Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (5): 1511-1517.DOI: 10.11772/j.issn.1001-9081.2022040553
• Cyber security • Previous Articles Next Articles
Kejun JIN, Hongtao YU(), Yiteng WU, Shaomei LI, Jianpeng ZHANG, Honghao ZHENG
Received:
2022-04-21
Revised:
2022-06-01
Accepted:
2022-06-06
Online:
2022-07-26
Published:
2023-05-10
Contact:
Hongtao YU
About author:
JIN Kejun, born in 1993, M. S. candidate. His research interest include artificial intelligence security.Supported by:
金柯君, 于洪涛(), 吴翼腾, 李邵梅, 张建朋, 郑洪浩
通讯作者:
于洪涛
作者简介:
金柯君(1993—),男,浙江诸暨人,硕士研究生,主要研究方向:人工智能安全基金资助:
CLC Number:
Kejun JIN, Hongtao YU, Yiteng WU, Shaomei LI, Jianpeng ZHANG, Honghao ZHENG. Improved defense method for graph convolutional network based on singular value decomposition[J]. Journal of Computer Applications, 2023, 43(5): 1511-1517.
金柯君, 于洪涛, 吴翼腾, 李邵梅, 张建朋, 郑洪浩. 改进的基于奇异值分解的图卷积网络防御方法[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1511-1517.
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/10.11772/j.issn.1001-9081.2022040553
攻击类型 | 模型/防御方法 | 发表年份 | 应用场景 | 求解方法 |
---|---|---|---|---|
图对抗性攻击 | Nettack[ | 2018 | 投毒/逃逸 | 逐元素遍历筛选扰动 |
FGA/GradArgmax[ | 2018 | 逃逸 | 以梯度为指导进行扰动筛选 | |
Metattack[ | 2019 | 投毒 | 以元梯度为指导进行扰动筛选 | |
GF-Attack[ | 2020 | 逃逸 | 基于特征值的扰动理论求得的闭式解指导扰动筛选 | |
ReWatt[ | 2021 | 逃逸 | 采用策略梯度优化学习策略以取得最大化奖励值 | |
图对抗性防御 | GAT/GATV[ | 2019 | 逃逸 | 基于图动态正则化进行对抗训练 |
SVD[ | 2020 | 投毒/逃逸 | 利用奇异值分解和低秩近似进行预处理 | |
RGCN[ | 2019 | 投毒 | 使用高斯分布表示GCN 中隐藏层输出 | |
Pro-GNN[ | 2020 | 投毒 | 通过约束,迭代地重构干净图并优化GNN 参数 |
Tab. 1 Common graph adversarial attacks and defense methods
攻击类型 | 模型/防御方法 | 发表年份 | 应用场景 | 求解方法 |
---|---|---|---|---|
图对抗性攻击 | Nettack[ | 2018 | 投毒/逃逸 | 逐元素遍历筛选扰动 |
FGA/GradArgmax[ | 2018 | 逃逸 | 以梯度为指导进行扰动筛选 | |
Metattack[ | 2019 | 投毒 | 以元梯度为指导进行扰动筛选 | |
GF-Attack[ | 2020 | 逃逸 | 基于特征值的扰动理论求得的闭式解指导扰动筛选 | |
ReWatt[ | 2021 | 逃逸 | 采用策略梯度优化学习策略以取得最大化奖励值 | |
图对抗性防御 | GAT/GATV[ | 2019 | 逃逸 | 基于图动态正则化进行对抗训练 |
SVD[ | 2020 | 投毒/逃逸 | 利用奇异值分解和低秩近似进行预处理 | |
RGCN[ | 2019 | 投毒 | 使用高斯分布表示GCN 中隐藏层输出 | |
Pro-GNN[ | 2020 | 投毒 | 通过约束,迭代地重构干净图并优化GNN 参数 |
数据集 | 节点数 | 连边数 | 标签类别 | 特征数 |
---|---|---|---|---|
Citeseer | 2 110 | 3 668 | 6 | 3 703 |
Cora | 2 485 | 5 069 | 7 | 1 433 |
Pubmed | 19 717 | 44 338 | 3 | 500 |
Tab. 2 Statistical characteristics of datasets
数据集 | 节点数 | 连边数 | 标签类别 | 特征数 |
---|---|---|---|---|
Citeseer | 2 110 | 3 668 | 6 | 3 703 |
Cora | 2 485 | 5 069 | 7 | 1 433 |
Pubmed | 19 717 | 44 338 | 3 | 500 |
扰动比例 | GCN | ISVD_0 | ISVDatt |
---|---|---|---|
0.00 | 0.832 | 0.635 | 0.806 |
0.05 | 0.765 | 0.648 | 0.785 |
0.10 | 0.704 | 0.639 | 0.769 |
0.15 | 0.651 | 0.628 | 0.737 |
0.20 | 0.597 | 0.613 | 0.675 |
0.25 | 0.475 | 0.546 | 0.571 |
Tab. 3 Classification accuracy of different models under different settings on Cora dataset
扰动比例 | GCN | ISVD_0 | ISVDatt |
---|---|---|---|
0.00 | 0.832 | 0.635 | 0.806 |
0.05 | 0.765 | 0.648 | 0.785 |
0.10 | 0.704 | 0.639 | 0.769 |
0.15 | 0.651 | 0.628 | 0.737 |
0.20 | 0.597 | 0.613 | 0.675 |
0.25 | 0.475 | 0.546 | 0.571 |
