(2): 1-11. |
| HU H, LIU P Y. Few-shot relation classification: a survey [J]. Journal of Chinese Information Processing, 2020, 36(2): 1-11. | |
| [8] | MINTZ M, BILLS S, SNOW R, et al. Distant supervision for relation extraction without labeled data [C]// Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Stroudsburg: ACL, 2009: 1003-1011. |
| [9] | BHARTIYA A, BADOLA K, MAUSAM. DiS-ReX: a multilingual dataset for distantly supervised relation extraction [C]// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Stroudsburg: ACL, 2022: 849-863. |
| [10] | 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. Red Hook: Curran Associates Inc., 2016: 3637-3645. |
| [11] | 黄友文,胡燕芳,魏国庆. 结合原型校准分布的小样本学习方法[J].电子测量技术, 2022, 45(5): 132-139. |
| HUANG Y W, HU Y F, WEI G Q. Prototype-based calibration distribution for few-shot learning [J]. Electronic Measurement Technology, 2022, 45(5): 132-139. | |
| [12] | MUNKHDALAI T, YU H. Meta networks [C]// Proceedings of the 34th International Conference on Machine Learning. New York: JMLR.org, 2017: 2554-2563. |
| [13] | KOCH G, ZEMEL R, SALAKHUTDINOV R. Siamese neural networks for one-shot image recognition [EB/OL]. [2024-12-04].. |
| [14] | SNELL J, SWERSKY K, ZEMEL R. Prototypical networks for few-shot learning [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 4080-4090. |
| [15] | ANTONIOU A, EDWARDS H, STORKEY A. How to train your MAML [EB/OL]. [2024-12-04].. |
| [16] | LI H, DONG W, MEI X, et al. LGM-Net: learning to generate matching networks for few-shot learning [C]// Proceedings of the 36th International Conference on Machine Learning. New York: JMLR.org, 2019: 3825-3834. |
| [17] | ZHMOGINOV A, SANDLER M, VLADYMYROV M. HyperTransformer: model generation for supervised and semi-supervised few-shot learning [C]// Proceedings of the 39th International Conference on Machine Learning. New York: JMLR.org, 2022: 27075-27098. |
| [18] | HAN X, ZHU H, YU P, et al. FewRel: a large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation [C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2018: 4803-4809. |
| [19] | XIE Y, XU H, LI J, et al. Heterogeneous graph neural networks for noisy few-shot relation classification [J]. Knowledge-Based Systems, 2020, 194: No.105548. |
| [20] | QU M, GAO T, XHONNEUX L P A C, et al. Few-shot relation extraction via Bayesian meta-learning on relation graphs [C]// Proceedings of the 37th International Conference on Machine Learning. New York: JMLR.org, 2020: 7867-7876. |
| [21] | GAO T, HAN X, ZHU H, et al. FewRel 2.0: towards more challenging few-shot relation classification [C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2019: 6250-6255. |
| [22] | DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional Transformers for language understanding [C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Stroudsburg: ACL, 2019: 4171-4186. |
| [23] | SOARES L B, FITZGERALD N, LING J, et al. Matching the blanks: distributional similarity for relation learning [C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2019: 2895-2905. |
| [24] | GAO T, HAN X, LIU Z, et al. Hybrid attention-based prototypical networks for noisy few-shot relation classification [C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 6407-6414. |
| [25] | HAN J, CHENG B, LU W. Exploring task difficulty for few-shot relation extraction [C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2021: 2605-2616. |
| [26] | LIU Y, HU J, WAN X, et al. A simple yet effective relation information guided approach for few-shot relation extraction [C]// Findings of the Association for Computational Linguistics: ACL 2022. Stroudsburg: ACL, 2022: 757-763. |
| [27] | 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 and Knowledge Management. New York: ACM, 2020: 2273-2276. |
| [28] | LI X, LIU C, YU J, et al. Prototypical attention network for few-shot relation classification with entity-aware embedding module[J]. Applied Intelligence, 2023, 53(9): 10978-10994. |
| [29] | FENG J, WEI Q, CUI J. Prototypical networks relation classification model based on entity convolution [J]. Computer Speech and Language, 2023, 77: No.101432. |
| [30] | HE H, NIU H, FENG J, et al. A prototype network enhanced relation semantic representation for few-shot relation extraction[J]. Human-Centric Intelligent Systems, 2023, 3: 1-12. |
