# Overcoming Catastrophic Forgetting in Graph Neural Networks with Experience Replay

arXiv: https://arxiv.org/abs/2003.09908 · HTML: https://mlsanity.com/paper/2003.09908/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2020.

## Built on by (most cited first, 5 of 5)

- [TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning](https://mlsanity.com/paper/2106.06273/) (2021)
- [Hierarchical Prototype Networks for Continual Graph Representation Learning](https://mlsanity.com/paper/2111.15422/) (2021)
- [Neuroplastic Expansion in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.07994/) (2024)
- [TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2104.08419/) (2021)
- [Incremental Evaluation and Training in Relational Deep Learning](https://mlsanity.com/paper/2608.13023/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have recently received significant research attention due to their superior performance on a variety of graph-related learning tasks. Most of the current works focus on either static or dynamic graph settings, addressing a single 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 present the Experience Replay based framework ER-GNN for CGL to alleviate 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 catastrophic forgetting issue. We propose three experience node selection strategies: mean of feature, coverage maximization, and influence maximization, to guide the process of selecting experience nodes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our ER-GNN and shed light on the incremental graph (non-Euclidean) structure learning.