实验对象 | τ | k=5 | k=10 | k=15 | k=20 | k=25 |
---|---|---|---|---|---|---|
扰动图 | 0.00 | 0.782 | 0.783 | 0.763 | 0.712 | 0.683 |
0.05 | 0.763 | 0.806 | 0.793 | 0.786 | 0.776 | |
0.10 | 0.707 | 0.753 | 0.701 | 0.697 | 0.672 | |
0.15 | 0.718 | 0.707 | 0.692 | 0.679 | 0.668 | |
0.20 | 0.667 | 0.680 | 0.707 | 0.673 | 0.657 | |
0.25 | 0.648 | 0.653 | 0.659 | 0.623 | 0.607 | |
原始图 | 0.00 | 0.689 | 0.749 | 0.732 | 0.707 | 0.673 |
0.05 | 0.707 | 0.769 | 0.743 | 0.729 | 0.707 | |
0.10 | 0.683 | 0.701 | 0.692 | 0.661 | 0.687 | |
0.15 | 0.668 | 0.670 | 0.651 | 0.638 | 0.627 | |
0.20 | 0.643 | 0.650 | 0.672 | 0.630 | 0.627 | |
0.25 | 0.612 | 0.600 | 0.591 | 0.572 | 0.553 |
Tab. 4 Classification accuracy under different parameter settings(Metattack, disturbance rate is 10%)
实验对象 | τ | k=5 | k=10 | k=15 | k=20 | k=25 |
---|---|---|---|---|---|---|
扰动图 | 0.00 | 0.782 | 0.783 | 0.763 | 0.712 | 0.683 |
0.05 | 0.763 | 0.806 | 0.793 | 0.786 | 0.776 | |
0.10 | 0.707 | 0.753 | 0.701 | 0.697 | 0.672 | |
0.15 | 0.718 | 0.707 | 0.692 | 0.679 | 0.668 | |
0.20 | 0.667 | 0.680 | 0.707 | 0.673 | 0.657 | |
0.25 | 0.648 | 0.653 | 0.659 | 0.623 | 0.607 | |
原始图 | 0.00 | 0.689 | 0.749 | 0.732 | 0.707 | 0.673 |
0.05 | 0.707 | 0.769 | 0.743 | 0.729 | 0.707 | |
0.10 | 0.683 | 0.701 | 0.692 | 0.661 | 0.687 | |
0.15 | 0.668 | 0.670 | 0.651 | 0.638 | 0.627 | |
0.20 | 0.643 | 0.650 | 0.672 | 0.630 | 0.627 | |
0.25 | 0.612 | 0.600 | 0.591 | 0.572 | 0.553 |
数据集 | 原始图 | Pro_GNN | RGCN | SVD | ISVDatt |
---|---|---|---|---|---|
Cora | 0.843 | 0.828 | 0.829 | 0.814 | 0.806 |
Citeseer | 0.721 | 0.726 | 0.725 | 0.714 | 0.707 |
Pubmed | 0.860 | 0.865 | 0.857 | 0.839 | 0.832 |
Tab. 5 Classification accuracy of different defense methods on original graph
数据集 | 原始图 | Pro_GNN | RGCN | SVD | ISVDatt |
---|---|---|---|---|---|
Cora | 0.843 | 0.828 | 0.829 | 0.814 | 0.806 |
Citeseer | 0.721 | 0.726 | 0.725 | 0.714 | 0.707 |
Pubmed | 0.860 | 0.865 | 0.857 | 0.839 | 0.832 |
数据集 | 扰动比例 | Metattack攻击 | DICE攻击 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
GCN | Pro_GNN | RGCN | SVD | ISVD | GCN | Pro_GNN | RGCN | SVD | ISVD | ||
Cora | 0.00 | 0.832 | 0.828 | 0.828 | 0.814 | 0.806 | 0.843 | 0.828 | 0.828 | 0.814 | 0.806 |
0.05 | 0.765 | 0.823 | 0.774 | 0.784 | 0.785 | 0.819 | 0.820 | 0.828 | 0.678 | 0.776 | |
0.10 | 0.704 | 0.790 | 0.774 | 0.715 | 0.769 | 0.795 | 0.786 | 0.777 | 0.687 | 0.806 | |
0.15 | 0.651 | 0.765 | 0.722 | 0.667 | 0.737 | 0.790 | 0.795 | 0.769 | 0.693 | 0.783 | |
0.20 | 0.597 | 0.733 | 0.668 | 0.589 | 0.675 | 0.766 | 0.787 | 0.768 | 0.704 | 0.791 | |
0.25 | 0.475 | 0.697 | 0.554 | 0.521 | 0.571 | 0.742 | 0.776 | 0.750 | 0.714 | 0.788 | |
Citeseer | 0.00 | 0.720 | 0.726 | 0.725 | 0.714 | 0.707 | 0.739 | 0.726 | 0.725 | 0.714 | 0.707 |
0.05 | 0.709 | 0.731 | 0.705 | 0.688 | 0.693 | 0.732 | 0.734 | 0.737 | 0.734 | 0.689 | |
0.10 | 0.676 | 0.724 | 0.677 | 0.689 | 0.691 | 0.725 | 0.713 | 0. 725 | 0.712 | 0.709 | |
0.15 | 0.656 | 0.708 | 0.657 | 0.633 | 0.663 | 0.717 | 0.693 | 0.713 | 0.692 | 0.713 | |
