In the process of collecting heterogeneous graph data, node attributes are often missing due to privacy protection policies or copyright constraints. Regarding both incomplete attributes and completely missing attributes, a heterogeneous graph representation learning algorithm based on attribute completion (HGAC) was proposed. For nodes with incomplete attributes, the missing attributes were obtained by constructing an adjacency matrix in the attribute space and performing graph convolution. Subsequently, the attributes were regarded as abstract nodes, and under the guidance of meta-paths, the topological embeddings of both nodes and attributes were learned. The similarity among the topological embeddings were then used to complete completely missing attributes. Experiments conducted on three real datasets demonstrate that the proposed algorithm effectively enhances the performance of downstream tasks and possesses strong generalization capability.
定义1 属性缺失的图:给定一个图以及对应的邻接矩阵和节点属性集合,存在节点集合,其中的节点属性完全缺失,对应的属性集合表示为,同时,存在节点集合,其中的节点属性不完备,对应的属性集合表示为,并以掩码矩阵 I 来记录中的属性缺失情况.当时,代表节点的第个属性缺失;反之,当时,代表节点的第个属性存在.将除上述两种节点之外的节点称为属性完整的节点,用表示,对应的属性集合为.对于图,若满足,,则称图为属性缺失的图.为了便于后续论述,将属性不完备的节点简称为不完备节点,将属性完全缺失的节点简称为缺失节点,将属性完整的节点简称为完整节点.
ZhouLi-hua, WangJia-long, WangLi-zhen, et al. Heterogeneous information network representation learning: a survey[J]. Chinese Journal of Computers, 2022, 45(1): 160-189.
[4]
JinD, HuoC Y, LiangC D, et al. Heterogeneous graph neural network via attribute completion[C]//Proceedings of the Web Conference 2021. Ljubljana, 2021: 391-400.
[5]
KipfT N, WellingM. Semi-supervised classification with graph convolutional networks[C]//International Conference on Learning Representations. Toulon, 2017: 1-14.
[6]
WangX, JiH Y, ShiC, et al. Heterogeneous graph attention network[C]//The World Wide Web Conference. San Francisco, 2019: 2022-2032.
[7]
FuX, ZhangJ, MengZ, et al. MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding[C]//Proceedings of the Web Conference 2020. Taipei, 2020: 2331-2341.
[8]
YouJ, MaX, DingY, et al. Handling missing data with graph representation learning[J]. Advances in Neural Information Processing Systems, 2020, 33: 19075-19087.
ChenX, ChenS, YaoJ, et al. Learning on attribute-missing graphs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 44(2): 740-757.
[11]
TuW X, ZhouS H, LiuX W, et al. Initializing then refining: a simple graph attribute imputation network[C]//Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. Vienna, 2022: 3494-3500.
[12]
WangK, YuY, HuangC, et al. Heterogeneous graph neural network for attribute completion[J]. Knowledge-Based Systems, 2022, 251: 109171.
[13]
HeD X, LiangC D, HuoC Y, et al. Analyzing heterogeneous networks with missing attributes by unsupervised contrastive learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(4): 4438-4450.
[14]
ZhuG, ZhuZ, WangW, et al. Autoac: towards automated attribute completion for heterogeneous graph neural network[C]//2023 IEEE 39th International Conference on Data Engineering (ICDE). Anaheim, 2023: 2808-2821.
[15]
LiC, YanY Y, FuJ H, et al. HetReGAT-FC: heterogeneous residual graph attention network via feature completion[J]. Information Sciences, 2023, 632: 424-438.
[16]
DongY X, ChawlaN V, SwamiA. Metapath2vec: scalable representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax, 2017: 135-144.