您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（理学版）》

《山东大学学报(理学版)》 ›› 2024, Vol. 59 ›› Issue (7): 64-75.doi: 10.6040/j.issn.1671-9352.1.2023.102

• 综述 • 上一篇    下一篇

融合多重特征的噪声网络对齐方法

咸宁1,2(),范意兴1,2,廉涛3,郭嘉丰1,2,*()   

  1. 1. 中国科学院计算技术研究所网络与数据科学与技术重点实验室，北京 100190
    2. 中国科学院大学计算机科学与技术学院，北京 100190
    3. 太原理工大学计算机科学与技术学院(大数据学院)，山西 晋中 030600
  • 收稿日期:2023-11-24 出版日期:2024-07-20 发布日期:2024-07-15
  • 通讯作者: 郭嘉丰 E-mail:xianning21s@ict.ac.cn;guojiafeng@ict.ac.cn
  • 作者简介:咸宁(1999—)，男，硕士研究生，研究方向为网络对齐、大语言模型评估. E-mail：xianning21s@ict.ac.cn
  • 基金资助:
    国家自然科学基金资助项目(62372431);国家重点研发计划项目(2021QY1701);国家重点研发计划项目(2023YFA1011602);中国科学院青年创新促进会会员项目(2021100);中国科学院计算技术研究所创新项目(E261090);国防科技创新项目

Noise network alignment method integrating multiple features

Ning XIAN1,2(),Yixing FAN1,2,Tao LIAN3,Jiafeng GUO1,2,*()   

  1. 1. Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
    2. School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100190, China
    3. College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Jinzhong 030600, Shanxi, China
  • Received:2023-11-24 Online:2024-07-20 Published:2024-07-15
  • Contact: Jiafeng GUO E-mail:xianning21s@ict.ac.cn;guojiafeng@ict.ac.cn

RichHTML

4

PDF (PC)

832

摘要：

针对网络对齐任务中网络结构差异大和锚节点对噪声大的问题，提出一种基于多轮迭代的网络对齐方法。该方法在每轮迭代时使用多种启发式方法计算不同维度的节点特征，利用多重特征的组合来评估锚节点的可靠性，过滤其中潜在的噪声，增强每轮对齐过程的置信度; 使用图神经网络增强无属性节点之间的一致性，减轻网络结构差异带来的影响。实验结果表明, 该方法可以在高噪声的情况下具有高准确率，验证了其有效性。

关键词: 网络对齐, 图同构网络, 噪声过滤, 图元

Abstract:

A multi-round iterative network alignment method is proposed to address the challenges of large structural differences and high noise sensitivity in anchor nodes in network alignment tasks. The method calculates node features of different dimensions using various heuristic approaches at each iteration, utilizing the combination of multiple features to assess the reliability of anchor nodes, filter potential noise, and enhance the confidence of each alignment round. Additionally, a graph neural network is employed to improve the consistency between nodes without attributes, mitigating the impact of structural differences in networks. Experimental results demonstrate that this method achieves high accuracy under high noise conditions, verifying its effectiveness.

Key words: network alignment, graph isomorphism, noise filtering, graphlet

中图分类号: 

  • TP391

图1

图元度向量"

表1

数据集信息"

数据集 网络名 节点数 边数 节点属性数 所有的对齐节点对数
原始Arenas Email网络 Gs 1 135 5 451 0 1 135
合成Arenas Email网络 Gt 1 135 5 437 0
Facebook Gs 1 043 4 734 0 1 043
Twitter Gt 1 043 4 860 0
Douban Offline Gs 1 118 1 511 538 1 118
Douban Online Gt 3 906 8 164 538

表2

对齐结果"

数据集 指标 本文方法/% REGAL/% CENALP/%
Accuracy 94.45 0.09 77.48
Arenas Email Precision@5 98.06 0.44 87.49
Precision@10 98.06 0.88 92.85
Accuracy 96.36 34.13 91.66
Facebook-Twitter Precision@5 97.32 44.87 93.44
Precision@10 98.47 49.09 95.01
Accuracy 46.24 2.77 21.91
Douban Precision@5 63.24 8.50 34.26
Precision@10 72.27 11.09 40.52

图2

正例节点比例对对齐正确率的影响"

图3

迭代轮数对对齐正确率的影响"

图4

各对齐组件对对齐正确率的影响"

