Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (9): 2726-2731.DOI: 10.11772/j.issn.1001-9081.2023091325
• Data science and technology • Previous Articles Next Articles
Received:
2023-09-27
Revised:
2023-12-11
Accepted:
2023-12-12
Online:
2023-12-22
Published:
2024-09-10
Contact:
Yan ZHU
About author:
DU Yu, born in 1999, M. S. candidate. Her research interests include network analysis, academic network cooperative behavior disappearance prediction.
Supported by:
通讯作者:
朱焱
作者简介:
杜郁(1999—),女,四川雅安人,硕士研究生,主要研究方向:网络分析、学术网络合作行为消失预测基金资助:
CLC Number:
Yu DU, Yan ZHU. Constructing pre-trained dynamic graph neural network to predict disappearance of academic cooperation behavior[J]. Journal of Computer Applications, 2024, 44(9): 2726-2731.
杜郁, 朱焱. 构建预训练动态图神经网络预测学术合作行为消失[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2726-2731.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023091325
子数据集 | 作者数 | 合作关系数 |
---|---|---|
1996 | 1 495 | 35 233 |
1997 | 2 238 | 79 027 |
94—96 | 2 293 | 50 943 |
97—99 | 5 713 | 239 541 |
Tab. 1 Specific information of four subdatasets
子数据集 | 作者数 | 合作关系数 |
---|---|---|
1996 | 1 495 | 35 233 |
1997 | 2 238 | 79 027 |
94—96 | 2 293 | 50 943 |
97—99 | 5 713 | 239 541 |
模型 | HepTh(1996) | HepTh(1997) | ||
---|---|---|---|---|
AUC | AP | AUC | AP | |
DeepWalk | 56.40 | 76.69 | 53.30 | 86.70 |
CTDNE | 56.95 | 72.30 | 53.76 | 86.35 |
HTNE | 56.99 | 76.79 | 55.85 | 85.87 |
MMDNE | 55.71 | 75.99 | 55.21 | 85.94 |
MTNE | 54.00 | 75.98 | 56.37 | 87.98 |
Jodie | 62.89 | 78.81 | 61.72 | 89.99 |
DyRep | 65.02 | 80.89 | 59.38 | 89.78 |
PreDGN | 75.49 | 86.76 | 67.54 | 91.93 |
Tab. 2 Experimental results on 1-year interval datasets
模型 | HepTh(1996) | HepTh(1997) | ||
---|---|---|---|---|
AUC | AP | AUC | AP | |
DeepWalk | 56.40 | 76.69 | 53.30 | 86.70 |
CTDNE | 56.95 | 72.30 | 53.76 | 86.35 |
HTNE | 56.99 | 76.79 | 55.85 | 85.87 |
MMDNE | 55.71 | 75.99 | 55.21 | 85.94 |
MTNE | 54.00 | 75.98 | 56.37 | 87.98 |
Jodie | 62.89 | 78.81 | 61.72 | 89.99 |
DyRep | 65.02 | 80.89 | 59.38 | 89.78 |
PreDGN | 75.49 | 86.76 | 67.54 | 91.93 |
模型 | HepTh(94—96) | HepTh(97—99) | ||
---|---|---|---|---|
AUC | AP | AUC | AP | |
DeepWalk | 55.25 | 74.16 | 56.46 | 80.74 |
CTDNE | 55.08 | 72.03 | 56.42 | 78.67 |
HTNE | 59.02 | 75.76 | 58.40 | 81.19 |
MMDNE | 53.00 | 69.59 | 56.20 | 80.21 |
MTNE | 54.52 | 71.69 | 57.58 | 80.69 |
Jodie | 60.68 | 77.59 | 64.96 | 84.78 |
DyRep | 65.32 | 79.04 | 71.02 | 86.11 |
PreDGN | 78.73 | 87.30 | 74.29 | 89.12 |
Tab. 3 Experimental results on 3-year interval datasets
模型 | HepTh(94—96) | HepTh(97—99) | ||
---|---|---|---|---|
AUC | AP | AUC | AP | |
DeepWalk | 55.25 | 74.16 | 56.46 | 80.74 |
CTDNE | 55.08 | 72.03 | 56.42 | 78.67 |
HTNE | 59.02 | 75.76 | 58.40 | 81.19 |
MMDNE | 53.00 | 69.59 | 56.20 | 80.21 |
MTNE | 54.52 | 71.69 | 57.58 | 80.69 |
Jodie | 60.68 | 77.59 | 64.96 | 84.78 |
DyRep | 65.32 | 79.04 | 71.02 | 86.11 |
PreDGN | 78.73 | 87.30 | 74.29 | 89.12 |
模型 | HepTh(1996) | HepTh(1997) | HepTh (94—96) | HepTh (97—99) |
