AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network

by   Guanghui Zhu, et al.

Many real-world data can be modeled as heterogeneous graphs that contain multiple types of nodes and edges. Meanwhile, due to excellent performance, heterogeneous graph neural networks (GNNs) have received more and more attention. However, the existing work mainly focuses on the design of novel GNN models, while ignoring another important issue that also has a large impact on the model performance, namely the missing attributes of some node types. The handcrafted attribute completion requires huge expert experience and domain knowledge. Also, considering the differences in semantic characteristics between nodes, the attribute completion should be fine-grained, i.e., the attribute completion operation should be node-specific. Moreover, to improve the performance of the downstream graph learning task, attribute completion and the training of the heterogeneous GNN should be jointly optimized rather than viewed as two separate processes. To address the above challenges, we propose a differentiable attribute completion framework called AutoAC for automated completion operation search in heterogeneous GNNs. We first propose an expressive completion operation search space, including topology-dependent and topology-independent completion operations. Then, we propose a continuous relaxation schema and further propose a differentiable completion algorithm where the completion operation search is formulated as a bi-level joint optimization problem. To improve the search efficiency, we leverage two optimization techniques: discrete constraints and auxiliary unsupervised graph node clustering. Extensive experimental results on real-world datasets reveal that AutoAC outperforms the SOTA handcrafted heterogeneous GNNs and the existing attribute completion method


page 1

page 11


Bi-Level Attention Graph Neural Networks

Recent graph neural networks (GNNs) with the attention mechanism have hi...

Learning on Attribute-Missing Graphs

Graphs with complete node attributes have been widely explored recently....

The Devil is in the Conflict: Disentangled Information Graph Neural Networks for Fraud Detection

Graph-based fraud detection has heretofore received considerable attenti...

Collaborative Graph Neural Networks for Attributed Network Embedding

Graph neural networks (GNNs) have shown prominent performance on attribu...

Fair Attribute Completion on Graph with Missing Attributes

Tackling unfairness in graph learning models is a challenging task, as t...

AutoGEL: An Automated Graph Neural Network with Explicit Link Information

Recently, Graph Neural Networks (GNNs) have gained popularity in a varie...

Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks

Heterogeneous information networks (HINs) are widely employed for descri...

Please sign up or login with your details

Forgot password? Click here to reset