
HopHop Relationaware Graph Neural Networks
Graph Neural Networks (GNNs) are widely used in graph representation lea...
read it

Reinforced Neighborhood Selection Guided MultiRelational Graph Neural Networks
Graph Neural Networks (GNNs) have been widely used for the representatio...
read it

GTEA: Representation Learning for Temporal Interaction Graphs via Edge Aggregation
We consider the problem of representation learning for temporal interact...
read it

Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection
The graphbased model can help to detect suspicious fraud online. Owing ...
read it

A joint 3D UNetGraph Neural Networkbased method for Airway Segmentation from chest CTs
We present an endtoend deep learning segmentation method by combining ...
read it

Heterogeneous Similarity Graph Neural Network on Electronic Health Records
Mining Electronic Health Records (EHRs) becomes a promising topic becaus...
read it

Heterogeneous Graph Neural Networks for Malicious Account Detection
We present, GEM, the first heterogeneous graph neural network approach f...
read it
Tree StructureAware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
While Graph Neural Network (GNN) has shown superiority in learning node representations of homogeneous graphs, leveraging GNN on heterogeneous graphs remains a challenging problem. The dominating reason is that GNN learns node representations by aggregating neighbors' information regardless of node types. Some work is proposed to alleviate such issue by exploiting relations or metapath to sample neighbors with distinct categories, then use attention mechanism to learn different importance for different categories. However, one limitation is that the learned representations for different types of nodes should own different feature spaces, while all the above work still project node representations into one feature space. Moreover, after exploring massive heterogeneous graphs, we identify a fact that multiple nodes with the same type always connect to a node with another type, which reveals the manytoone schema, a.k.a. the hierarchical tree structure. But all the above work cannot preserve such tree structure, since the exact multihop path correlation from neighbors to the target node would be erased through aggregation. Therefore, to overcome the limitations of the literature, we propose TGNN, a tree structureaware graph neural network model for graph representation learning. Specifically, the proposed TGNN consists of two modules: (1) the integrated hierarchical aggregation module and (2) the relational metric learning module. The integrated hierarchical aggregation module aims to preserve the tree structure by combining GNN with Gated Recurrent Unit to integrate the hierarchical and sequential neighborhood information on the tree structure to node representations. The relational metric learning module aims to preserve the heterogeneity by embedding each type of nodes into a typespecific space with distinct distribution based on similarity metrics.
READ FULL TEXT
Comments
There are no comments yet.