Heterogeneous graph neural networks analysis: a survey of techniques, evaluations and applications

Bing, Rui; Yuan, Guan; Zhu, Mu; Meng, Fanrong; Ma, Huifang; Qiao, Shaojie

doi:10.1007/s10462-022-10375-2

Cited by 20 publications

(8 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, in the range [2,4], the ACC values stabilize. Finally, in the range [4,7], the ACC value decreases slowly. This indicates that too small L values cannot fully capture the intra-type features of nodes in the network, and too large L leads to capturing imprecise intra-type features.…”

Section: Parameter Sensitivitymentioning

confidence: 96%

“…For example, for the DBLP dataset, the ACC value increases rapidly in the range [1,2]. Then, in the range [2,4], the ACC values stabilize. Finally, in the range [4,7], the ACC value decreases slowly.…”

Section: Parameter Sensitivitymentioning

confidence: 99%

“…The feature matrix X of nodes can be used in the analysis of downstream tasks of the network. 4 The proposed model…”

Section: Definitionmentioning

confidence: 99%

“…This indicates that too small L values cannot fully capture the intra-type features of nodes in the network, and too large L leads to capturing imprecise intra-type features. Specifically, the relative stability range of the parameter L is [1,3] on Amazon, [2,4] on DBLP and Yelp. (2) Comparing different datasets, the window length of the Yelp and DBLP datasets should be larger than that of the Amazon dataset.…”

Section: Parameter Sensitivitymentioning

confidence: 99%

“…For this reason, heterogeneous network representation learning has been proposed and is developing rapidly [3]. Heterogeneous network representation learning is the process of converting highdimensional complex HINs into low-dimensional simple discrete vectors that retain as much of the underlying features of the network as possible [4]. After heterogeneous network representation learning, the resulting low-dimensional vectors can be used as feature input for downstream network analysis tasks to improve speed and performance [5].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Robust and fast representation learning for heterogeneous information networks

Lei

Chen

et al. 2023

Front. Phys.

View full text Add to dashboard Cite

Network representation learning is an important tool that can be used to optimize the speed and performance of downstream analysis tasks by extracting latent features of heterogeneous networks. However, in the face of new challenges of increasing network size, diverse latent features, and unseen network noise, existing representation models need to be further optimized. In this paper, a robust and fast representation learning model is proposed for heterogeneous networks, called RFRL. First, the global features of a heterogeneous network are divided into multiple intra-type local features and inter-type local features, and a type-aware biased sampling is designed to generate training samples for each local feature. Second, a node-type-aware and a link-type-aware shallow representation strategy are used to learn intra-type features and inter-type features respectively. This enables the model to achieve good performance while having high speed through the divide-and-conquer learning process and shallow learning model, thus coping with increasing network size and latent feature diversity. Finally, adversarial learning is used to integrate the above two representation strategies to address unseen network noise and enhance the robustness of representation learning. Extensive experiments on three network analysis tasks and three public datasets demonstrate the good performance of our RFRL model.

show abstract