0.20 | 0.620 | 0.662 | 0.625 | 0.586 | 0.639 | 0.698 | 0.703 | 0.698 | 0.687 | 0.717 | |
0.25 | 0.569 | 0.664 | 0.554 | 0.572 | 0.603 | 0.661 | 0.696 | 0.664 | 0.668 | 0.698 | |
Pubmed | 0.00 | 0.872 | 0.865 | 0.857 | 0.839 | 0.828 | 0.871 | 0.865 | 0.857 | 0.839 | 0.832 |
0.05 | 0.831 | 0.873 | 0.711 | 0.834 | 0.822 | 0.852 | 0.857 | 0.857 | 0.814 | 0.839 | |
0.10 | 0.812 | 0.873 | 0.775 | 0.833 | 0.820 | 0.837 | 0.846 | 0.829 | 0.793 | 0.828 | |
0.15 | 0.787 | 0.872 | 0.739 | 0.831 | 0.827 | 0.829 | 0.843 | 0.824 | 0.787 | 0.826 | |
0.20 | 0.774 | 0.871 | 0.712 | 0.830 | 0.831 | 0.824 | 0.842 | 0.815 | 0.794 | 0.820 | |
0.25 | 0.755 | 0.867 | 0.680 | 0.827 | 0.827 | 0.814 | 0.841 | 0.809 | 0.802 | 0.809 |
Tab. 6 Classification accuracies under Metattack and DICE attacks
数据集 | 扰动比例 | Metattack攻击 | DICE攻击 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|
GCN | Pro_GNN | RGCN | SVD | ISVD | GCN | Pro_GNN | RGCN | SVD | ISVD | ||
Cora | 0.00 | 0.832 | 0.828 | 0.828 | 0.814 | 0.806 | 0.843 | 0.828 | 0.828 | 0.814 | 0.806 |
0.05 | 0.765 | 0.823 | 0.774 | 0.784 | 0.785 | 0.819 | 0.820 | 0.828 | 0.678 | 0.776 | |
0.10 | 0.704 | 0.790 | 0.774 | 0.715 | 0.769 | 0.795 | 0.786 | 0.777 | 0.687 | 0.806 | |
0.15 | 0.651 | 0.765 | 0.722 | 0.667 | 0.737 | 0.790 | 0.795 | 0.769 | 0.693 | 0.783 | |
0.20 | 0.597 | 0.733 | 0.668 | 0.589 | 0.675 | 0.766 | 0.787 | 0.768 | 0.704 | 0.791 | |
0.25 | 0.475 | 0.697 | 0.554 | 0.521 | 0.571 | 0.742 | 0.776 | 0.750 | 0.714 | 0.788 | |
Citeseer | 0.00 | 0.720 | 0.726 | 0.725 | 0.714 | 0.707 | 0.739 | 0.726 | 0.725 | 0.714 | 0.707 |
0.05 | 0.709 | 0.731 | 0.705 | 0.688 | 0.693 | 0.732 | 0.734 | 0.737 | 0.734 | 0.689 | |
0.10 | 0.676 | 0.724 | 0.677 | 0.689 | 0.691 | 0.725 | 0.713 | 0. 725 | 0.712 | 0.709 | |
0.15 | 0.656 | 0.708 | 0.657 | 0.633 | 0.663 | 0.717 | 0.693 | 0.713 | 0.692 | 0.713 | |
0.20 | 0.620 | 0.662 | 0.625 | 0.586 | 0.639 | 0.698 | 0.703 | 0.698 | 0.687 | 0.717 | |
0.25 | 0.569 | 0.664 | 0.554 | 0.572 | 0.603 | 0.661 | 0.696 | 0.664 | 0.668 | 0.698 | |
Pubmed | 0.00 | 0.872 | 0.865 | 0.857 | 0.839 | 0.828 | 0.871 | 0.865 | 0.857 | 0.839 | 0.832 |
0.05 | 0.831 | 0.873 | 0.711 | 0.834 | 0.822 | 0.852 | 0.857 | 0.857 | 0.814 | 0.839 | |
0.10 | 0.812 | 0.873 | 0.775 | 0.833 | 0.820 | 0.837 | 0.846 | 0.829 | 0.793 | 0.828 | |
0.15 | 0.787 | 0.872 | 0.739 | 0.831 | 0.827 | 0.829 | 0.843 | 0.824 | 0.787 | 0.826 | |
0.20 | 0.774 | 0.871 | 0.712 | 0.830 | 0.831 | 0.824 | 0.842 | 0.815 | 0.794 | 0.820 | |
0.25 | 0.755 | 0.867 | 0.680 | 0.827 | 0.827 | 0.814 | 0.841 | 0.809 | 0.802 | 0.809 |
1 | 陈晋音,黄国瀚,张敦杰,等. 一种面向图神经网络的图重构防御方法[J]. 计算机研究与发展, 2021, 58(5): 1075-1091. 10.7544/issn1000-1239.2021.20200935 |
CHEN J Y, HUANG G H, ZHANG D J, et al. GRD-GNN: graph reconstruction defense for graph neural network[J]. Journal of Computer Research and Development, 2021, 58(5): 1075-1091. 10.7544/issn1000-1239.2021.20200935 | |
2 | TANG J, QU M, MEI Q Z. PTE: predictive text embedding through large-scale heterogeneous text networks[C]// Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2015: 1165-1174. 10.1145/2783258.2783307 |
