[1]肖添龙,徐计,王国胤.基于偏序关系的多视图多粒度图表示学习框架[J].智能系统学报,2025,20(1):243-254.[doi:10.11992/tis.202406010]
XIAO Tianlong,XU Ji,WANG Guoyin.A multi-view and multi-granularity graph representation learning framework based on partial order relations[J].CAAI Transactions on Intelligent Systems,2025,20(1):243-254.[doi:10.11992/tis.202406010]
点击复制
XIAO Tianlong,XU Ji,WANG Guoyin.A multi-view and multi-granularity graph representation learning framework based on partial order relations[J].CAAI Transactions on Intelligent Systems,2025,20(1):243-254.[doi:10.11992/tis.202406010]
基于偏序关系的多视图多粒度图表示学习框架
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第1期
页码:
243-254
栏目:
人工智能院长论坛
出版日期:
2025-01-05
- Title:
- A multi-view and multi-granularity graph representation learning framework based on partial order relations
- Keywords:
- graph neural networks; graph pooling; multi-granularity; partial order relationships; node classification task; graph representation learning; semi-supervised learning; graph embedding
- 分类号:
- TP391
- 摘要:
- 图池化作为图神经网络中重要的组件，在获取图的多粒度信息的过程中扮演了重要角色。而当前的图池化操作均以平等地位看待数据点，普遍未考虑利用邻域内数据之间的偏序关系，从而造成图结构信息破坏。针对此问题，本文提出一种基于偏序关系的多视图多粒度图表示学习框架(multi-view and multi-granularity graph representation learning based on partial order relationships, MVMGr-PO)，它通过从节点特征视图、图结构视图以及全局视图对节点进行综合评分，进而基于节点之间的偏序关系进行下采样操作。相比于其他图表示学习方法，MVMGr-PO可以有效地提取多粒度图结构信息，从而可以更全面地表征图的内在结构和属性。此外，MVMGr-PO可以集成多种图神经网络架构，包括GCN(graph convolutional network)、GAT(graph attention network)以及GraphSAGE(graph sample and aggregate)等。通过在6个数据集上进行实验评估，与现有基线模型相比，MVMGr-PO在分类准确率上有明显提升。
- Abstract:
- Graph pooling, as a crucial component of graph neural networks (GNNs), plays a vital role in capturing multi-granularity information of graphs. However, current graph pooling operations typically treat data points equally, often neglecting the partial order relationships among data within neighborhoods, which leads to the disruption of graph structural information. To address this issue, we propose a novel framework for multi-view and multi-granularity graph representation learning based on partial order relationships, named MVMGr-PO. This framework comprehensively scores nodes from the perspectives of node feature view, graph structure view, and global view, and then performs down-sampling operations based on the partial order relationships among nodes. Compared with other graph representation learning methods, MVMGr-PO effectively extracts multi-granularity graph structural information, thus providing a more comprehensive representation of the intrinsic structure and attributes of the graph. Additionally, MVMGr-PO can integrate various graph neural network (GNN) architectures, including graph convolutional network (GCN), graph attention network (GAT), and graph sample and aggregate (GraphSAGE). Experimental evaluations on six datasets demonstrate that compared with existing baseline models, MVMGr-PO significantly improves classification accuracy.
- 参考文献/References:
-
[1] SCHMARJE L, SANTAROSSA M, SCHR?DER S M, et al. A survey on semiself and unsupervised learning for image classification[J]. IEEE access, 2021, 9: 82146-82168.
[2] 陈洛轩, 林成创, 郑招良, 等. Transformer在计算机视觉场景下的研究综述[J]. 计算机科学, 2023, 50(12): 130-147.
CHEN Luoxuan, LIN Chengchuang, ZHENG Zhaoliang, et al. Review of transformer in computer vision[J]. Computer science, 2023, 50(12): 130-147.
[3] LAURIOLA I, LAVELLI A, AIOLLI F. An introduction to deep learning in natural language processing: models, techniques, and tools[J]. Neurocomputing, 2022, 470: 443-456.
