《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (5): 1372-1378.DOI: 10.11772/j.issn.1001-9081.2024071001
• 第十届中国数据挖掘会议 • 上一篇
收稿日期:
2024-07-23
修回日期:
2024-09-07
接受日期:
2024-09-10
发布日期:
2024-09-25
出版日期:
2025-05-10
通讯作者:
刘晔
作者简介:
龙雨菲(2003—),女,湖南衡阳人,主要研究方向:数据挖掘、图学习、机器学习基金资助:
Yufei LONG, Yuchen MOU, Ye LIU()
Received:
2024-07-23
Revised:
2024-09-07
Accepted:
2024-09-10
Online:
2024-09-25
Published:
2025-05-10
Contact:
Ye LIU
About author:
LONG Yufei, born in 2003. Her research interests include data mining, graph learning, machine learning.Supported by:
摘要:
针对现有多源数据表示学习模型在处理大规模复杂高维数据时存在的容易遗漏数据源间高阶关联信息和易受到噪声干扰的问题,提出一种基于张量化图卷积网络(T-GCN)和对比学习的多源数据表示学习模型(MS-TGC)。首先,利用K近邻(KNN)算法和图卷积网络(GCN)统一多源数据维度,拼接得到张量化多源数据;其次,利用定义的张量图卷积算子实现高维图卷积运算,同时学习数据源内部信息及数据源间关联信息;最后,构建多源数据对比学习范式,通过添加基于语义一致性与标签一致性的对比约束,提升MS-TGC在处理含噪声数据时的表示学习准确率,增强模型的鲁棒性。实验结果表明,当有标签样本率为0.3时,与CONMF(Co-consensus Orthogonal Non-negative Matrix Factorization)模型相比,MS-TGC在BDGP和20newsgroup数据集上的半监督分类准确率分别提升了1.36和5.53个百分点。可见MS-TGC能够更有效地捕捉数据源间关联信息,降低噪声干扰,得到高质量多源数据表示。
中图分类号:
龙雨菲, 牟宇辰, 刘晔. 基于张量化图卷积网络和对比学习的多源数据表示学习模型[J]. 计算机应用, 2025, 45(5): 1372-1378.
Yufei LONG, Yuchen MOU, Ye LIU. Multi-source data representation learning model based on tensorized graph convolutional network and contrastive learning[J]. Journal of Computer Applications, 2025, 45(5): 1372-1378.
数据集 | 模型 | 不同有标签样本率下的准确率 | ||||
---|---|---|---|---|---|---|
0.1 | 0.2 | 0.3 | 0.4 | 0.5 | ||
BDGP | AMGL | 0.817 9±0.007 7 | 0.840 4±0.007 9 | 0.854 5±0.003 8 | 0.862 4±0.007 1 | 0.871 5±0.007 0 |
LMSSC | 0.657 3±0.019 1 | 0.658 9±0.018 7 | 0.665 0±0.017 0 | 0.669 6±0.019 3 | 0.675 0±0.012 9 | |
MVAR | 0.805 4±0.006 4 | 0.809 8±0.011 3 | 0.814 5±0.009 9 | 0.818 7±0.006 6 | 0.821 9±0.010 3 | |
MR-GCN | 0.918 8±0.009 0 | 0.925 5±0.007 8 | 0.932 3±0.005 1 | 0.933 8±0.004 8 | 0.938 6±0.003 7 | |
CONMF | 0.932 3±0.004 0 | 0.944 4±0.007 3 | 0.947 6±0.009 0 | 0.948 1±0.008 7 | 0.955 6±0.006 4 | |
MS-TGC | 0.949 1±0.006 2 | 0.955 3±0.003 9 | 0.960 9±0.004 1 | 0.962 0±0.005 8 | 0.969 3±0.006 3 | |
CiteSeer | AMGL | 0.549 7±0.009 3 | 0.604 3±0.009 5 | 0.619 5±0.007 8 | 0.640 1±0.008 4 | 0.650 3±0.006 8 |
LMSSC | 0.581 7±0.360 6 | 0.552 6±0.005 3 | 0.553 8±0.010 0 | 0.568 7±0.003 0 | 0.640 4±0.003 2 | |
MVAR | 0.594 9±0.011 4 | 0.616 5±0.011 4 | 0.619 6±0.004 4 | 0.636 0±0.010 2 | 0.649 6±0.006 2 | |
MR-GCN | 0.591 6±0.021 8 | 0.619 1±0.014 5 | 0.623 6±0.011 9 | 0.624 6±0.013 7 | 0.654 0±0.008 4 | |
CONMF | 0.587 3±0.004 7 | 0.593 5±0.002 9 | 0.617 9±0.007 3 | 0.630 1±0.006 9 | 0.642 1±0.005 7 | |
MS-TGC | 0.606 2±0.025 9 | 0.618 4±0.022 0 | 0.624 9±0.011 7 | 0.639 0±0.015 5 | 0.655 4±0.016 8 | |
