Graph Neural Network with Automorphic Equivalence Filters

11/09/2020
by   Fengli Xu, et al.
0

Graph neural network (GNN) has recently been established as an effective representation learning framework on graph data. However, the popular message passing models rely on local permutation invariant aggregate functions, which gives rise to the concerns about their representational power. Here, we introduce the concept of automorphic equivalence to theoretically analyze GNN's expressiveness in differentiating node's structural role. We show that the existing message passing GNNs have limitations in learning expressive representations. Moreover, we design a novel GNN class that leverages learnable automorphic equivalence filters to explicitly differentiate the structural roles of each node's neighbors, and uses a squeeze-and-excitation module to fuse various structural information. We theoretically prove that the proposed model is expressive in terms of generating distinct representations for nodes with different structural feature. Besides, we empirically validate our model on eight real-world graph data, including social network, e-commerce co-purchase network and citation network, and show that it consistently outperforms strong baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/19/2022

EDEN: A Plug-in Equivariant Distance Encoding to Beyond the 1-WL Test

The message-passing scheme is the core of graph representation learning....
research
02/09/2022

Graph Neural Network for Cell Tracking in Microscopy Videos

We present a novel graph neural network (GNN) approach for cell tracking...
research
11/27/2022

Beyond 1-WL with Local Ego-Network Encodings

Identifying similar network structures is key to capture graph isomorphi...
research
12/21/2022

Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Neural Networks

The core operation of current Graph Neural Networks (GNNs) is the aggreg...
research
03/11/2022

Graph Summarization with Graph Neural Networks

The goal of graph summarization is to represent large graphs in a struct...
research
09/02/2022

A Class-Aware Representation Refinement Framework for Graph Classification

Graph Neural Networks (GNNs) are widely used for graph representation le...
research
08/04/2020

Graph Neural Networks with Low-rank Learnable Local Filters

For the classification of graph data consisting of features sampled on a...

Please sign up or login with your details

Forgot password? Click here to reset