| [31] | 季一木,张旺,刘强,等. 基于小样本学习的中文文本关系抽取方法[J]. 南京邮电大学学报(自然科学版), 2023, 43(4): 64-71. |
| JI Y M, ZHANG W, LIU Q, et al. A relation extraction method for Chinese text based on few-shot learning [J]. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 2023, 43(4): 64-71. | |
| [32] | YANG S, ZHANG Y, NIU G, et al. Entity concept-enhanced few-shot relation extraction [C]// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). Stroudsburg: ACL, 2021: 987-991. |
| [33] | HE K, FAN H, WU Y, et al. Momentum contrast for unsupervised visual representation learning [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 9726-9735. |
| [34] | CHEN T, KORNBLITH S, NOROUZI M, et al. A simple framework for contrastive learning of visual representations [C]// Proceedings of the 37th International Conference on Machine Learning. New York: JMLR.org, 2020: 1597-1607. |
| [35] | TIAN Y, KRISHNAN D, ISOLA P. Contrastive multiview coding[C]// Proceedings of the 2020 European Conference on Computer Vision, LNCS 12356. Cham: Springer, 2020: 776-794. |
| [36] | ZHANG Y, JIANG H, MIURA Y, et al. Contrastive learning of medical visual representations from paired images and text [C]// Proceedings of the 7th Machine Learning for Healthcare Conference. New York: JMLR.org, 2022: 2-25. |
| [37] | RADFORD A, KIM J W, HALLACY C, et al. Learning transferable visual models from natural language supervision [C]// Proceedings of the 38th International Conference on Machine Learning. New York: JMLR.org, 2021: 8748-8763. |
| [38] | LUO D, GAN Y, HOU R, et al. Synergistic anchored contrastive pre-training for few-shot relation extraction [C]// Proceedings of the 38th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2024: 18742-18750. |
| [39] | BORCHERT P, DE WEERDT J, MOENS M F. Efficient information extraction in few-shot relation classification through contrastive representation learning [C]// Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers). Stroudsburg: ACL, 2024: 638-646. |
| [40] | LI W, QIAN T. Graph-based model generation for few-shot relation extraction [C]// Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2022: 62-71. |
| [41] | LI R, ZHONG J, HU W, et al. Adaptive class augmented prototype network for few-shot relation extraction [J]. Neural Networks, 2024, 169: 134-142. |
| [42] | ZHANG Y, CEN M, WU T, et al. RAPS: a novel few-shot relation extraction pipeline with query-information guided attention and adaptive prototype fusion: RAPS for few-shot RE [C]// Proceedings of the 2024 International Conference on Modeling, Natural Language Processing and Machine Learning. New York: ACM, 2024: 147-152. |
| [1] | 刘晓霞, 况立群, 王松, 焦世超, 韩慧妍, 熊风光. 多尺度时空解耦的骨架行为识别对比学习[J]. 《计算机应用》唯一官方网站, 2026, 46(3): 767-774. |
| [2] | 董莉梅, 李雁姿, 李家印, 许力. 基于邻域增强的无监督图异常检测[J]. 《计算机应用》唯一官方网站, 2026, 46(2): 458-466. |
| [3] | 魏涵玥, 郭晨娟, 梅杰源, 田锦东, 陈鹏, 徐榕荟, 杨彬. 融合时频特征与混合文本的多模态股票预测框架MATCH[J]. 《计算机应用》唯一官方网站, 2026, 46(2): 427-436. |
| [4] | 罗虎, 张明书. 基于跨模态注意力机制与对比学习的谣言检测方法[J]. 《计算机应用》唯一官方网站, 2026, 46(2): 361-367. |
| [5] | 李玟, 李开荣, 杨凯. 基于数据增强的子图感知对比学习[J]. 《计算机应用》唯一官方网站, 2026, 46(1): 1-9. |
| [6] | 杨兴耀, 齐正, 于炯, 张祖莲, 马帅, 沈洪涛. 时间感知和空间增强的双通道图神经网络会话推荐模型[J]. 《计算机应用》唯一官方网站, 2026, 46(1): 104-112. |
| [7] | 程梓洋, 黄瑞章, 薛菁菁. 深度演化主题聚类模型[J]. 《计算机应用》唯一官方网站, 2026, 46(1): 85-94. |
| [8] | 刘超, 余岩化. 融合降噪策略与多视图对比学习的知识感知推荐模型[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 2827-2837. |
| [9] | 许志雄, 李波, 边小勇, 胡其仁. 对抗样本嵌入注意力U型网络的3D医学图像分割[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 3011-3016. |
| [10] | 王祉苑, 彭涛, 杨捷. 分布外检测中训练与测试的内外数据整合[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2497-2506. |
| [11] | 王静, 刘嘉星, 宋婉莹, 薛嘉兴, 丁温欣. 基于空间变换网络和特征分布校准的小样本皮肤图像分类模型[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2720-2726. |
| [12] | 杨青, 朱焱. 改进语言规则中的表示的隐喻识别[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2491-2496. |
| [13] | 闫家鑫, 陈艳平, 杨卫哲, 黄瑞章, 秦永彬. 基于特征组合的异构图注意力网络关系抽取[J]. 《计算机应用》唯一官方网站, 2025, 45(8): 2470-2476. |
| [14] | 白瑞峰, 苟光磊, 文浪, 缪宛谕. 基于粒球原型网络的小样本图像分类方法[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2269-2277. |
| [15] | 谢劲, 褚苏荣, 强彦, 赵涓涓, 张华, 高勇. 用于胸片中硬负样本识别的双支分布一致性对比学习模型[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2369-2377. |
| 阅读次数 | ||||||
|
全文 |
|
|||||
|
摘要 |
|
|||||