MNIST-USPS | AMGL | 0.957 0±0.001 6 | 0.960 4±0.000 5 | 0.981 0±0.001 3 | 0.982 5±0.001 0 | 0.982 4±0.001 5 |
LMSSC | 0.944 9±0.009 6 | 0.974 9±0.002 6 | 0.975 6±0.002 7 | 0.974 9±0.003 7 | 0.977 5±0.003 5 | |
MVAR | 0.671 4±0.012 1 | 0.868 3±0.007 0 | 0.902 8±0.002 9 | 0.919 3±0.004 8 | 0.928 4±0.005 0 | |
MR-GCN | 0.958 0±0.005 0 | 0.964 5±0.003 8 | 0.974 0±0.003 1 | 0.979 3±0.003 5 | 0.974 0±0.001 7 | |
CONMF | 0.945 1±0.002 7 | 0.948 7±0.007 6 | 0.957 1±0.008 0 | 0.963 4±0.006 2 | 0.966 7±0.001 6 | |
MS-TGC | 0.969 3±0.006 3 | 0.981 9±0.004 1 | 0.985 8±0.003 3 | 0.987 1±0.002 3 | 0.987 9±0.004 2 | |
20newsgroup | AMGL | 0.710 0±0.025 0 | 0.762 2±0.019 4 | 0.795 7±0.018 4 | 0.813 0±0.018 2 | 0.834 0±0.024 3 |
LMSSC | 0.632 0±0.075 3 | 0.643 1±0.022 2 | 0.654 7±0.016 2 | 0.701 7±0.022 4 | 0.727 2±0.022 3 | |
MVAR | 0.710 2±0.039 2 | 0.796 7±0.031 8 | 0.815 7±0.029 4 | 0.853 0±0.023 5 | 0.864 4±0.025 7 | |
MR-GCN | 0.718 0±0.035 8 | 0.779 2±0.022 2 | 0.799 4±0.017 1 | 0.808 0±0.018 8 | 0.835 7±0.022 1 | |
CONMF | 0.748 9±0.002 7 | 0.771 4±0.006 2 | 0.775 7±0.003 2 | 0.794 6±0.005 1 | 0.838 6±0.002 4 | |
MS-TGC | 0.777 3±0.254 0 | 0.805 0±0.027 8 | 0.831 0±0.018 5 | 0.856 6±0.017 1 | 0.867 6±0.018 0 |
表1 不同有标签样本率时4个基准数据集上的半监督分类准确率对比
Tab. 1 Semi-supervised classification accuracy comparison on 4 benchmark datasets at different labeled sample ratio
数据集 | 模型 | 不同有标签样本率下的准确率 | ||||
---|---|---|---|---|---|---|
0.1 | 0.2 | 0.3 | 0.4 | 0.5 | ||
BDGP | AMGL | 0.817 9±0.007 7 | 0.840 4±0.007 9 | 0.854 5±0.003 8 | 0.862 4±0.007 1 | 0.871 5±0.007 0 |
LMSSC | 0.657 3±0.019 1 | 0.658 9±0.018 7 | 0.665 0±0.017 0 | 0.669 6±0.019 3 | 0.675 0±0.012 9 | |
MVAR | 0.805 4±0.006 4 | 0.809 8±0.011 3 | 0.814 5±0.009 9 | 0.818 7±0.006 6 | 0.821 9±0.010 3 | |
MR-GCN | 0.918 8±0.009 0 | 0.925 5±0.007 8 | 0.932 3±0.005 1 | 0.933 8±0.004 8 | 0.938 6±0.003 7 | |
CONMF | 0.932 3±0.004 0 | 0.944 4±0.007 3 | 0.947 6±0.009 0 | 0.948 1±0.008 7 | 0.955 6±0.006 4 | |
MS-TGC | 0.949 1±0.006 2 | 0.955 3±0.003 9 | 0.960 9±0.004 1 | 0.962 0±0.005 8 | 0.969 3±0.006 3 | |
CiteSeer | AMGL | 0.549 7±0.009 3 | 0.604 3±0.009 5 | 0.619 5±0.007 8 | 0.640 1±0.008 4 | 0.650 3±0.006 8 |
LMSSC | 0.581 7±0.360 6 | 0.552 6±0.005 3 | 0.553 8±0.010 0 | 0.568 7±0.003 0 | 0.640 4±0.003 2 | |
MVAR | 0.594 9±0.011 4 | 0.616 5±0.011 4 | 0.619 6±0.004 4 | 0.636 0±0.010 2 | 0.649 6±0.006 2 | |
MR-GCN | 0.591 6±0.021 8 | 0.619 1±0.014 5 | 0.623 6±0.011 9 | 0.624 6±0.013 7 | 0.654 0±0.008 4 | |
CONMF | 0.587 3±0.004 7 | 0.593 5±0.002 9 | 0.617 9±0.007 3 | 0.630 1±0.006 9 | 0.642 1±0.005 7 | |
MS-TGC | 0.606 2±0.025 9 | 0.618 4±0.022 0 | 0.624 9±0.011 7 | 0.639 0±0.015 5 | 0.655 4±0.016 8 | |
