IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification

07/22/2019
by   Lin Meng, et al.
21

Deep learning models have achieved huge success in numerous fields, such as computer vision and natural language processing. However, unlike such fields, it is hard to apply traditional deep learning models on the graph data due to the `node-orderless' property. Normally, we use an adjacent matrix to represent a graph, but an artificial and random node-order will be cast on the graphs, which renders the performance of deep models extremely erratic and not robust. In order to eliminate the unnecessary node-order constraint, in this paper, we propose a novel model named Isomorphic Neural Network (IsoNN), which learns the graph representation by extracting its isomorphic features via the graph matching between input graph and templates. IsoNN has two main components: graph isomorphic feature extraction component and classification component. The graph isomorphic feature extraction component utilizes a set of subgraph templates as the kernel variables to learn the possible subgraph patterns existing in the input graph and then computes the isomorphic features. A set of permutation matrices is used in the component to break the node-order brought by the matrix representation. To further lower down the computational cost and identify the optimal subgraph patterns, IsoNN adopts two min-pooling layers to find the optimal matching. The first min-pooling layer aims at finding the best permutation matrix, whereas the second one is used to determine the best templates for the input graph data. Three fully-connected layers are used as the classification component in IsoNN. Extensive experiments are conducted on real-world datasets, and the experimental results demonstrate both the effectiveness and efficiency of IsoNN.

READ FULL TEXT
research
06/19/2020

Graph Pooling with Node Proximity for Hierarchical Representation Learning

Graph neural networks have attracted wide attentions to enable represent...
research
05/08/2019

PiNet: A Permutation Invariant Graph Neural Network for Graph Classification

We propose an end-to-end deep learning learning model for graph classifi...
research
10/06/2022

Enhancing Mixup-Based Graph Learning for Language Processing via Hybrid Pooling

Graph neural networks (GNNs) have recently been popular in natural langu...
research
04/17/2018

Network Signatures from Image Representation of Adjacency Matrices: Deep/Transfer Learning for Subgraph Classification

We propose a novel subgraph image representation for classification of n...
research
10/08/2022

Towards Real-Time Temporal Graph Learning

In recent years, graph representation learning has gained significant po...
research
06/06/2022

Graph Rationalization with Environment-based Augmentations

Rationale is defined as a subset of input features that best explains or...
research
12/18/2021

FlowPool: Pooling Graph Representations with Wasserstein Gradient Flows

In several machine learning tasks for graph structured data, the graphs ...

Please sign up or login with your details

Forgot password? Click here to reset