---|---|---|---|---|
Jodie | 62.89 | 61.72 | 60.68 | 64.96 |
Jodie-np | 69.36 | 61.21 | 73.02 | 66.15 |
DyRep | 65.02 | 59.38 | 65.32 | 71.02 |
DyRep-np | 68.35 | 67.43 | 71.24 | 74.88 |
PreDGN-np | 72.94 | 53.06 | 77.97 | 70.54 |
PreDGN | 75.49 | 67.54 | 78.73 | 74.29 |
Tab. 4 AUCs of different encoder models
模型 | HepTh(1996) | HepTh(1997) | HepTh (94—96) | HepTh (97—99) |
---|---|---|---|---|
Jodie | 62.89 | 61.72 | 60.68 | 64.96 |
Jodie-np | 69.36 | 61.21 | 73.02 | 66.15 |
DyRep | 65.02 | 59.38 | 65.32 | 71.02 |
DyRep-np | 68.35 | 67.43 | 71.24 | 74.88 |
PreDGN-np | 72.94 | 53.06 | 77.97 | 70.54 |
PreDGN | 75.49 | 67.54 | 78.73 | 74.29 |
子数据集 | 模型 | AUC | AP |
---|---|---|---|
1996 | PreDGN-nm | 73.71 | 85.83 |
PreDGN | 75.49 | 86.76 | |
1997 | PreDGN-nm | 62.05 | 90.13 |
PreDGN | 67.54 | 91.93 | |
94—96 | PreDGN-nm | 75.12 | 84.78 |
PreDGN | 78.73 | 87.30 | |
97—99 | PreDGN-nm | 72.91 | 87.51 |
PreDGN | 74.29 | 89.12 |
Tab. 5 Experimental results of motif feature ablation
子数据集 | 模型 | AUC | AP |
---|---|---|---|
1996 | PreDGN-nm | 73.71 | 85.83 |
PreDGN | 75.49 | 86.76 | |
1997 | PreDGN-nm | 62.05 | 90.13 |
PreDGN | 67.54 | 91.93 | |
94—96 | PreDGN-nm | 75.12 | 84.78 |
PreDGN | 78.73 | 87.30 | |
97—99 | PreDGN-nm | 72.91 | 87.51 |
PreDGN | 74.29 | 89.12 |
预训练数据 占比 | HepTh(1996) | HepTh(1997) | HepTh (94—96) | HepTh (97—99) |
---|---|---|---|---|
20 | 73.00 | 64.18 | 75.58 | 69.23 |
30 | 73.37 | 64.32 | 76.16 | 69.35 |
40 | 73.57 | 65.55 | 76.47 | 69.98 |
50 | 73.93 | 64.58 | 76.24 | 71.18 |
60 | 75.16 | 64.45 | 77.23 | 72.04 |
70 | 75.23 | 66.60 | 77.51 | 72.97 |
Tab. 6 AUCs of different pre-trained data sizes
预训练数据 占比 | HepTh(1996) | HepTh(1997) | HepTh (94—96) | HepTh (97—99) |
---|---|---|---|---|
20 | 73.00 | 64.18 | 75.58 | 69.23 |
30 | 73.37 | 64.32 | 76.16 | 69.35 |
40 | 73.57 | 65.55 | 76.47 | 69.98 |
50 | 73.93 | 64.58 | 76.24 | 71.18 |
60 | 75.16 | 64.45 | 77.23 | 72.04 |
70 | 75.23 | 66.60 | 77.51 | 72.97 |
层数 | HepTh(1996) | HepTh(94—96) | ||
---|---|---|---|---|
AUC/% | 训练时间/s | AUC/% | 训练时间/s | |
0 | 55.90 | 142 | 58.81 | 268 |
1 | 75.49 | 235 | 78.73 | 374 |
2 | 75.37 | 420 | 79.36 | 807 |
3 | 75.46 | 2 281 | 79.34 | 2 946 |
4 | 75.42 | 5 628 | 79.38 | 7 492 |
5 | 75.39 | 15 312 | 78.99 | 18 904 |
Tab. 7 Experimental results of different attention layers
层数 | HepTh(1996) | HepTh(94—96) | ||
---|---|---|---|---|
AUC/% | 训练时间/s | AUC/% | 训练时间/s | |
0 | 55.90 | 142 | 58.81 | 268 |
1 | 75.49 | 235 | 78.73 | 374 |
2 | 75.37 | 420 | 79.36 | 807 |
3 | 75.46 | 2 281 | 79.34 | 2 946 |
4 | 75.42 | 5 628 | 79.38 | 7 492 |
5 | 75.39 | 15 312 | 78.99 | 18 904 |
1 | XU B, LI L, LIU J, et al. Disappearing link prediction in scientific collaboration networks [J]. IEEE Access, 2018, 6:69702-69712. |
2 | LI L, WANG W, YU S, et al. A modified node2vec method for disappearing link prediction [C]// Proceedings of the IEEE 15th International Conference on Dependable, Autonomic and Secure Computing, 15th International Conference on Pervasive Intelligence and Computing, 3rd International Conference on Big Data Intelligence and Computing and Cyber Science and Technology Congress. Piscataway: IEEE, 2017: 1232-1235. |
