Lifelong Graph Learning
Abstract
Graph neural networks (GNN) are powerful models for many graphstructured tasks. Existing models often assume that the complete structure of the graph is available during training. In practice, however, graphstructured data is usually formed in a streaming fashion so that learning a graph continuously is often necessary. In this paper, we bridge GNN and lifelong learning by converting a continual graph learning problem to a regular graph learning problem so GNN can inherit the lifelong learning techniques developed for convolutional neural networks (CNN). We propose a new topology, the feature graph, which takes features as new nodes and turns nodes into independent graphs. This successfully converts the original problem of node classification to graph classification. In the experiments, we demonstrate the efficiency and effectiveness of feature graph networks (FGN) by continuously learning a sequence of classical graph datasets. We also show that FGN achieves superior performance in two applications, i.e., lifelong human action recognition with wearable devices and feature matching. To the best of our knowledge, FGN is the first method to bridge graph learning and lifelong learning via a novel graph topology. Source code is available at https://github.com/wangchen/LGL
 Publication:

arXiv eprints
 Pub Date:
 September 2020
 DOI:
 10.48550/arXiv.2009.00647
 arXiv:
 arXiv:2009.00647
 Bibcode:
 2020arXiv200900647W
 Keywords:

 Computer Science  Machine Learning;
 Statistics  Machine Learning
 EPrint:
 Accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022