Graph Learning Network: A Structure Learning Algorithm

05/29/2019
by   Darwin Saire Pilco, et al.
0

Recently, graph neural networks (GNNs) has proved to be suitable in tasks on unstructured data. Particularly in tasks as community detection, node classification, and link prediction. However, most GNN models still operate with static relationships. We propose the Graph Learning Network (GLN), a simple yet effective process to learn node embeddings and structure prediction functions. Our model uses graph convolutions to propose expected node features, and predict the best structure based on them. We repeat these steps recursively to enhance the prediction and the embeddings.

READ FULL TEXT

page 9

page 11

research
06/11/2019

Position-aware Graph Neural Networks

Learning node embeddings that capture a node's position within the broad...
research
10/30/2020

Revisiting Graph Neural Networks for Link Prediction

Graph neural networks (GNNs) have achieved great success in recent years...
research
08/19/2023

Geometric instability of graph neural networks on large graphs

We analyse the geometric instability of embeddings produced by graph neu...
research
01/07/2022

Neighbor2vec: an efficient and effective method for Graph Embedding

Graph embedding techniques have led to significant progress in recent ye...
research
06/25/2022

SiMa: Effective and Efficient Data Silo Federation Using Graph Neural Networks

Virtually every sizable organization nowadays is building a form of a da...
research
01/28/2020

Graph Neighborhood Attentive Pooling

Network representation learning (NRL) is a powerful technique for learni...
research
03/22/2020

Continual Graph Learning

Graph Neural Networks (GNNs) have recently received significant research...

Please sign up or login with your details

Forgot password? Click here to reset