3 | MURO C, LI B, HE K. Link prediction and unlink prediction on dynamic networks [J]. IEEE Transactions on Computational Social Systems, 2023, 10(2):590-601. |
4 | TRIVEDI R, FARAJTABAR M, BISWAL P, et al. DyRep: learning representations over dynamic graphs[EB/OL]. [2022-10-03]. . |
5 | KUMAR S, ZHANG X, LESKOVEC J. Predicting dynamic embedding trajectory in temporal interaction networks [C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019 :1269-1278. |
6 | KAZEMI S M, GOEL R, JAIN K, et al. Representation learning for dynamic graphs: a survey [J]. Journal of Machine Learning Research, 2020, 21:1-73. |
7 | QIU J, CHEN Q, DONG Y, et al. GCC: graph contrastive coding for graph neural network pre-training [C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020: 1150-1160. |
8 | HU Z, DONG Y, WANG K, et al. GPT-GNN: generative pre-training of graph neural networks [C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020:1857-1867. |
9 | HAO B, ZHANG J, YIN H, et al. Pre-training graph neural networks for cold-start users and items representation [C]// Proceedings of the 14th ACM International Conference on Web Search and Data Mining. New York: ACM, 2021: 265-273. |
10 | HUANG H, FANG Z, WANG X, et al. Motif-preserving temporal network embedding [C]// Proceedings of the 29th International Joint Conferences on Artificial Intelligence. California: IJCAI.org, 2020:1237-1243. |
11 | LIU Z, HUANG C, YU Y, et al. Motif-preserving dynamic attributed network embedding [C]// Proceedings of the Web Conference 2021. Republic and Canton of Geneva: International World Wide Web Conferences Steering Committee, 2021:1629-1638. |
12 | BOURITSAS G, FRASCA F, ZAFEIRIOU S, et al. Improving graph neural network expressivity via subgraph isomorphism counting [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(1): 657-668. |
13 | XU D, RUAN C, KUMAR S, et al. Self-attention with functional time representation learning [C]// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2019: 15915-15925. |
14 | 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. |
15 | NGUYEN G H, LEE J B, ROSSI R A, et al. Continuous-time dynamic network embeddings [C]// Companion of the Web Conference 2018. Republic and Canton of Geneva: International World Wide Web Conferences Steering Committee, 2018: 969-976. |
16 | ZOU Y, LIU G, LIN H, et al. Embedding temporal network via neighborhood formation [C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2018:2857-2866. |
17 | LU Y, WANG X, SHI C, et al. Temporal network embedding with micro-and macro-dynamics [C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York: ACM, 2019:469-478. |
[1] | Tingjie TANG, Jiajin HUANG, Jin QIN. Session-based recommendation with graph auxiliary learning [J]. Journal of Computer Applications, 2024, 44(9): 2711-2718. |
