Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (3): 663-670.DOI: 10.11772/j.issn.1001-9081.2021040790
Special Issue: 人工智能; 2021年中国计算机学会人工智能会议(CCFAI 2021)
• 2021 CCF Conference on Artificial Intelligence (CCFAI 2021) • Next Articles
Jun HU1,2(), Zhengkang XU1,2, Li LIU1,2, Fujin ZHONG1,2
Received:
2021-05-17
Revised:
2021-06-11
Accepted:
2021-06-23
Online:
2021-11-09
Published:
2022-03-10
Contact:
Jun HU
About author:
XU Zhengkang, born in 1996, M. S. candidate. His research interests include machine learning, intelligent information processing.Supported by:
胡军1,2(), 许正康1,2, 刘立1,2, 钟福金1,2
通讯作者:
胡军
作者简介:
许正康(1996—),男,安徽马鞍山人,硕士研究生,主要研究方向:机器学习、智能信息处理基金资助:
CLC Number:
Jun HU, Zhengkang XU, Li LIU, Fujin ZHONG. Network embedding method based on multi-granularity community information[J]. Journal of Computer Applications, 2022, 42(3): 663-670.
胡军, 许正康, 刘立, 钟福金. 融合多粒度社区信息的网络嵌入方法[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 663-670.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2021040790
属性 | Cora | Wiki | DBLP | |
---|---|---|---|---|
4 039 | 2 708 | 2 405 | 13 184 | |
88 234 | 5 429 | 15 985 | 48 018 | |
— | 7 | 19 | 5 |
Tab. 1 Dataset information
属性 | Cora | Wiki | DBLP | |
---|---|---|---|---|
4 039 | 2 708 | 2 405 | 13 184 | |
88 234 | 5 429 | 15 985 | 48 018 | |
— | 7 | 19 | 5 |
方法 | 删除边比例/% | ||||
---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | |
DeepWalk | 93.01 | 93.85 | 93.46 | 93.34 | 94.76 |
node2vec | 93.16 | 95.25 | 95.56 | 95.61 | |
ComE | 95.55 | 97.10 | 96.61 | 96.10 | 96.91 |
GEMSEC | 97.23 | 97.61 | 97.73 | 97.73 | 97.74 |
EMGC | 98.71 | 98.89 | 98.84 | 98.67 | 98.65 |
Tab. 2 AUC results for link prediction on Facebook
方法 | 删除边比例/% | ||||
---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | |
DeepWalk | 93.01 | 93.85 | 93.46 | 93.34 | 94.76 |
node2vec | 93.16 | 95.25 | 95.56 | 95.61 | |
ComE | 95.55 | 97.10 | 96.61 | 96.10 | 96.91 |
GEMSEC | 97.23 | 97.61 | 97.73 | 97.73 | 97.74 |
EMGC | 98.71 | 98.89 | 98.84 | 98.67 | 98.65 |
方法 | 删除边比例/% | ||||
---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | |
DeepWalk | 81.23 | 78.40 | |||
node2vec | 82.47 | 81.87 | 72.99 | ||
ComE | 84.35 | 86.45 | 82.91 | 82.65 | 78.47 |
GEMSEC | 91.50 | 89.24 | 86.94 | 82.33 | 74.78 |
EMGC | 92.89 | 90.67 | 87.38 | 82.51 | 73.77 |
Tab. 3 AUC results for link prediction on Cora
方法 | 删除边比例/% | ||||
---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | |
DeepWalk | 81.23 | 78.40 | |||
node2vec | 82.47 | 81.87 | 72.99 | ||
ComE | 84.35 | 86.45 | 82.91 | 82.65 | 78.47 |
GEMSEC | 91.50 | 89.24 | 86.94 | 82.33 | 74.78 |
EMGC | 92.89 | 90.67 | 87.38 | 82.51 | 73.77 |
方法 | 删除边比例/% | ||||
---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | |
DeepWalk | 82.52 | 80.75 | |||
node2vec | 84.10 | 84.28 | 81.68 | ||
ComE | 88.39 | 87.50 | 85.71 | 84.95 | 84.46 |
GEMSEC | 92.52 | 91.93 | 91.30 | 90.44 | 89.40 |
EMGC | 93.11 | 92.00 | 91.20 | 90.37 | 89.01 |
Tab. 4 AUC results for link prediction on Wiki
方法 | 删除边比例/% | ||||