MNIST-USPS | AMGL | 0.957 0±0.001 6 | 0.960 4±0.000 5 | 0.981 0±0.001 3 | 0.982 5±0.001 0 | 0.982 4±0.001 5 |
LMSSC | 0.944 9±0.009 6 | 0.974 9±0.002 6 | 0.975 6±0.002 7 | 0.974 9±0.003 7 | 0.977 5±0.003 5 | |
MVAR | 0.671 4±0.012 1 | 0.868 3±0.007 0 | 0.902 8±0.002 9 | 0.919 3±0.004 8 | 0.928 4±0.005 0 | |
MR-GCN | 0.958 0±0.005 0 | 0.964 5±0.003 8 | 0.974 0±0.003 1 | 0.979 3±0.003 5 | 0.974 0±0.001 7 | |
CONMF | 0.945 1±0.002 7 | 0.948 7±0.007 6 | 0.957 1±0.008 0 | 0.963 4±0.006 2 | 0.966 7±0.001 6 | |
MS-TGC | 0.969 3±0.006 3 | 0.981 9±0.004 1 | 0.985 8±0.003 3 | 0.987 1±0.002 3 | 0.987 9±0.004 2 | |
20newsgroup | AMGL | 0.710 0±0.025 0 | 0.762 2±0.019 4 | 0.795 7±0.018 4 | 0.813 0±0.018 2 | 0.834 0±0.024 3 |
LMSSC | 0.632 0±0.075 3 | 0.643 1±0.022 2 | 0.654 7±0.016 2 | 0.701 7±0.022 4 | 0.727 2±0.022 3 | |
MVAR | 0.710 2±0.039 2 | 0.796 7±0.031 8 | 0.815 7±0.029 4 | 0.853 0±0.023 5 | 0.864 4±0.025 7 | |
MR-GCN | 0.718 0±0.035 8 | 0.779 2±0.022 2 | 0.799 4±0.017 1 | 0.808 0±0.018 8 | 0.835 7±0.022 1 | |
CONMF | 0.748 9±0.002 7 | 0.771 4±0.006 2 | 0.775 7±0.003 2 | 0.794 6±0.005 1 | 0.838 6±0.002 4 | |
MS-TGC | 0.777 3±0.254 0 | 0.805 0±0.027 8 | 0.831 0±0.018 5 | 0.856 6±0.017 1 | 0.867 6±0.018 0 |
有标签样本率 | 半监督分类准确率 | |||
---|---|---|---|---|
W/O Contrastive | W/O T‑GCN | W/O T‑GCN + Contrastive | MS‑TGC | |
0.1 | 0.867 3±0.003 8 | 0.776 7±0.005 0 | 0.762 1±0.004 2 | 0.949 1±0.006 2 |
0.2 | 0.889 1±0.004 9 | 0.794 1±0.006 5 | 0.778 2±0.006 7 | 0.955 3±0.003 9 |
0.3 | 0.893 7±0.005 4 | 0.820 8±0.008 2 | 0.792 1±0.002 3 | 0.960 9±0.004 1 |
0.4 | 0.928 5±0.004 4 | 0.853 5±0.005 1 | 0.803 3±0.007 0 | 0.962 0±0.005 8 |
0.5 | 0.930 1±0.006 8 | 0.878 9±0.003 5 | 0.834 1±0.005 7 | 0.969 3±0.006 3 |
表2 BDGP数据集上的消融实验结果(分类准确率)
Tab. 2 Ablation experimental results on BDGP dataset (classification accuracy)
有标签样本率 | 半监督分类准确率 | |||
---|---|---|---|---|
W/O Contrastive | W/O T‑GCN | W/O T‑GCN + Contrastive | MS‑TGC | |
0.1 | 0.867 3±0.003 8 | 0.776 7±0.005 0 | 0.762 1±0.004 2 | 0.949 1±0.006 2 |
0.2 | 0.889 1±0.004 9 | 0.794 1±0.006 5 | 0.778 2±0.006 7 | 0.955 3±0.003 9 |
0.3 | 0.893 7±0.005 4 | 0.820 8±0.008 2 | 0.792 1±0.002 3 | 0.960 9±0.004 1 |
0.4 | 0.928 5±0.004 4 | 0.853 5±0.005 1 | 0.803 3±0.007 0 | 0.962 0±0.005 8 |
0.5 | 0.930 1±0.006 8 | 0.878 9±0.003 5 | 0.834 1±0.005 7 | 0.969 3±0.006 3 |
1 | ZHAO X, DAI Q, WU J, et al. Multi-view tensor graph neural networks through reinforced aggregation[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(4): 4077-4091. |
2 | LIU Y, HE L, CAO B, et al. Multi-view multi-graph embedding for brain network clustering analysis[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2018, 32(1): 117-124. |
