GPS: A Policy-driven Sampling Approach for Graph Representation Learning

by   Tiehua Zhang, et al.
Macquarie University

Graph representation learning has drawn increasing attention in recent years, especially for learning the low dimensional embedding at both node and graph level for classification and recommendations tasks. To enable learning the representation on the large-scale graph data in the real world, numerous research has focused on developing different sampling strategies to facilitate the training process. Herein, we propose an adaptive Graph Policy-driven Sampling model (GPS), where the influence of each node in the local neighborhood is realized through the adaptive correlation calculation. Specifically, the selections of the neighbors are guided by an adaptive policy algorithm, contributing directly to the message aggregation, node embedding updating, and graph level readout steps. We then conduct comprehensive experiments against baseline methods on graph classification tasks from various perspectives. Our proposed model outperforms the existing ones by 3 several vital benchmarks, achieving state-of-the-art performance in real-world datasets.


page 1

page 2

page 3

page 4


A Representation Learning Framework for Property Graphs

Representation learning on graphs, also called graph embedding, has demo...

Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization

Recent years have seen a rise in the development of representational lea...

Graph Representation Learning: A Survey

Research on graph representation learning has received a lot of attentio...

Towards Relation-centered Pooling and Convolution for Heterogeneous Graph Learning Networks

Heterogeneous graph neural network has unleashed great potential on grap...

Learning Robust Representations with Graph Denoising Policy Network

Graph representation learning, aiming to learn low-dimensional represent...

Hyperparameter-free and Explainable Whole Graph Embedding

Many real-world complex systems can be described as graphs. For a large-...

Small World Model for scaling up prediction result based on SEIR model

Data-driven epidemic simulation helps better policymaking. Compared with...

Please sign up or login with your details

Forgot password? Click here to reset