---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | |
DeepWalk | 82.52 | 80.75 | |||
node2vec | 84.10 | 84.28 | 81.68 | ||
ComE | 88.39 | 87.50 | 85.71 | 84.95 | 84.46 |
GEMSEC | 92.52 | 91.93 | 91.30 | 90.44 | 89.40 |
EMGC | 93.11 | 92.00 | 91.20 | 90.37 | 89.01 |
方法 | 删除边比例/% | ||||
---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | |
DeepWalk | 94.35 | 92.69 | |||
node2vec | 93.62 | 93.18 | 91.24 | ||
ComE | 94.91 | 93.70 | 93.16 | 92.11 | 88.01 |
GEMSEC | 92.03 | 91.10 | 90.70 | ||
EMGC | 95.64 | 95.38 | 95.11 | 94.36 | 93.17 |
Tab. 5 AUC results for link prediction on DBLP
方法 | 删除边比例/% | ||||
---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | |
DeepWalk | 94.35 | 92.69 | |||
node2vec | 93.62 | 93.18 | 91.24 | ||
ComE | 94.91 | 93.70 | 93.16 | 92.11 | 88.01 |
GEMSEC | 92.03 | 91.10 | 90.70 | ||
EMGC | 95.64 | 95.38 | 95.11 | 94.36 | 93.17 |
评价标准 | 方法 | 不同训练比例/% | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | ||
Macro-F1 | DeepWalk | 75.48 | 78.45 | 79.44 | 80.67 | 80.87 | 81.65 | 81.86 | 81.91 | 81.49 |
node2vec | 75.58 | 78.84 | 80.10 | 80.52 | 81.03 | 81.23 | 81.61 | 81.72 | 81.94 | |
ComE | 74.72 | 75.51 | 76.27 | 77.38 | 78.21 | 78.71 | 78.79 | 78.22 | 79.91 | |
GEMSEC | 73.61 | 75.86 | 77.06 | 77.76 | 77.80 | 77.86 | 78.14 | 79.00 | 79.25 | |
EMGC | 74.49 | 78.14 | 79.86 | 80.98 | 81.22 | 82.30 | 82.37 | 83.16 | 82.31 | |
Micro-F1 | DeepWalk | 76.78 | 79.60 | 80.70 | 81.79 | 82.03 | 82.86 | 82.95 | 82.82 | 82.47 |
node2vec | 77.08 | 79.87 | 80.98 | 81.36 | 81.77 | 82.10 | 82.50 | 82.61 | 82.78 | |
ComE | 76.02 | 76.69 | 77.44 | 78.37 | 79.20 | 79.72 | 79.75 | 79.37 | 81.10 | |
GEMSEC | 74.89 | 76.82 | 77.83 | 78.58 | 78.68 | 78.60 | 78.90 | 79.90 | 80.29 | |
EMGC | 75.70 | 78.59 | 81.46 | 82.05 | 82.34 | 82.89 | 83.61 | 83.39 | 85.38 |
Tab. 6 Node classification results on Cora dataset
评价标准 | 方法 | 不同训练比例/% | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | ||
Macro-F1 | DeepWalk | 75.48 | 78.45 | 79.44 | 80.67 | 80.87 | 81.65 | 81.86 | 81.91 | 81.49 |
node2vec | 75.58 | 78.84 | 80.10 | 80.52 | 81.03 | 81.23 | 81.61 | 81.72 | 81.94 | |
ComE | 74.72 | 75.51 | 76.27 | 77.38 | 78.21 | 78.71 | 78.79 | 78.22 | 79.91 | |
GEMSEC | 73.61 | 75.86 | 77.06 | 77.76 | 77.80 | 77.86 | 78.14 | 79.00 | 79.25 | |
EMGC | 74.49 | 78.14 | 79.86 | 80.98 | 81.22 | 82.30 | 82.37 | 83.16 | 82.31 | |
Micro-F1 | DeepWalk | 76.78 | 79.60 | 80.70 | 81.79 | 82.03 | 82.86 | 82.95 | 82.82 | 82.47 |
node2vec | 77.08 | 79.87 | 80.98 | 81.36 | 81.77 | 82.10 | 82.50 | 82.61 | 82.78 | |
ComE | 76.02 | 76.69 | 77.44 | 78.37 | 79.20 | 79.72 | 79.75 | 79.37 | 81.10 | |
GEMSEC | 74.89 | 76.82 | 77.83 | 78.58 | 78.68 | 78.60 | 78.90 | 79.90 | 80.29 | |
EMGC | 75.70 | 78.59 | 81.46 | 82.05 | 82.34 | 82.89 | 83.61 | 83.39 | 85.38 |
评价标准 | 方法 | 不同训练比例/% | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | ||
Macro-F1 | DeepWalk | 89.65 | 90.33 | 90.76 | 90.79 | 91.01 | 91.13 | 91.19 | 91.47 | 91.57 |