3 | WANG S H, TANG J L, AGGARWAL C, et al. Signed network embedding in social media[C]// Proceedings of the 2017 SIAM International Conference on Data Mining. Pennsylvania, PA: Society for Industrial and Applied Mathematics, 2017: 327-335. 10.1137/1.9781611974973.37 |
4 | XUAN Q, WANG J H, ZHAO M H, et al. Subgraph networks with application to structural feature space expansion[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 33(6): 2776-2789. 10.1109/tkde.2019.2957755 |
5 | 赵霞,张泽华,张晨威,等. RGNE:粗糙粒化的网络嵌入式重叠社区发现方法[J]. 计算机研究与发展, 2020, 57(6):1302-1311. 10.7544/issn1000-1239.2020.20190572 |
ZHAO X, ZHANG Z H, ZHANG C W, et al. RGNE: a network embedding method for overlapping community detection based on rough granulation[J]. Journal of Computer Research and Development, 2020, 57(6):1302-1311. 10.7544/issn1000-1239.2020.20190572 | |
6 | ZÜGNER D, AKBARNEJAD A, GÜNNEMANN S. Adversarial attacks on neural networks for graph data[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2018: 2847-2856. 10.1145/3219819.3220078 |
7 | 翟正利,李鹏辉,冯舒. 图对抗攻击研究综述[J]. 计算机工程与应用, 2021, 57(7):14-21. 10.3778/j.issn.1002-8331.2012-0367 |
ZHAI Z L, LI P H, FENG S. Research overview of adversarial attacks on graphs[J]. Computer Engineering and Applications, 2021, 57(7):14-21. 10.3778/j.issn.1002-8331.2012-0367 | |
8 | JIN W, LI Y X, XU H, et al. Adversarial attacks and defenses on graphs: a review and empirical study[J] ACM SIGKDD Explorations Newsletter, 2020, 22(2):19-34. 10.1145/3447556.3447566 |
9 | CHEN L, LI J T, PENG J Y, et al. A survey of adversarial learning on graphs[EB/OL]. [2022-01-15].. |
10 | ZHOU K, ZHA H Y, SONG L. Learning social infectivity in sparse low-rank networks using multi-dimensional Hawkes processes[C]// Proceedings of the 16th International Conference on Artificial Intelligence and Statistics. New York: JMLR.org, 2013: 641-649. |
11 | FORTUNATO S. Community detection in graphs[J]. Physics Reports, 2010, 486(3/4/5): 75-174. 10.1016/j.physrep.2009.11.002 |
12 | McPHERSON M, SMITH-LOVIN L, COOK J M. Birds of a feather: homophily in social networks[J]. Annual Review of Sociology, 2001, 27:415-444. 10.1146/annurev.soc.27.1.415 |
13 | KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2022-02-04].. 10.48550/arXiv.1609.02907 |
14 | ENTEZARI N, AL-SAYOURI S A, DARVISHZADEH A, et al. All you need is low (rank): defending against adversarial attacks on graphs[C]// Proceedings of the 13th ACM International Conference on Web Search and Data Mining. New York: ACM, 2020: 169-177. 10.1145/3336191.3371789 |
15 | WANG S H, TANG J L, AGGARWAL C, et al. Linked document embedding for classification[C]// Proceedings of the 25th ACM International Conference on Information and Knowledge Management. New York: ACM, 2016: 115-124. 10.1145/2983323.2983755 |
16 | DAI H J, LI H, TIAN T, et al. Adversarial attack on graph structured data[C]// Proceedings of the 35th International Conference on Machine Learning. New York: JMLR.org, 2018: 1115-1124. |