1 SHU Kai , WANG Suhang , TANG Jiliang , et al. User identity linkage across online social networks: a review[J]. ACM SIGKDD Explorations Newsletter, 2017, 18 (2): 5- 17.
doi: 10.1145/3068777.3068781
2 ZHONG Erheng, FAN Wei, WANG Junwei, et al. ComSoc: adaptive transfer of user behaviors over composite social network[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Beijing: ACM, 2012: 696-704.
3 PEI Shihao, YU Lu, YU Guoxian, et al. Graph alignment with noisy supervision[C]//Proceedings of the ACM Web Conference 2022. Lyon: ACM, 2022: 1104-1114.
4 GUZZI PH , MILENKOVIĆ T . Survey of local and global biological network alignment: the need to reconcile the two sides of the same coin[J]. Briefings in Bioinformatics, 2018, 19, 472- 481.
5 CHEN Chen, TONG Hanghang, XIE Lei, et al. FASCINATE: Fast cross-layer dependency inference on multi-layered networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016: 765-774.
6 MAO Xin, WANG Wenting, WU Yuanbin, et al. From alignment to assignment: frustratingly simple unsupervised entity alignment[C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Punta Cana: Association for Computational Linguistics, 2021: 2843-2853.
7 TRUNG H T, VAN VINH T, TAM N T, et al. Adaptive network alignment with unsupervised and multi-order convolutional networks[C]//2020 IEEE 36th International Conference on Data Engineering (ICDE). Dallas: IEEE, 2020: 85-96.
8 PEI Shichao, YU Lu, YU Guoxian, et al. REA: robust cross-lingual entity alignment between knowledge graphs[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2020: 2175-2184.
9 EMMERT-STREIB F , DEHMER M , SHI Y . Fifty years of graph matching, network alignment and network comparison[J]. Information Sciences, 2016, 346 (C): 180- 197.
10 BURKARD R E , PITSOULIS L S . The quadratic assignment problem[J]. Parallel Optimization Colloquium, 2012, 25 (4): 143- 174.
11 MILENKOVIĆ T , NG W L , HAYES W , et al. Optimal network alignment with graphlet degree vectors[J]. Cancer Informatics, 2010, 9, 121- 137.
12 BAYATI M , GLEICH D F , SABERI A , et al. Message-passing algorithms for sparse network alignment[J]. ACM Transactions on Knowledge Discovery from Data, 2013, 7 (1): 1- 31.
13 KOUTRA D, TONG H, LUBENSKY D. BIG-ALIGN: fast bipartite graph alignment[C]//2013 IEEE 13th International Conference on Data Mining. Dallas: IEEE, 2013: 389-398.
14 SAAD-ELDIN A, PEDIGO B D, PRIEBE C E, et al. Graph matching via optimal transport[EB/OL]. (2021-11-09)[2023-09-01]. https://arxiv.org/abs/2111.05366.
15 SINGH R , XU J , BERGER B . Global alignment of multiple protein interaction networks with application to functional orthology detection[J]. Proceedings of the National Academy of Sciences of the United States of America, 2008, 105 (35): 12763- 12768.
16 HEIMANN M, SHEN H, SAFAVI T, et al. REGAL: representation learning-based graph alignment[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM, 2018: 117-126.
17 ZHANG Si, TONG Hanghang. FINAL: fast attributed network alignment[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016: 1345-1354.
18 MAN Tong, SHEN Huawei, LIU Shenghua, et al. Predict anchor links across social networks via an embedding approach[C]//Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. New York: AAAI Press, 2016: 1823-1829.
19 NGUYEN T T , PHAM M T , NGUYEN T T , et al. Structural representation learning for network alignment with self-supervised anchor links[J]. Expert Systems with Applications, 2021, 165, 113857.
doi: 10.1016/j.eswa.2020.113857
20 XIN Keyuan, SUN Zequn, HUA Wen, et al. Large-scale entity alignment via knowledge graph merging, partitioning and embedding[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management. Atlanta: ACM, 2022: 2240-2249.
21 WANG Zichuan, LYU Qingsong, LAN Xiaohan, et al. Cross-lingual knowledge graph alignment via graph convolutional networks[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels: Association for Computational Linguistics, 2018: 349-357.
