# DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning

arXiv: https://arxiv.org/abs/2402.13711 · HTML: https://mlsanity.com/paper/2402.13711/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 30 of 32)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings](https://mlsanity.com/paper/2006.13009/) (2020)
- [NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification](https://mlsanity.com/paper/2306.08385/) (2023)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [Scalable and Order-robust Continual Learning with Additive Parameter Decomposition](https://mlsanity.com/paper/1902.09432/) (2019)
- [Online Coreset Selection for Rehearsal-based Continual Learning](https://mlsanity.com/paper/2106.01085/) (2021)
- [SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks](https://mlsanity.com/paper/2102.05034/) (2021)
- [Overcoming Catastrophic Forgetting in Graph Neural Networks](https://mlsanity.com/paper/2012.06002/) (2020)
- [Representational Continuity for Unsupervised Continual Learning](https://mlsanity.com/paper/2110.06976/) (2021)
- [A Survey on Graph Structure Learning: Progress and Opportunities](https://mlsanity.com/paper/2103.03036/) (2021)
- [Streaming Graph Neural Networks via Continual Learning](https://mlsanity.com/paper/2009.10951/) (2020)
- [Dynamically Expandable Graph Convolution for Streaming Recommendation](https://mlsanity.com/paper/2303.11700/) (2023)
- [Reinforced Continual Learning for Graphs](https://mlsanity.com/paper/2209.01556/) (2022)
- [Self-Supervised Graph Structure Refinement for Graph Neural Networks](https://mlsanity.com/paper/2211.06545/) (2022)
- [Towards Robust Graph Incremental Learning on Evolving Graphs](https://mlsanity.com/paper/2402.12987/) (2024)
- [Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification](https://mlsanity.com/paper/2103.11750/) (2021)
- [RDGSL: Dynamic Graph Representation Learning with Structure Learning](https://mlsanity.com/paper/2309.02025/) (2023)
- [Homophily-enhanced Structure Learning for Graph Clustering](https://mlsanity.com/paper/2308.05309/) (2023)
- [Self-organization Preserved Graph Structure Learning with Principle of Relevant Information](https://mlsanity.com/paper/2301.00015/) (2022)
- [Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification](https://mlsanity.com/paper/2302.09755/) (2023)

## Built on by (most cited first, 14 of 14)

- [Recent Advances of Multimodal Continual Learning: A Comprehensive Survey](https://mlsanity.com/paper/2410.05352/) (2024)
- [Federated Continual Graph Learning](https://mlsanity.com/paper/2411.18919/) (2024)
- [Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach](https://mlsanity.com/paper/2501.11823/) (2025)
- [Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding](https://mlsanity.com/paper/2508.02426/) (2025)
- [When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty](https://mlsanity.com/paper/2505.13989/) (2025)
- [HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning](https://mlsanity.com/paper/2505.17458/) (2025)
- [E-CGL: An Efficient Continual Graph Learner](https://mlsanity.com/paper/2408.09350/) (2024)
- [Condensation-Concatenation Framework for Dynamic Graph Continual Learning](https://mlsanity.com/paper/2512.11317/) (2025)
- [When Classes Evolve: A Benchmark and Framework for Stage-Aware Class-Incremental Learning](https://mlsanity.com/paper/2602.00573/) (2026)
- [UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning](https://mlsanity.com/paper/2605.09862/) (2026)
- [Informative Graph Structure Learning](https://mlsanity.com/paper/2605.16809/) (2026)
- [UNIT: Unleash Large Language Models Potential for Graph Continual Learning](https://mlsanity.com/paper/2607.10159/) (2026)
- [CA-DGCL: Dynamic Graph Continual Learning via Condensation and Attachment](https://mlsanity.com/paper/2607.11112/) (2026)
- [DSETA: A Dual-Stage Continual Learning Framework for Travel Time Prediction in Dynamic Traffic Environments](https://mlsanity.com/paper/2608.00402/) (2026)

## Abstract (arXiv)

We investigate the replay buffer in rehearsal-based approaches for graph continual learning (GCL) methods. Existing rehearsal-based GCL methods select the most representative nodes for each class and store them in a replay buffer for later use in training subsequent tasks. However, we discovered that considering only the class representativeness of each replayed node makes the replayed nodes to be concentrated around the center of each class, incurring a potential risk of overfitting to nodes residing in those regions, which aggravates catastrophic forgetting. Moreover, as the rehearsal-based approach heavily relies on a few replayed nodes to retain knowledge obtained from previous tasks, involving the replayed nodes that have irrelevant neighbors in the model training may have a significant detrimental impact on model performance. In this paper, we propose a GCL model named DSLR, specifically, we devise a coverage-based diversity (CD) approach to consider both the class representativeness and the diversity within each class of the replayed nodes. Moreover, we adopt graph structure learning (GSL) to ensure that the replayed nodes are connected to truly informative neighbors. Extensive experimental results demonstrate the effectiveness and efficiency of DSLR. Our source code is available at https://github.com/seungyoon-Choi/DSLR_official.