[4] 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.
[5] SAKAI M, NAGAYASU K, SHIBUI N, et al. Prediction of pharmacological activities from chemical structures with graph convolutional neural networks[J]. Scientific reports, 2021, 11(1): 525.
[6] GAO Chen, WANG Xiang, HE Xiangnan, et al. Graph neural networks for recommender system[C]//Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. Virtual Event: ACM, 2022: 1623-1625.
[7] 吴国栋, 查志康, 涂立静, 等. 图神经网络推荐研究进展[J]. 智能系统学报, 2020, 15(1): 14-24.
WU Guodong, ZHA Zhikang, TU Lijing, et al. Research advances in graph neural network recommendation[J]. CAAI transactions on intelligent systems, 2020, 15(1): 14-24.
[8] 刘彦北, 马夕然, 王雯. 可信的图神经网络节点分类方法[J]. 天津工业大学学报, 2024, 43(1): 82-88.
LIU Yanbei, MA Xiran, WANG Wen. Node classification method based on trusted graph neural network[J]. Journal of Tiangong university, 2024, 43(1): 82-88.
[9] 东昱晓, 柯庆, 吴斌. 基于节点相似性的链接预测[J]. 计算机科学, 2011, 38(7): 162-164,199.
DONG Yuxiao, KE Qing, WU Bin. Link prediction based on node similarity[J]. Computer science, 2011, 38(7): 162-164,199.
[10] 王兆慧, 沈华伟, 曹婍, 等. 图分类研究综述[J]. 软件学报, 2022, 33(1): 171-192.
WANG Zhaohui, SHEN Huawei, CAO Qi, et al. Survey on graph classification[J]. Journal of software, 2022, 33(1): 171-192.
[11] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[EB/OL]. (2017-06-07)[2024-06-07]. https://arxiv.org/abs/1706.02216v4.
[12] CHIANG Weilin, LIU Xuanqing, SI Si, et al. Cluster-GCN: an efficient algorithm for training deep and large graph convolutional networks[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Anchorage: ACM, 2019: 257-266.
[13] YING Z, YOU Jiaxuan, MORRIS C, et al. Hierarchical graph representation learning with differentiable pooling[J]. Advances in neural information processing systems, 2018, 31: 1-11.
[14] ZHONG Zhiqiang, LI Chengte, PANG Jun. Multi-grained semantics-aware graph neural networks[J]. IEEE transactions on knowledge and data engineering, 2023, 35(7): 7251-7262.
[15] GAO H, JI S. Graph U-Nets[J]. IEEE transactions on pattern analysis and machine intelligence, 2022, 44(9): 4948-4960.
[16] ZHANG Zhen, BU Jiajun, ESTER M, et al. Hierarchical multi-view graph pooling with structure learning[J]. IEEE transactions on knowledge and data engineering, 2023, 35(1): 545-559.
[17] RANJAN E, SANYAL S, TALUKDAR P. ASAP: adaptive structure aware pooling for learning hierarchical graph representations[J]. Proceedings of the AAAI conference on artificial intelligence, 2020, 34(4): 5470-5477.
[18] 张蕾, 钱峰, 赵姝, 等. 基于多粒度结构的网络表示学习[J]. 智能系统学报, 2019, 14(6): 1233-1242.
ZHANG Lei, QIAN Feng, ZHAO Shu, et al. Network representation learning based on multi-granularity structure[J]. CAAI transactions on intelligent systems, 2019, 14(6): 1233-1242.
[19] SUN Haichao, WANG Guoyin, LIU Qun. Graph neural networks with multi-granularity pooling[C]//2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems. Chengdu: IEEE, 2022: 114-118.
[20] LIANG Jiongqian, GURUKAR S, PARTHASARATHY S. MILE: a multi-level framework for scalable graph embedding[J]. Proceedings of the international AAAI conference on web and social media, 2021, 15: 361-372.
