Heterogeneous graph embedding with single-level aggregation and infomax encoding
Heterogeneous graph embedding with single-level aggregation and infomax encoding
复制标题
DOI：
10.1007/s10994-022-06160-5
复制
发表时间：
2022-04
期刊：
影响因子：
7.5
通讯作者：
Nuttapong Chairatanakul;Xin Liu;Nguyen Thai Hoang;T. Murata
中科院分区：
文献类型：
--
作者：
Nuttapong Chairatanakul;Xin Liu;Nguyen Thai Hoang;T. Murata
对于异构图结构数据的嵌入方法的研究越来越受到人们的关注。现有技术的方法通常采用两级聚合方案，其中第一级聚合属于相同类型或组的邻居的信息，并且第二级采用平均或注意机制来聚合第一级的输出。我们发现，两级聚合可能会遭受一个向下加权的问题，忽视个别节点的信息，特别是当有一个不同类型的关系的数量不平衡。我们开发了一个新的简单而有效的单级聚合计划与infomax编码，命名为HIME，无监督异构图嵌入。我们的单级聚合方案执行特定于关系的转换，以获得同质嵌入聚合信息之前，从多个类型的邻居。因此，它强调了每个邻居的平等贡献，而不会受到权重下降的问题。大量的实验表明，HIME始终优于国家的最先进的方法，在链接预测，节点分类，节点聚类任务。
There has been an increasing interest in developing embedding methods for heterogeneous graph-structured data. The state-of-the-art approaches often adopt a bi-level aggregation scheme, where the first level aggregates information of neighbors belonging to the same type or group, and the second level employs the averaging or attention mechanism to aggregate the outputs of the first level. We find that bi-level aggregation may suffer from a down-weighting issue and overlook individual node information, especially when there is an imbalance in the number of different typed relations. We develop a new simple yet effective single-level aggregation scheme with infomax encoding, named HIME, for unsupervised heterogeneous graph embedding. Our single-level aggregation scheme performs relation-specific transformation to obtain homogeneous embeddings before aggregating information from multiple typed neighbors. Thus, it emphasizes each neighbor’sequalcontribution and does not suffer from the down-weighting issue. Extensive experiments demonstrate that HIME consistently outperforms the state-of-the-art approaches in link prediction, node classification, and node clustering tasks.