node2vec | 90.44 | 90.93 | 91.19 | 91.38 | 91.52 | 91.79 | 91.76 | 91.69 | 91.62 | |
ComE | 90.60 | 90.79 | 90.80 | 90.93 | 90.99 | 91.08 | 91.09 | 91.18 | 90.67 | |
GEMSEC | 86.56 | 88.45 | 89.06 | 89.43 | 89.74 | 89.84 | 89.91 | 89.85 | 89.92 | |
EMGC | 89.56 | 90.86 | 91.19 | 91.58 | 91.64 | 91.88 | 91.85 | 91.89 | 91.83 | |
Micro-F1 | DeepWalk | 90.33 | 90.91 | 91.27 | 91.28 | 91.50 | 91.60 | 91.66 | 91.91 | 92.00 |
node2vec | 91.00 | 91.41 | 91.64 | 91.77 | 91.89 | 92.16 | 92.13 | 92.02 | 91.91 | |
ComE | 91.03 | 91.16 | 91.19 | 91.31 | 91.36 | 91.42 | 91.42 | 91.45 | 90.97 | |
GEMSEC | 87.11 | 89.02 | 89.56 | 89.91 | 90.19 | 90.28 | 90.34 | 90.24 | 90.36 | |
EMGC | 90.09 | 91.14 | 91.63 | 91.93 | 91.94 | 92.12 | 92.10 | 92.20 | 92.11 |
Tab. 7 Node classification results on DBLP dataset
评价标准 | 方法 | 不同训练比例/% | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | ||
Macro-F1 | DeepWalk | 89.65 | 90.33 | 90.76 | 90.79 | 91.01 | 91.13 | 91.19 | 91.47 | 91.57 |
node2vec | 90.44 | 90.93 | 91.19 | 91.38 | 91.52 | 91.79 | 91.76 | 91.69 | 91.62 | |
ComE | 90.60 | 90.79 | 90.80 | 90.93 | 90.99 | 91.08 | 91.09 | 91.18 | 90.67 | |
GEMSEC | 86.56 | 88.45 | 89.06 | 89.43 | 89.74 | 89.84 | 89.91 | 89.85 | 89.92 | |
EMGC | 89.56 | 90.86 | 91.19 | 91.58 | 91.64 | 91.88 | 91.85 | 91.89 | 91.83 | |
Micro-F1 | DeepWalk | 90.33 | 90.91 | 91.27 | 91.28 | 91.50 | 91.60 | 91.66 | 91.91 | 92.00 |
node2vec | 91.00 | 91.41 | 91.64 | 91.77 | 91.89 | 92.16 | 92.13 | 92.02 | 91.91 | |
ComE | 91.03 | 91.16 | 91.19 | 91.31 | 91.36 | 91.42 | 91.42 | 91.45 | 90.97 | |
GEMSEC | 87.11 | 89.02 | 89.56 | 89.91 | 90.19 | 90.28 | 90.34 | 90.24 | 90.36 | |
EMGC | 90.09 | 91.14 | 91.63 | 91.93 | 91.94 | 92.12 | 92.10 | 92.20 | 92.11 |
1 | ZHANG D K, YIN J, ZHU X Q, et al. Network representation learning: a survey[J]. IEEE Transactions on Big Data, 2018, 6(1): 3-28. |
2 | 齐金山,梁循,李志宇,等. 大规模复杂信息网络表示学习:概念、方法与挑战[J]. 计算机学报,2018,41(10):2394-2420. 10.11897/SP.J.1016.2018.02394 |
QI J S, LIANG X, LI Z Y, et al. Representation learning of large-scale complex information network: concepts, methods and challenges[J]. Chinese Journal of Computers, 2018, 41(10): 2394-2420. 10.11897/SP.J.1016.2018.02394 | |
3 | SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2008, 20(1): 61-80. 10.1109/tnn.2008.2005605 |
4 | WU Z H, PAN S R, CHEN F W, et al. A comprehensive survey on graph neural network[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24. 10.1109/tnnls.2020.2978386 |
5 | WANG X, CUI P, WANG J, et al. Community preserving network embedding[C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence. Menlo Alto, CA: AAAI, 2017: 203-209. 10.1609/aaai.v33i01.33015337 |
6 | LI Y, WANG Y, ZHANG T T, et al. Learning network embedding with community structural information[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. Menlo Alto, CA: AAAI, 2019: 2937-2943. 10.24963/ijcai.2019/407 |
7 | 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. 10.1145/2623330.2623732 |