22 LI Chengjiang, CAO Yixin, HOU Lei, et al. Semi-supervised entity alignment via joint knowledge embedding model and cross-graph model[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong: Association for Computational Linguistics, 2019: 2723-2732.
23 PEI Shichao, YU Lu, YU Guoxian, et al. Graph alignment with noisy supervision[C]//Proceedings of the ACM Web Conference 2022. New York: ACM, 2022: 1104-1114.
24 KOUTRA D , SHAH N , VOGELSTEIN J T , et al. Delta Con: principled massive-graph similarity function with attribution[J]. ACM Transactions on Knowledge Discovery from Data, 2016, 10 (3): 1- 43.
25 PRZULJ N . Biological network comparison using graphlet degree distribution[J]. Bioinformatics, 2007, 23 (2): e177- e183.
doi: 10.1093/bioinformatics/btl301
26 TONG H, FALOUTSOS C, PAN J Y. Fast random walk with restart and its applications[C]//Sixth International Conference on Data Mining (ICDM'06). Hong Kong: IEEE, 2006: 613-622.
27 XU K, HU W, LESKOVEC J, et al. How powerful are graph neural networks?[EB/OL]. (2018-10-01)[2023-08-06]. https://arxiv.org/abs/1810.00826.
28 XU Keyulu, LI Chengtao, TIAN Yongle, et al. Representation learning on graphs with jumping knowledge networks[C]// Proceedings of the 35th International Conference on Machine Learning: Volume 80. Stockholmsmässan: PMLR, 2018 : 5453-5462.
29 PARK J D , TRAN C , SHIN W Y , et al. On the power of gradual network alignment using dual-perception similarities[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (12): 15292- 15307.
30 YAN Yucheng, ZHANG Si, TONG Hanghang. BRIGHT: a bridging algorithm for network alignment[C]//Proceedings of the Web Conference 2021. Ljubljana: ACM, 2021: 3907-3917.
31 GUIMERÀ R , DANON L , DÍAZ-GUILERA A , et al. Self-similar community structure in a network of human interactions[J]. Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics, 2003, 68, 065103.
32 CAO Xuezhi, YU Yong. BASS: a bootstrapping approach for aligning heterogenous social networks[M]//FRASCONI P, LANDWEHR N, MANCO G, et al. Machine Learning and Knowledge Discovery in Databases: Volume 9851. Cham: Springer, 2016: 459-475.
33 DU Xingbo, YAN Junchi, ZHA Hongyuan. Joint link prediction and network alignment via cross-graph embedding[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. Macao: International Joint Conferences on Artificial Intelligence Organization, 2019: 2251-2257.
34 FEY M, LENSSEN J E. Fast graph representation learning with pytorch geometric[EB/OL]. (2019-05-06)[2023-09-01]. https://arxiv.org/abs/1903.02428v3.
[1] 张晓媛, 田毅, 任子涵, 段天宇, 杨斯媛, 张月轩. 拓扑邻域基在密度聚类算法中的应用[J]. 《山东大学学报(理学版)》, 2026, 61(5): 55-64.
[2] 孙迪,郭义童,任超,范海峰,张传雷. 基于多尺度特征融合与改进注意力的锈蚀螺栓螺帽检测[J]. 《山东大学学报(理学版)》, 2026, 61(1): 1-14.
[3] 仲尚,马丽,刘文哲,李雨豪. 融合多尺度注意力机制和改进特征融合的轻量化水面小目标检测模型[J]. 《山东大学学报(理学版)》, 2026, 61(1): 15-25.
[4] 余雷,孙懿,华金铭,李腊全. 基于深度神经网络的重症监护室脓毒症患者死亡风险预测模型分析[J]. 《山东大学学报(理学版)》, 2026, 61(1): 26-35.
[5] 王军涛,黄强. 基于一般重叠函数的模糊数学形态学边缘检测方法[J]. 《山东大学学报(理学版)》, 2026, 61(1): 36-48.
[6] 李文焱,李丽红,王洪欣. 基于知识度量的模糊粗糙c-均值算法[J]. 《山东大学学报(理学版)》, 2026, 61(1): 49-64.
[7] 孙清,叶军,曾广财,宋苏洋,汪一心. 结合蝙蝠算法和紧密度改进的三支K-means算法[J]. 《山东大学学报(理学版)》, 2026, 61(1): 65-75.
[8] 邹峥,雷雨晟,刘石坚,王定一,邱学炜,史雯雯,周校通. 白蚁分区式微方向感知的精确形态识别[J]. 《山东大学学报(理学版)》, 2026, 61(1): 76-84.
[9] 梁霞,郭洁. 基于在线评论的线上教学平台选择方法[J]. 《山东大学学报(理学版)》, 2024, 59(9): 108-118.
[10] 黎超,廖薇. 基于医疗知识驱动的中文疾病文本分类模型[J]. 《山东大学学报(理学版)》, 2024, 59(7): 122-130.
[11] 纪杰,孙承杰,单丽莉,尚伯乐,林磊. 基于提示学习的电信网络诈骗案件分类方法[J]. 《山东大学学报(理学版)》, 2024, 59(7): 113-121.
[12] 罗奇,苟刚. 基于聚类和群组归一化的多模态对话情绪识别[J]. 《山东大学学报(理学版)》, 2024, 59(7): 105-112.
[13] 赵峰叙,王健,林原,林鸿飞. 面向排序学习的概率分布优化模型[J]. 《山东大学学报(理学版)》, 2024, 59(7): 95-104.
[14] 黄兴宇,赵明宇,吕子钰. 面向图神经网络表征学习的类别知识探针[J]. 《山东大学学报(理学版)》, 2024, 59(7): 85-94.
[15] 桂梁,徐遥,何世柱,张元哲,刘康,赵军. 基于动态邻居选择的知识图谱事实错误检测方法[J]. 《山东大学学报(理学版)》, 2024, 59(7): 76-84.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(理学版)》编辑部　
地址: 山东省济南市山大南路27号山东大学中心校区（250100）　电话: +86-0531-88366917　E-mail: xblxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发