[21] STANOVIC S, GAüZèRE B, BRUN L. Maximal independent vertex set applied to Graph pooling[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2022: 11-21.
[22] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. (2016-09-09)[2024-06-07]. https://arxiv.org/abs/1609.02907v4.
[23] WU Junran, CHEN Xueyan, XU Ke, et al. Structural entropy guided graph hierarchical pooling[C]//International conference on machine learning. New York: PMLR, 2022: 24017-24030.
[24] LEE J, LEE I, KANG J. Self-attention graph pooling[C]//International conference on machine learning. New York: PMLR, 2019: 3734-3743.
[25] JIANG Jianjian, LEI Fangyuan, DAI Qingyun, et al. Graph pooling in graph neural networks with node feature correlation[C]//Proceedings of the 3rd International Conference on Data Science and Information Technology. Xia’men: ACM, 2020: 105-110.
[26] KIM Y. Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2014: 1746-1751.
[27] 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.
[28] 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. San Francisco: ACM, 2016: 855-864.
[29] Veli?kovi? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL]. (2017-10-30)[2024-06-07]. https://arxiv.org/abs/1710.10903.
[30] FEY M, LENSSEN J E. Fast graph representation learning with PyTorch geometric[EB/OL]. (2019-03-06) [2024-06-07]. https://arxiv.org/abs/1903.02428v3.
[31] KINGMA D P, BA J, HAMMAD M M. Adam: a method for stochastic optimization[EB/OL]. (2014-12-22) [2024-06-07]. https://arxiv.org/abs/1412.6980v9.
[32] WATTS D J, STROGATZ S H. Collective dynamics of ‘small-world’ networks[J]. Nature, 1998, 393(6684): 440-442.
[33] GROVER A, LESKOVEC J. Node2vec: scalable featurelearning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 855-864.
[34] VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. Stat, 2017, 1050(20): 39-41.
[35] FEI M, LENSSEN J E. Fast graph representation learning with PyTorch geometric[C]//ICLR Workshop on Representation Learning on Graphs and Manifolds. Appleton: ICLR, 2019: 1-9.
[36] KINGMA D P, Ba J. Adam: a method for stochastic optimization[EB/OL]. (2022-12-22)[2024-06-07]. https://arxiv.org/abs/1412.6980.
- 相似文献/References:
-
[1]吴国栋,查志康,涂立静,等.图神经网络推荐研究进展[J].智能系统学报,2020,15(1):14.[doi:10.11992/tis.201908034]
WU Guodong,ZHA Zhikang,TU Lijing,et al.Research advances in graph neural network recommendation[J].CAAI Transactions on Intelligent Systems,2020,15():14.[doi:10.11992/tis.201908034]
[2]张勇,高大林,巩敦卫,等.用于关系抽取的注意力图长短时记忆神经网络[J].智能系统学报,2021,16(3):518.[doi:10.11992/tis.202008036]
ZHANG Yong,GAO Dalin,GONG Dunwei,et al.Attention graph long short-term memory neural network for relation extraction[J].CAAI Transactions on Intelligent Systems,2021,16():518.[doi:10.11992/tis.202008036]
[3]周俊,张志强,曹月恬,等.地理位置和时间感知的表示学习框架[J].智能系统学报,2021,16(5):909.[doi:10.11992/tis.202104011]
