Continual Graph Learning
By Fan Zhou, Chengtai Cao, Ting Zhong, Kunpeng Zhang, Goce Trajcevski, Ji Geng. 2020
10 citations recorded by the source corpus.
Graph Neural Networks (GNNs) have recently received significant research attention due to their prominent performance on a variety of graph-related learning tasks. Most of the existing works focus on either static or dynamic graph settings, addressing a particular task, e.g., node/graph classification, link prediction. In this work, we investigate the question: can GNNs be applied to continuously learning a sequence of tasks? Towards that, we explore the Continual Graph Learning (CGL) paradigm and we present the Experience Replay based framework ER-GNN for CGL to address the catastrophic forgetting problem in existing GNNs. ER-GNN stores knowledge from previous tasks as experiences and replays them when learning new tasks to mitigate the forgetting issue. We propose three experience node selection strategies: mean of features, coverage maximization and influence maximization, to guide the process of selecting experience nodes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of ER-GNN and shed light on the incremental (non-Euclidean) graph structure learning.
Subfields: Artificial Intelligence
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
- Mark J. Coates
- Yingxue Zhang
- Wei Guo
- Yishi Xu
- Chen Wang
- Ruiming Tang
- Yuheng Qiu
- Sebastian A. Scherer
Citations in the corpus
- Lifelong Graph Learning (2020, methodology): “Several exemplar selection methods are tested in [31] for graph networks, while it has a different problem formulation with this paper.”
- GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems (2020, background): “Other recent attempts that use knowledge distillation for GNN models [27, 33] are not directly suitable for recommendation scenarios.”