8 | GROVER A, LESKOVEC J. node2vec: scalable feature learning for networks[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 855-864. 10.1145/2939672.2939754 |
9 | TANG J, QU M, WANG M, et al. LINE: large-scale information network embedding[C]// Proceedings of the 24th International Conference on World Wide Web. Republic and Canton of Geneva: International World Wide Web Conferences Steering Committee, 2015: 1067-1077. 10.1145/2736277.2741093 |
10 | CAVALLARI S, ZHENG V W, CAI H Y, et al. Learning community embedding with community detection and node embedding on graphs[C]// Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. New York: ACM, 2017: 377-386. 10.1145/3132847.3132925 |
11 | ROZEMBERCZKI B, DAVIES R, SARKAR R, et al. GEMSEC: graph embedding with self clustering[C]// Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. New York: ACM, 2019: 65-72. 10.1145/3341161.3342890 |
12 | KEIKHA M M, RAHGOZAR M, ASADPOUR M. Community aware random walk for network embedding[J]. Knowledge-Based Systems, 2018, 148: 47-54. 10.1016/j.knosys.2018.02.028 |
13 | ZHOU M Q, LIU D, KONG Y H, et al. Enhanced network representation learning with community aware and relational attention[J]. IEEE Access, 2020, 8: 57136-57147. 10.1109/access.2020.2981649 |
14 | TU C C, ZENG X K, WANG H, et al. A unified framework for community detection and network representation learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 31(6): 1051-1065. 10.1109/tkde.2018.2852958 |
15 | 徐丽, 丁世飞. 粒度聚类算法研究[J]. 计算机科学, 2021, 38(8): 25-38. 10.1007/978-3-642-22691-5_44 |
XU L, DING S F. Research on granularity clustering algorithms[J]. Computer Science, 2011, 38(8): 25-28. 10.1007/978-3-642-22691-5_44 | |
16 | 段震, 闵星, 王倩倩,等. 基于商空间的多层粒化社区发现方法[J].南京大学学报(自然科学), 2017, 53(4): 764-774. 10.13232/j.cnki.jnju.2017.04.020 |
DUAN Z, MIN X, WANG Q Q, et al. Multilayer granulation community detection method based on quotient space[J]. Journal of Nanjing University(Natural Science), 2017, 53(4):764-774. 10.13232/j.cnki.jnju.2017.04.020 | |
17 | NIEPERT M, AHMED M, KUTZKOV K. Learning convolutional neural networks for graphs[C]// Proceedings of the 33rd International Conference on Machine Learning. Cambridge, MA: JMLR Press, 2016: 2014-2023. |
18 | KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2021-05-06]. . |
19 | VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C/OL]. [2021-05-06]. . |
20 | 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. Cambridge, MA: MIT Press, 2017:1025-1035. 10.1145/3219819.3219890 |
21 | MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2013: 3111-3119. |
22 | MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL]. [2021-05-06]. . 10.3126/jiee.v3i1.34327 |
23 | BLONDEL V D, GUILLAUME J L, LAMBIOTTE R, et al. Fast unfolding of communities in large networks[J]. Journal of Statistical Mechanics: Theory and Experiment, 2008, 2008(10): 10008. 10.1088/1742-5468/2008/10/p10008 |
24 | LESKOVEC J, KREVL A. SNAP datasets: stanford large network dataset collection[DB/OL]. [2021-05-06]. , 2014. |
