GLAM: Graph Learning by Modeling Affinity to Labeled Nodes for Graph Neural Networks

02/20/2021
by   Vijay Lingam, et al.
4

Graph Neural Networks have shown excellent performance on semi-supervised classification tasks. However, they assume access to a graph that may not be often available in practice. In the absence of any graph, constructing k-Nearest Neighbor (kNN) graphs from the given data have shown to give improvements when used with GNNs over other semi-supervised methods. This paper proposes a semi-supervised graph learning method for cases when there are no graphs available. This method learns a graph as a convex combination of the unsupervised kNN graph and a supervised label-affinity graph. The label-affinity graph directly captures all the nodes' label-affinity with the labeled nodes, i.e., how likely a node has the same label as the labeled nodes. This affinity measure contrasts with the kNN graph where the metric measures closeness in the feature space. Our experiments suggest that this approach gives close to or better performance (up to 1.5 faster (up to 70x) to train, than state-of-the-art graph learning methods. We also conduct several experiments to highlight the importance of individual components and contrast them with state-of-the-art methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/08/2021

Improving the Training of Graph Neural Networks with Consistency Regularization

Graph neural networks (GNNs) have achieved notable success in the semi-s...
research
03/16/2018

Graph Partition Neural Networks for Semi-Supervised Classification

We present graph partition neural networks (GPNN), an extension of graph...
research
03/05/2020

Factorized Graph Representations for Semi-Supervised Learning from Sparse Data

Node classification is an important problem in graph data management. It...
research
03/14/2023

GANN: Graph Alignment Neural Network for Semi-Supervised Learning

Graph neural networks (GNNs) have been widely investigated in the field ...
research
10/21/2019

Graph Construction from Data using Non Negative Kernel regression (NNK Graphs)

Data driven graph constructions are often used in various applications, ...
research
07/23/2020

Grale: Designing Networks for Graph Learning

How can we find the right graph for semi-supervised learning? In real wo...
research
06/06/2022

Interpolation-based Correlation Reduction Network for Semi-Supervised Graph Learning

Graph Neural Networks (GNNs) have achieved promising performance in semi...

Please sign up or login with your details

Forgot password? Click here to reset