17 | CHEN J, WU Y, XU X, et al. Fast gradient attack on network embedding[EB/OL]. [2022-03-24].. |
18 | ZÜGNER D, GÜNNEMANN S. Adversarial attacks on graph neural networks via meta learning[EB/OL]. [2022-01-12].. 10.24963/ijcai.2019/872 |
19 | CHANG H, RONG Y, XU T Y, et al. A restricted black-box adversarial framework towards attacking graph embedding models[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2020: 3389-3396. 10.1609/aaai.v34i04.5741 |
20 | MA Y, WANG S H, DERR T, et al. Graph adversarial attack via rewiring[C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2021: 1161-1169. 10.1145/3447548.3467416 |
21 | 李鹏辉,翟正利,冯舒. 图对抗防御研究进展[J]. 计算机科学与探索, 2021, 15(12):2292-2303. |
LI P H, ZHAI Z L, FENG S. Research progress of adversarial defenses on graphs[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(12):2292-2303. | |
22 | FENG F L, HE X N, TANG J, et al. Graph adversarial training: dynamically regularizing based on graph structure[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 33(6):2493-2504. 10.1109/tkde.2019.2957786 |
23 | ZHU D Y, ZHANG Z W, CUI P, et al. Robust graph convolutional networks against adversarial attacks[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019: 1399-1407. 10.1145/3292500.3330851 |
24 | JIN W, MA Y, LIU X R, et al. Graph structure learning for robust graph neural networks[C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020: 66-74. 10.1145/3394486.3403049 |
25 | WU H J, WANG C, TYSHETSKIY Y, et al. Adversarial examples on graph data: deep insights into attack and defense[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. California: ijcai.org, 2019: 4816-4823. 10.24963/ijcai.2019/669 |
26 | TAN P N, STEINBACK M, KUMAR V. 数据挖掘导论(完整版)[M]. 范明,范宏建,译. 北京:人民邮电出版社, 2011:263-266. |
TAN P N, STEINBACK M, KUMAR V. Introduction to Data Mining[M]. FAN M, FAN H J, translated. Beijing: Posts & Telecom Press, 2011:263-266. | |
27 | 赵楠,皮文超,许长桥. 一种面向多维特征分析过滤的视频推荐算法[J]. 计算机科学, 2020, 47(4): 103-107. 10.11896/jsjkx.190700177 |
ZHAO N, PI W C, XU C Q. Video recommendation algorithm for multidimensional feature analysis and filtering[J]. Computer Science, 2020, 47(4): 103-107. 10.11896/jsjkx.190700177 | |
28 | McCALLUM A K, NIGAM K, RENNIE J. Automating the construction of internet portals with machine learning[J]. Information Retrieval, 2000, 3(2):127-163. 10.1023/a:1009953814988 |
29 | GILES C L, BOLLACKER K D, LAWRENCE S. CiteSeer: an automatic citation indexing system[C]// Proceedings of the 3rd ACM Conference on Digital Libraries. New York: ACM, 1998: 89-98. 10.1145/276675.276685 |
30 | SEN P, NAMATA G, BILGIC M, et al. Collective classification in network data[J]. AI Magazine, 2008, 29(3): 93-106. 10.1609/aimag.v29i3.2157 |
31 | WANIEK M, MICHALAK T P, WOOLDRIDGE M J, et al. Hiding individuals and communities in a social network[J]. Nature Human Behaviour, 2018, 2: 139-147. 10.1038/s41562-017-0290-3 |