3 | MA G X, HE L F, LU C T, et al. Multi-view clustering with graph embedding for connectome analysis[C]// Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York: ACM, 2017: 127-136. |
4 | PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: online learning of social representations[C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2014: 701-710. |
5 | PENG H, YANG R, WANG Z, et al. Lime: low-cost and incremental learning for dynamic heterogeneous information networks[J]. IEEE Transactions on Computers, 2022, 71(3): 628-642. |
6 | ZHANG X, HE L, CHEN K, et al. Multi-view graph convolutional network and its applications on neuroimage analysis for Parkinson's disease[C]// Proceedings of the 2018 AMIA Annual Symposium. Washington, DC: AMIA Publications, 2018: 1147-1156. |
7 | HASSANI K, KHASAHMADI A H. Contrastive multi-view representation learning on graphs[C]// Proceedings of the 37th International Conference on Machine Learning. New York: ACM, 2020: 4116-4126. |
8 | KHAN M R, BLUMENSTOCK J E. Multi-GCN: graph convolutional networks for multi-view networks, with applications to global poverty[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 606-613. |
9 | BRUNA J, ZAREMBA W, SZLAM A,et al. Spectral networks and locally connected networks on graphs[EB/OL]. [2024-03-08]. . |
10 | HENAFF M, BRUNA J, LeCUN Y. Deep convolutional networks on graph-structured data[EB/OL]. [2024-04-02]. . |
11 | DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]// Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2016: 3844-3852. |
12 | KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]// Proceedings of the 5th International Conference on Learning Representations. Red Hook: Curran Associates Inc., 2017: 2713-2726. |
13 | PENG S, SUGIYAMA K, MINE T. SVD-GCN: a simplified graph convolution paradigm for recommendation[C]// Proceedings of the 31st ACM International Conference on Information and Knowledge Management. New York: ACM, 2022: 1625-1634. |
14 | 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. Red Hook: Curran Associates Inc., 2017: 1025-1035. |
15 | MONTI F, BOSCAINI D, MASCI J, et al. Geometric deep learning on graphs and manifolds using mixture model CNNs[C]// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 5425-5434. |
16 | JØRGENSEN P B, JACOBSEN K W, SCHMIDT M N. Neural message passing with edge updates for predicting properties of molecules and materials [EB/OL]. [2023-12-22]. . |
17 | YUN S, JEONG M, KIM R, et al. Graph transformer networks[C]// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2019: 11983-11993. |
