Lifelong Graph Learning

By Chen Wang, Yuheng Qiu, Sebastian A. Scherer. 2020

64 citations recorded by the source corpus.

Graph neural networks (GNN) are powerful models for many graph-structured tasks. Existing models often assume that the complete structure of the graph is available during training. In practice, however, graph-structured 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/wang-chen/LGL.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Graph Learning, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hang Su
2. Jun Zhu
3. Jun Liu
4. Liyuan Wang
5. Xingxing Zhang
6. Hossein Rahmani
7. Dacheng Tao
8. Li Xu

In Computer Vision and Pattern Recognition

1. Hossein Rahmani
2. Jun Liu
3. Hang Su
4. Jun Zhu
5. Liyuan Wang
6. Xingxing Zhang
7. Dacheng Tao
8. Li Xu

In Graph Learning

1. Jun Liu
2. Jun Zhu
3. Dacheng Tao
4. Dongjin Song
5. Xikun Zhang

In Meta & Continual Learning

1. Xingxing Zhang
2. Liyuan Wang
3. Hang Su
4. Jun Zhu
5. Jun Liu
6. Hossein Rahmani
7. Dacheng Tao
8. Li Xu

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “We present only some representative applications in the above two sections, with other more specialized and cross-cutting scenarios to be explored, such as robotics [25], [76], [243], graph learning [219], [423], [496], bioimaging [497], etc.”
• Recent Advances of Continual Learning in Computer Vision: An Overview (2021, positive): “Specifically, FGN designs a new graph topology through which the continual growth of a graph can be regarded as the continual increase of training samples, and typical convolutional-neural-network-based continual learning techniques can thus be used for graph learning.”
• CGLB: Benchmark Tasks for Continual Graph Learning (2022, background): “Recently, continual graph learning (CGL) is attracting significant amount of attention from the community due to its practical importance [47, 55, 10, 27, 1, 7, 46].”