mlsanityData to 7 Oct 2026

Graph Lifelong Learning: A Survey

arXiv 2202.10688 ↗First posted 22 Feb 2022cs.LG cs.AIcited by 30

Not on the map. Why?

Abstract (arXiv)

Graph learning is a popular approach for performing machine learning on graph-structured data. It has revolutionized the machine learning ability to model graph data to address downstream tasks. Its application is wide due to the availability of graph data ranging from all types of networks to information systems. Most graph learning methods assume that the graph is static and its complete structure is known during training. This limits their applicability since they cannot be applied to problems where the underlying graph grows over time and/or new tasks emerge incrementally. Such applications require a lifelong learning approach that can learn the graph continuously and accommodate new information whilst retaining previously learned knowledge. Lifelong learning methods that enable continuous learning in regular domains like images and text cannot be directly applied to continuously evolving graph data, due to its irregular structure. As a result, graph lifelong learning is gaining attention from the research community. This survey paper provides a comprehensive overview of recent advancements in graph lifelong learning, including the categorization of existing methods, and the discussions of potential applications and open research problems.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 87 of its 137 references that are in the map. First posted on arXiv 22 Feb 2022.

Builds on

87 of 137 references.

References · 87

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  8. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  9. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  10. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  11. 2016Learning without Forgettingcited by 2,465
  12. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
38 more
  1. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  2. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  3. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  4. 2016Variational Graph Auto-Encoderscited by 1,373
  5. 2016Progressive Neural Networkscited by 1,332
  6. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  7. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  8. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  9. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  11. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  12. 2017A Survey on Multi-Task Learningcited by 838
  13. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  14. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  15. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  16. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  17. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  18. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  19. 2020Benchmarking Graph Neural Networkscited by 672
  20. 2020Long-tail learning via logit adjustmentcited by 605
  21. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  22. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  23. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  24. 2018Deep Learning on Graphs: A Surveycited by 393
  25. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  26. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  27. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  28. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
  29. 2019Representation Learning for Dynamic Graphs: A Surveycited by 260
  30. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  31. 2018Graph networks as learnable physics engines for inference and controlcited by 242
  32. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  33. 2015Structural-RNN: Deep Learning on Spatio-Temporal Graphscited by 234
  34. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  35. 2018Online Learning: A Comprehensive Surveycited by 203
  36. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  37. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 164
  38. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 158

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 7; 2024: 12; 2025: 6.

30 papers.

Sort:

  1. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  2. 2022Self-Supervised Continual Graph Learning in Adaptive Riemannian Spacescited by 32
  3. 2024Graph Transformers: A Surveycited by 32
  4. 2024Graph Condensation: A Surveycited by 23
  5. 2024Continual Learning on Graphs: Challenges, Solutions, and Opportunitiescited by 20
  6. 2023Continual Graph Learning: A Surveycited by 17
  7. 2024Graph Learning under Distribution Shifts: A Comprehensive Survey on Domain Adaptation, Out-of-distribution, and Continual Learningcited by 17
  8. 2024Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approachcited by 12
  9. 2025Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learningcited by 12
  10. 2023Universal Graph Continual Learningcited by 9
  11. 2024Continual Learning for Smart City: A Surveycited by 9
  12. 2022BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learningcited by 8
18 more
  1. 2022SS-GNN: A Simple-Structured Graph Neural Network for Affinity Predictioncited by 7
  2. 2023On the Limitation and Experience Replay for GNNs in Continual Learningcited by 7
  3. 2023Open-World Lifelong Graph Learningcited by 5
  4. 2024Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networkscited by 4
  5. 2022Lifelong Learning for Neural powered Mixed Integer Programmingcited by 2
  6. 2024Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognitioncited by 2
  7. 2025Online Continual Graph Learningcited by 2
  8. 2023Balanced Graph Structure Information for Brain Disease Detectioncited by 1
  9. 2022tegdet: An extensible Python Library for Anomaly Detection using Time-Evolving Graphscited by 0
  10. 2023Learning Continually on a Sequence of Graphs -- The Dynamical System Waycited by 0
  11. 2024LingML: Linguistic-Informed Machine Learning for Enhanced Fake News Detectioncited by 0
  12. 2024Deep-Graph-Sprints: Accelerated Representation Learning in Continuous-Time Dynamic Graphscited by 0
  13. 2024E-CGL: An Efficient Continual Graph Learnercited by 0
  14. 2024Slicing Input Features to Accelerate Deep Learning: A Case Study with Graph Neural Networkscited by 0
  15. 2025Advances in Continual Graph Learning for Anti-Money Laundering Systems: A Comprehensive Reviewcited by 0
  16. 2025MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCILcited by 0
  17. 2025Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detectioncited by 0
  18. 2025The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learningcited by 0