[1] | Cheng FANG, Bei LI, Ping HAN, Qiong WU. Fine-grained emotion classification of Chinese microblog based on syntactic dependency graph [J]. Journal of Computer Applications, 2023, 43(4): 1056-1061. |
[2] | Hao SUN, Jian CAO, Haisheng LI, Dianhui MAO. Session-based recommendation model based on enhanced capsule network [J]. Journal of Computer Applications, 2023, 43(4): 1043-1049. |
[3] | Yingmao YAO, Xiaoyan JIANG. Video-based person re-identification method based on graph convolution network and self-attention graph pooling [J]. Journal of Computer Applications, 2023, 43(3): 728-735. |
[4] | Zhenliang LI, Bo LI. Improved method of convolution neural network based on matrix decomposition [J]. Journal of Computer Applications, 2023, 43(3): 685-691. |
[5] | Lubao LI, Tian CHEN, Fuji REN, Beibei LUO. Bimodal emotion recognition method based on graph neural network and attention [J]. Journal of Computer Applications, 2023, 43(3): 700-705. |
[6] | Tao PENG, Yalong KANG, Feng YU, Zili ZHANG, Junping LIU, Xinrong HU, Ruhan HE, Li LI. Pedestrian trajectory prediction based on multi-head soft attention graph convolutional network [J]. Journal of Computer Applications, 2023, 43(3): 736-743. |
[7] | Yu WANG, Yubo YUAN, Yi GUO, Jiajie ZHANG. Sentiment boosting model for emotion recognition in conversation text [J]. Journal of Computer Applications, 2023, 43(3): 706-712. |
[8] | Ruoying WANG, Fan LYU, Liuqing ZHAO, Fuyuan HU. Floorplan generation algorithm integrating user requirements and boundary constraints [J]. Journal of Computer Applications, 2023, 43(2): 575-582. |
[9] | Yating SU, Cuixiang LIU. Three-dimensional human reconstruction model based on high-resolution net and graph convolutional network [J]. Journal of Computer Applications, 2023, 43(2): 583-588. |
[10] | Jie LIANG, Xiaoyan HAO, Yongle CHEN. Poisoning attack toward visual classification model [J]. Journal of Computer Applications, 2023, 43(2): 467-473. |
[11] | Jun ZHANG, Pengli WU, Lukui SHI, Jin SHI, Bin PAN. Deep learning model for multi-station temperature prediction combined with MOD11A1 and surface meteorological station data [J]. Journal of Computer Applications, 2023, 43(1): 321-328. |
[12] | Lining YUAN, Zhao LIU. Graph representation learning by autoencoder with one-shot aggregation [J]. Journal of Computer Applications, 2023, 43(1): 8-14. |
[13] | Jiaxuan WEI, Shikang DU, Zhixuan YU, Ruisheng ZHANG. Review of white-box adversarial attack technologies in image classification [J]. Journal of Computer Applications, 2022, 42(9): 2732-2741. |
[14] | Bo LIU, Linbo QING, Zhengyong WANG, Mei LIU, Xue JIANG. Group activity recognition based on partitioned attention mechanism and interactive position relationship [J]. Journal of Computer Applications, 2022, 42(7): 2052-2057. |
[15] | Jiafan ZHOU, Yuefeng DU, Baoyan SONG, Xiaoguang LI, Azhu ZHAO, Xujie XIAO. MOOC video recommendation method based on meta-path attention mechanism [J]. Journal of Computer Applications, 2022, 42(6): 1808-1813. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||