Jan 1, 2022 · A new method that can learn low and high order graph information simultaneously. The method fuses structure-preserving model with random walk sampling.

Duration: 16:11
Posted: Feb 21, 2022

Graph embedding methods convert the flexible graph structure into low-dimensional representations while maintaining the graph structure information.

Graph embedding provides an effective way to encode graph nodes as continuous vector representations in a low-dimensional space. The high-order proximities ...

Abstract: In many real applications of text mining, information retrieval and natural language processing, large-scale features are frequently used, ...

Missing: Proximity | Show results with:Proximity

In contrast, structural embedding methods capture a node's structural role independent of its prox- imity to specific nodes; this independence makes embed-.

Missing: Proximity | Show results with:Proximity

Network embedding has received increasing research attention in recent years. The existing methods show that the high-order proximity plays a key role in ...

In this paper, we propose a novel attention-based graph neural network called Multi-proximity Attention Network (MAN) for network embedding that simultaneously ...