18 | SUN Y, WANG S, T-Y HSIEH, et al. MEGAN: a generative adversarial network for multi-view network embedding[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers Inc., 2019: 3527-3533. |
19 | 张园园.基于多模态图神经网络的药物相互作用预测算法研究[D].郑州:郑州大学,2021:17-25. |
ZHANG Y Y. Research on drug-drug interactions algorithm based on multimodal graph neural network[D]. Zhengzhou: Zhengzhou University, 2021:17-25. | |
20 | NG M K P, LI X, YE Y. MultiRank: co-ranking for objects and relations in multi-relational data[C]// Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2011: 1217-1225. |
21 | LI X, NG M K, YE Y. MultiComm: finding community structure in multi-dimensional networks[J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(4): 929-941. |
22 | LI X, YE Y, XU X. Low-rank tensor completion with total variation for visual data inpainting[C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2017: 2210-2216. |
23 | KILMER M E, MARTIN C D. Factorization strategies for third-order tensors[J]. Linear Algebra and its Applications, 2011, 435(3): 641-658. |
24 | SONG G, NG M K, ZHANG X. Robust tensor completion using transformed tensor singular value decomposition[J]. Numerical Linear Algebra with Applications, 2020, 27(3): No.e2299. |
25 | NIU C, SHAN H, WANG G. SPICE: semantic pseudo-labeling for image clustering[J]. IEEE Transactions on Image Processing, 2022, 31: 7264-7278. |
26 | VAN G W, VANDENHENDE S, GEORGOULIS S, et al. Scan: learning to classify images without labels[C]// Proceedings of the 2020 European Conference on Computer Vision. Cham: Springer, 2020: 268-285. |
27 | ZHAO C, WU W, ZHANG H, et al. Sleep stage classification via multi-view based self-supervised contrastive learning of EEG[EB/OL]. [2024-01-22]. . |
28 | LIN Y, GOU Y, LIU Z, et al. COMPLETER: incomplete multi-view clustering via contrastive prediction[C]// Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 11174-11183. |
29 | PIELAWSKI N, WETZER E, ÖFVERSTEDT J, et al. CoMIR: contrastive multimodal image representation for registration[C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 18433-18444. |
30 | 韩滕跃,牛少彰,张文.基于对比学习的多模态序列推荐算法[J].计算机应用,2022,42(6):1683-1688. |
HAN T Y, NIU S Z, ZHANG W. Multimodal sequential recommendation algorithm based on contrastive learning[J]. Journal of Computer Applications, 2022,42(6):1683-1688. | |
31 | YANG Q, CHENG Z, KANG Y, et al. A novel multi-view contrastive learning for herb recommendation [EB/OL]. [2024-02-11]. . |
32 | 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: ACM, 2020: 1597-1607. |