ZHOU Jun,ZHANG Zhiqiang,CAO Yuetian,et al.A geography and time aware representation learning framework[J].CAAI Transactions on Intelligent Systems,2021,16():909.[doi:10.11992/tis.202104011]
[4]卢毅,陈亚冉,赵冬斌,等.关键点图对比图像分类方法[J].智能系统学报,2023,18(1):36.[doi:10.11992/tis.202112001]
LU Yi,CHEN Yaran,ZHAO Dongbin,et al.Keypoint-based graph contrastive neural network for image classification[J].CAAI Transactions on Intelligent Systems,2023,18():36.[doi:10.11992/tis.202112001]
[5]车飞虎,张大伟,邵朋朋,等.基于四元数门控图神经网络的脚本事件预测[J].智能系统学报,2023,18(1):138.[doi:10.11992/tis.202203042]
CHE Feihu,ZHANG Dawei,SHAO Pengpeng,et al.Script event prediction based on a quaternion-gated graph neural network[J].CAAI Transactions on Intelligent Systems,2023,18():138.[doi:10.11992/tis.202203042]
[6]孟祥福,温晶,李子函,等.多重注意力指导下的异构图嵌入方法[J].智能系统学报,2023,18(4):688.[doi:10.11992/tis.202204006]
MENG Xiangfu,WEN Jing,LI Zihan,et al.Heterogeneous graph embedding method guided by the multi-attention mechanism[J].CAAI Transactions on Intelligent Systems,2023,18():688.[doi:10.11992/tis.202204006]
[7]周贤琛,马扬,程光权,等.战场目标实体类型识别的鲁棒图神经网络方法[J].智能系统学报,2023,18(6):1156.[doi:10.11992/tis.202111025]
ZHOU Xianchen,MA Yang,CHENG Guangquan,et al.Robust graph neural network method for target entity type recognition in a battlefield environment[J].CAAI Transactions on Intelligent Systems,2023,18():1156.[doi:10.11992/tis.202111025]
[8]曹汉童,陈璟.融合Doc2vec与GCN的多类型蛋白质相互作用预测方法[J].智能系统学报,2023,18(6):1165.[doi:10.11992/tis.202212029]
CAO Hantong,CHEN Jing.Prediction of multitype protein interactions combining Doc2vec and GCN[J].CAAI Transactions on Intelligent Systems,2023,18():1165.[doi:10.11992/tis.202212029]
[9]刘晓光,李梅.基于深度学习的药物-靶标相互作用预测研究综述[J].智能系统学报,2024,19(3):494.[doi:10.11992/tis.202308024]
LIU Xiaoguang,LI Mei.A survey of deep learning-based drug-target interaction prediction[J].CAAI Transactions on Intelligent Systems,2024,19():494.[doi:10.11992/tis.202308024]
[10]王闪闪,巩长庆,秦华锋,等.基于深度学习的K近邻图迭代静脉识别算法研究[J].智能系统学报,2024,19(5):1149.[doi:10.11992/tis.202307009]
WANG Shanshan,GONG Changqing,QIN Huafeng,et al.Vein recognition algorithm combining K-nearest neighbor and graph iterative based on deep learning[J].CAAI Transactions on Intelligent Systems,2024,19():1149.[doi:10.11992/tis.202307009]
备注/Memo
收稿日期:2024-6-7。
基金项目:国家自然科学基金项目(62366008, 61966005, 62221005).
作者简介:肖添龙，硕士研究生，主要研究方向为图神经网络、粒计算和机器学习。E-mail：gs.tlxiao22@gzu.edu.cn。;徐计，特聘教授，博士，主要研究方向为数据挖掘、粒计算和机器学习。主持国家自然科学基金项目2项，主持大型互联网企业横向项目2项，出版学术专著1部，发表学术论文20余篇。E-mail：jixu@gzu.edu.cn。;王国胤，教授，博士生导师，国家级人才，重庆师范大学校长。主要研究方向为粗糙集、粒计算、数据挖掘、认知计算、大数据、人工智能。曾任国际粗糙集学会(IRSS)理事长，现任中国人工智能学会(CAAI)副理事长、中国计算机学会(CCF)理事、重庆市人工智能学会(CQAAI)理事长，IRSS/CAAI/CCF会士。获国内外发明专利授权20余项，出版学术专著和教材20多部（含编著），发表学术论文300余篇，论著被他人引用10 000多次。E-mail：wanggy@cqupt.edu.cn。
通讯作者:徐计. E-mail：jixu@gzu.edu.cn
更新日期/Last Update:
2025-01-05