[2] | Xingyao YANG, Yu CHEN, Jiong YU, Zulian ZHANG, Jiaying CHEN, Dongxiao WANG. Recommendation model combining self-features and contrastive learning [J]. Journal of Computer Applications, 2024, 44(9): 2704-2710. |
[3] | Hang YANG, Wanggen LI, Gensheng ZHANG, Zhige WANG, Xin KAI. Multi-layer information interactive fusion algorithm based on graph neural network for session-based recommendation [J]. Journal of Computer Applications, 2024, 44(9): 2719-2725. |
[4] | Kaipeng XUE, Tao XU, Chunjie LIAO. Multimodal sentiment analysis network with self-supervision and multi-layer cross attention [J]. Journal of Computer Applications, 2024, 44(8): 2387-2392. |
[5] | Fan YANG, Yao ZOU, Mingzhi ZHU, Zhenwei MA, Dawei CHENG, Changjun JIANG. Credit card fraud detection model based on graph attention Transformation neural network [J]. Journal of Computer Applications, 2024, 44(8): 2634-2642. |
[6] | Yue LIU, Fang LIU, Aoyun WU, Qiuyue CHAI, Tianxiao WANG. 3D object detection network based on self-attention mechanism and graph convolution [J]. Journal of Computer Applications, 2024, 44(6): 1972-1977. |
[7] | Xinrui LIN, Xiaofei WANG, Yan ZHU. Academic anomaly citation group detection based on local extended community detection [J]. Journal of Computer Applications, 2024, 44(6): 1855-1861. |
[8] | Shibin LI, Jun GONG, Shengjun TANG. Semi-supervised heterophilic graph representation learning model based on Graph Transformer [J]. Journal of Computer Applications, 2024, 44(6): 1816-1823. |
[9] | Jiong WANG, Taotao TANG, Caiyan JIA. PAGCL: positive augmentation graph contrastive learning recommendation method without negative sampling [J]. Journal of Computer Applications, 2024, 44(5): 1485-1492. |
[10] | Jie GUO, Jiayu LIN, Zuhong LIANG, Xiaobo LUO, Haitao SUN. Recommendation method based on knowledge‑awareness and cross-level contrastive learning [J]. Journal of Computer Applications, 2024, 44(4): 1121-1127. |
[11] | Hang YU, Yanling ZHOU, Mengxin ZHAI, Han LIU. Text classification based on pre-training model and label fusion [J]. Journal of Computer Applications, 2024, 44(3): 709-714. |
[12] | Dapeng XU, Xinmin HOU. Feature selection method for graph neural network based on network architecture design [J]. Journal of Computer Applications, 2024, 44(3): 663-670. |
[13] | Kaitian WANG, Qing YE, Chunlei CHENG. Classification method for traditional Chinese medicine electronic medical records based on heterogeneous graph representation [J]. Journal of Computer Applications, 2024, 44(2): 411-417. |
[14] | Rui GAO, Xuebin CHEN, Zucuan ZHANG. Dynamic social network privacy publishing method for partial graph updating [J]. Journal of Computer Applications, 2024, 44(12): 3831-3838. |
[15] | Nengbing HU, Biao CAI, Xu LI, Danhua CAO. Graph classification method based on graph pooling contrast learning [J]. Journal of Computer Applications, 2024, 44(11): 3327-3334. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||