25 | MCCALLUM A K, NIGAM K, RENNIE J, et al. Automating the construction of internet portals with machine learning[J]. Information Retrieval, 2000, 3(2): 127-163. 10.1023/a:1009953814988 |
26 | SEN P, NAMATA G, BILGIC M, et al. Collective classification in network data[J]. AI Magazine, 2008, 29(3): 93-93. 10.1609/aimag.v29i3.2157 |
[1] | Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650. |
[2] | Yao LIU, Yumeng LI, Miaomiao SONG. Cognitive graph based on business process [J]. Journal of Computer Applications, 2024, 44(6): 1699-1705. |
[3] | 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. |
[4] | Fan MENG, Qunli YANG, Jing HUO, Xinkuan WANG. EraseMTS: iterative active multivariable time series anomaly detection algorithm based on margin anomaly candidate set [J]. Journal of Computer Applications, 2024, 44(5): 1458-1463. |
[5] | Shiliang LIU, Yi WANG, Yinglong MA. Non-overlapping community detection with imbalanced community sizes [J]. Journal of Computer Applications, 2024, 44(11): 3396-3402. |
[6] | Zhongyu WANG, Xiaodong QIAN. Optimization of edge connection rules for supply chain network based on improved expectation maximization algorithm [J]. Journal of Computer Applications, 2024, 44(11): 3386-3395. |
[7] | Jie HUANG, Ruizi WU, Junli LI. Efficient adaptive robustness optimization algorithm for complex networks [J]. Journal of Computer Applications, 2024, 44(11): 3530-3539. |
[8] | Yuhao TANG, Dezhong PENG, Zhong YUAN. Fuzzy multi-granularity anomaly detection for incomplete mixed data [J]. Journal of Computer Applications, 2024, 44(10): 3097-3104. |
[9] | Jinghong WANG, Zhixia ZHOU, Hui WANG, Haokang LI. Attribute network representation learning with dual auto-encoder [J]. Journal of Computer Applications, 2023, 43(8): 2338-2344. |
[10] | Yinying ZHOU, Yunsheng ZHOU, Dunhui YU, Jun SUN. Adaptive social recommendation based on negative similarity [J]. Journal of Computer Applications, 2023, 43(8): 2439-2447. |
[11] | Xiaoyan ZHANG, Jiayi WANG. Comparison of three-way concepts under attribute clustering [J]. Journal of Computer Applications, 2023, 43(5): 1336-1341. |
[12] | Lin ZHOU, Yuzhi XIAO, Peng LIU, Youpeng QIN. Community mining algorithm based on multi-relationship of nodes and its application [J]. Journal of Computer Applications, 2023, 43(5): 1489-1496. |
[13] | Peng LI, Shilin WANG, Guangwu CHEN, Guanghui YAN. Key node mining in complex network based on improved local structural entropy [J]. Journal of Computer Applications, 2023, 43(4): 1109-1114. |
[14] | Keke WANG, Yu ZHU, Xiaoying WANG, Jianqiang HUANG, Tengfei CAO. Heterogeneous hypernetwork representation learning method with hyperedge constraint [J]. Journal of Computer Applications, 2023, 43(12): 3654-3661. |
[15] | Xiangyu LUO, Ke YAN, Yan LU, Tian WANG, Gang XIN. Nonuniform time slicing method based on prediction of community variance [J]. Journal of Computer Applications, 2023, 43(11): 3457-3463. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||