# Lifelong Learning of Graph Neural Networks for Open-World Node Classification

arXiv: https://arxiv.org/abs/2006.14422 · HTML: https://mlsanity.com/paper/2006.14422/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 22 of 22)

- [Out-Of-Distribution Generalization on Graphs: A Survey](https://mlsanity.com/paper/2202.07987/) (2022)
- [Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces](https://mlsanity.com/paper/2211.17068/) (2022)
- [Graph Lifelong Learning: A Survey](https://mlsanity.com/paper/2202.10688/) (2022)
- [Continual Learning on Graphs: Challenges, Solutions, and Opportunities](https://mlsanity.com/paper/2402.11565/) (2024)
- [Continual Graph Learning: A Survey](https://mlsanity.com/paper/2301.12230/) (2023)
- [Towards Robust Graph Incremental Learning on Evolving Graphs](https://mlsanity.com/paper/2402.12987/) (2024)
- [Topology-aware Embedding Memory for Continual Learning on Expanding Networks](https://mlsanity.com/paper/2401.13200/) (2024)
- [A Comparison of Deep-Learning Methods for Analysing and Predicting Business Processes](https://mlsanity.com/paper/2102.07838/) (2021)
- [Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes](https://mlsanity.com/paper/2112.10558/) (2021)
- [Universal Graph Continual Learning](https://mlsanity.com/paper/2308.13982/) (2023)
- [Continual Learning for Smart City: A Survey](https://mlsanity.com/paper/2404.00983/) (2024)
- [BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning](https://mlsanity.com/paper/2211.14568/) (2022)
- [On the Limitation and Experience Replay for GNNs in Continual Learning](https://mlsanity.com/paper/2302.03534/) (2023)
- [Open-World Lifelong Graph Learning](https://mlsanity.com/paper/2310.12565/) (2023)
- [Graph Relation Aware Continual Learning](https://mlsanity.com/paper/2308.08259/) (2023)
- [Online Deep Learning from Doubly-Streaming Data](https://mlsanity.com/paper/2204.11793/) (2022)
- [Temporal Generalization Estimation in Evolving Graphs](https://mlsanity.com/paper/2404.04969/) (2024)
- [When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty](https://mlsanity.com/paper/2505.13989/) (2025)
- [Learning Cellular Coverage from Real Network Configurations using GNNs](https://mlsanity.com/paper/2304.10328/) (2023)
- [Learning Continually on a Sequence of Graphs -- The Dynamical System Way](https://mlsanity.com/paper/2305.12030/) (2023)
- [POWN: Prototypical Open-World Node Classification](https://mlsanity.com/paper/2406.09926/) (2024)
- [Constraint Multi-class Positive and Unlabeled Learning for Distantly Supervised Named Entity Recognition](https://mlsanity.com/paper/2504.04963/) (2025)

## Abstract (arXiv)

Graph neural networks (GNNs) have emerged as the standard method for numerous tasks on graph-structured data such as node classification. However, real-world graphs are often evolving over time and even new classes may arise. We model these challenges as an instance of lifelong learning, in which a learner faces a sequence of tasks and may take over knowledge acquired in past tasks. Such knowledge may be stored explicitly as historic data or implicitly within model parameters. In this work, we systematically analyze the influence of implicit and explicit knowledge. Therefore, we present an incremental training method for lifelong learning on graphs and introduce a new measure based on k-neighborhood time differences to address variances in the historic data. We apply our training method to five representative GNN architectures and evaluate them on three new lifelong node classification datasets. Our results show that no more than 50% of the GNN's receptive field is necessary to retain at least 95% accuracy compared to training over the complete history of the graph data. Furthermore, our experiments confirm that implicit knowledge becomes more important when fewer explicit knowledge is available.