Position-Aware Subgraph Neural Networks with Data-Efficient Learning

11/01/2022
by   Chang Liu, et al.
0

Data-efficient learning on graphs (GEL) is essential in real-world applications. Existing GEL methods focus on learning useful representations for nodes, edges, or entire graphs with “small” labeled data. But the problem of data-efficient learning for subgraph prediction has not been explored. The challenges of this problem lie in the following aspects: 1) It is crucial for subgraphs to learn positional features to acquire structural information in the base graph in which they exist. Although the existing subgraph neural network method is capable of learning disentangled position encodings, the overall computational complexity is very high. 2) Prevailing graph augmentation methods for GEL, including rule-based, sample-based, adaptive, and automated methods, are not suitable for augmenting subgraphs because a subgraph contains fewer nodes but richer information such as position, neighbor, and structure. Subgraph augmentation is more susceptible to undesirable perturbations. 3) Only a small number of nodes in the base graph are contained in subgraphs, which leads to a potential “bias” problem that the subgraph representation learning is dominated by these “hot” nodes. By contrast, the remaining nodes fail to be fully learned, which reduces the generalization ability of subgraph representation learning. In this paper, we aim to address the challenges above and propose a Position-Aware Data-Efficient Learning framework for subgraph neural networks called PADEL. Specifically, we propose a novel node position encoding method that is anchor-free, and design a new generative subgraph augmentation method based on a diffused variational subgraph autoencoder, and we propose exploratory and exploitable views for subgraph contrastive learning. Extensive experiment results on three real-world datasets show the superiority of our proposed method over state-of-the-art baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/09/2022

Efficient Representation Learning of Subgraphs by Subgraph-To-Node Translation

A subgraph is a data structure that can represent various real-world pro...
research
09/01/2022

Models and Benchmarks for Representation Learning of Partially Observed Subgraphs

Subgraphs are rich substructures in graphs, and their nodes and edges ca...
research
06/18/2020

Subgraph Neural Networks

Deep learning methods for graphs achieve remarkable performance on many ...
research
04/21/2023

Learn to Cluster Faces with Better Subgraphs

Face clustering can provide pseudo-labels to the massive unlabeled face ...
research
04/24/2019

Learning big Gaussian Bayesian networks: partition, estimation, and fusion

Structure learning of Bayesian networks has always been a challenging pr...
research
09/07/2023

ProvG-Searcher: A Graph Representation Learning Approach for Efficient Provenance Graph Search

We present ProvG-Searcher, a novel approach for detecting known APT beha...
research
01/28/2013

Discriminative Feature Selection for Uncertain Graph Classification

Mining discriminative features for graph data has attracted much attenti...

Please sign up or login with your details

Forgot password? Click here to reset