GLMNet: Graph Learning-Matching Networks for Feature Matching

11/18/2019
by   Bo Jiang, et al.
0

Recently, graph convolutional networks (GCNs) have shown great potential for the task of graph matching. It can integrate graph node feature embedding, node-wise affinity learning and matching optimization together in a unified end-to-end model. One important aspect of graph matching is the construction of two matching graphs. However, the matching graphs we feed to existing graph convolutional matching networks are generally fixed and independent of graph matching, which thus are not guaranteed to be optimal for the graph matching task. Also, existing GCN matching method employs several general smoothing-based graph convolutional layers to generate graph node embeddings, in which extensive smoothing convolution operation may dilute the desired discriminatory information of graph nodes. To overcome these issues, we propose a novel Graph Learning-Matching Network (GLMNet) for graph matching problem. GLMNet has three main aspects. (1) It integrates graph learning into graph matching which thus adaptively learn a pair of optimal graphs that best serve graph matching task. (2) It further employs a Laplacian sharpening convolutional module to generate more discriminative node embeddings for graph matching. (3) A new constraint regularized loss is designed for GLMNet training which can encode the desired one-to-one matching constraints in matching optimization. Experiments on two benchmarks demonstrate the effectiveness of GLMNet and advantages of its main modules.

READ FULL TEXT

page 3

page 6

research
04/26/2019

Graph Optimized Convolutional Networks

Graph Convolutional Networks (GCNs) have been widely studied for graph d...
research
01/22/2018

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

Many interesting problems in machine learning are being revisited with n...
research
07/03/2020

Adaptive Graph Encoder for Attributed Graph Embedding

Attributed graph embedding, which learns vector representations from gra...
research
02/27/2021

FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding

Dynamic graphs arise in a plethora of practical scenarios such as social...
research
12/22/2021

SkipNode: On Alleviating Over-smoothing for Deep Graph Convolutional Networks

Over-smoothing is a challenging problem, which degrades the performance ...
research
11/11/2020

Rediscovering alignment relations with Graph Convolutional Networks

Knowledge graphs are concurrently published and edited in the Web of dat...
research
04/26/2022

Unified GCNs: Towards Connecting GCNs with CNNs

Graph Convolutional Networks (GCNs) have been widely demonstrated their ...

Please sign up or login with your details

Forgot password? Click here to reset