Online Continual Graph Learning
Not on the map. Why?
Abstract (arXiv)
Continual Learning (CL) aims to incrementally acquire new knowledge while mitigating catastrophic forgetting. Within this setting, Online Continual Learning (OCL) focuses on updating models promptly and incrementally from single or small batches of observations from a data stream. Extending OCL to graph-structured data is crucial, as many real-world networks evolve over time and require timely, online predictions. However, existing continual or streaming graph learning methods typically assume access to entire graph snapshots or multiple passes over tasks, violating the efficiency constraints of the online setting. To address this gap, we introduce the Online Continual Graph Learning (OCGL) setting, which formalizes node-level continual learning on evolving graphs under strict memory and computational budgets. OCGL defines how a model incrementally processes a stream of node-level information while maintaining anytime inference and respecting resource constraints. We further establish a comprehensive benchmark comprising seven datasets and nine CL strategies, suitably adapted to the OCGL setting, enabling a standardized evaluation setup. Finally, we present a minimalistic yet competitive baseline for OCGL, inspired by our benchmarking results, that achieves strong empirical performance with high efficiency.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 52 of its 76 references that are in the map. First posted on arXiv 5 Aug 2025.
Builds on
52 of 76 references.
References · 52
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2015Distilling the Knowledge in a Neural Networkcited by 10,324
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2016Learning without Forgettingcited by 2,496
- 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2017Gradient Episodic Memory for Continual Learningcited by 1,898
- 2019Simplifying Graph Convolutional Networkscited by 1,477
38 more
- 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
- 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
- 2018Experience Replay for Continual Learningcited by 1,095
- 2018Efficient Lifelong Learning with A-GEMcited by 1,058
- 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
- 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
- 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
- 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
- 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 449
- 2019Online Continual Learning with Maximally Interfered Retrievalcited by 379
- 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 364
- 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
- 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
- 2019Representation Learning for Dynamic Graphs: A Surveycited by 265
- 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
- 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 219
- 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
- 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 138
- 2018Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilizationcited by 104
- 2020Overcoming Catastrophic Forgetting in Graph Neural Networkscited by 95
- 2021Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inferencecited by 67
- 2020Streaming Graph Neural Networks via Continual Learningcited by 64
- 2021Wide Neural Networks Forget Less Catastrophicallycited by 64
- 2020Challenges in Benchmarking Stream Learning Algorithms with Real-world Datacited by 59
- 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 52
- 2021TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learningcited by 42
- 2023Taming Local Effects in Graph-based Spatiotemporal Forecastingcited by 37
- 2022Graph Lifelong Learning: A Surveycited by 30
- 2023Graph Deep Learning for Time Series Forecastingcited by 26
- 2023A Comprehensive Empirical Evaluation on Online Continual Learningcited by 24
- 2024Continual Learning on Graphs: Challenges, Solutions, and Opportunitiescited by 21
- 2023Deep learning for dynamic graphs: models and benchmarkscited by 19
- 2023Continual Graph Learning: A Surveycited by 18
- 2024Towards Robust Graph Incremental Learning on Evolving Graphscited by 18
- 2020Online Continual Learning on Sequencescited by 14
- 2024Topology-aware Embedding Memory for Continual Learning on Expanding Networkscited by 14
- 2024Continual Learning on Graphs: A Surveycited by 12
- 2023Universal Graph Continual Learningcited by 9
50 most cited of 52 All 52 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.