33 | NIE F P, LI J, LI X L. Parameter-free auto-weighted multiple graph learning: a framework for multiview clustering and semi-supervised classification[C]// Proceedings of the 25th International Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers Inc., 2016: 1881-1887. |
34 | BO X, KANG Z, ZHAO Z, et al. Latent multi-view semi-supervised classification[C]// Proceedings of the 2019 Asian Conference on Machine Learning. New York: JMLR, 2019: 348-362. |
35 | TAO H, HOU C P, NIE F P, et al. Scalable multi-view semi-supervised classification via adaptive regression[J]. IEEE Transactions on Image Processing, 2017, 26(9): 4283-4296. |
36 | HUANG Z C, LI X T, YE Y M, et al. MR-GCN: multi-relational graph convolutional networks based on generalized tensor product[C]// Proceedings of the 29th International Joint Conference on Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers Inc., 2020: 1258-1264. |
37 | LIANG N, YANG Z, LI Z, et al. Co-consensus semi-supervised multi-view learning with orthogonal non-negative matrix factorization[J]. Information Processing and Management, 2022, 59(5): No.103054. |
[1] | 田仁杰, 景明利, 焦龙, 王飞. 基于混合负采样的图对比学习推荐算法[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1053-1060. |
[2] | 党伟超, 温鑫瑜, 高改梅, 刘春霞. 基于多视图多尺度对比学习的图协同过滤[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1061-1068. |
[3] | 陈维, 施昌勇, 马传香. 基于多模态数据融合的农作物病害识别方法[J]. 《计算机应用》唯一官方网站, 2025, 45(3): 840-848. |
[4] | 王元龙, 刘亭华, 张虎. 基于跨模态对比学习的常识问答模型[J]. 《计算机应用》唯一官方网站, 2025, 45(3): 732-738. |
[5] | 张翰林, 王俊陆, 宋宝燕. 融合衍生特征的时间序列事件分类方法[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 428-435. |
[6] | 杨晟, 李岩. 面向目标检测的对比知识蒸馏方法[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 354-361. |
[7] | 严雪文, 黄章进. 基于对比学习的小样本图像分类方法[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 383-391. |
[8] | 余肖生, 王智鑫. 基于多层次图对比学习的序列推荐模型[J]. 《计算机应用》唯一官方网站, 2025, 45(1): 106-114. |
[9] | 杨兴耀, 陈羽, 于炯, 张祖莲, 陈嘉颖, 王东晓. 结合自我特征和对比学习的推荐模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2704-2710. |
[10] | 张春雪, 仇丽青, 孙承爱, 荆彩霞. 基于两阶段动态兴趣识别的购买行为预测模型[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2365-2371. |
[11] | 徐松, 张文博, 王一帆. 基于时空信息的轻量视频显著性目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2192-2199. |
[12] | 姚迅, 秦忠正, 杨捷. 生成式标签对抗的文本分类模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1781-1785. |
[13] | 蒋小霞, 黄瑞章, 白瑞娜, 任丽娜, 陈艳平. 基于事件表示和对比学习的深度事件聚类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1734-1742. |
[14] | 沈君凤, 周星辰, 汤灿. 基于改进的提示学习方法的双通道情感分析模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1796-1806. |
[15] | 汪炅, 唐韬韬, 贾彩燕. 无负采样的正样本增强图对比学习推荐方法PAGCL[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1485-1492. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||