# DG-CoLearn: An Efficient Collaborative Learning Framework for Dynamic Graphs

arXiv: https://arxiv.org/abs/2605.31427 · HTML: https://mlsanity.com/paper/2605.31427/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Subgraph Federated Learning with Missing Neighbor Generation](https://mlsanity.com/paper/2106.13430/) (2021)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Overcoming Catastrophic Forgetting in Graph Neural Networks](https://mlsanity.com/paper/2012.06002/) (2020)
- [Membership Inference Attack on Graph Neural Networks](https://mlsanity.com/paper/2101.06570/) (2021)
- [Community Interaction and Conflict on the Web](https://mlsanity.com/paper/1803.03697/) (2018)
- [FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning](https://mlsanity.com/paper/2204.05562/) (2022)
- [Machine Unlearning Fails to Remove Data Poisoning Attacks](https://mlsanity.com/paper/2406.17216/) (2024)
- [TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs](https://mlsanity.com/paper/2406.09639/) (2024)
- [FedGraph: Federated Graph Learning with Intelligent Sampling](https://mlsanity.com/paper/2111.01370/) (2021)
- [Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks](https://mlsanity.com/paper/2111.08202/) (2021)
- [FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks](https://mlsanity.com/paper/2201.12433/) (2022)
- [Towards Robust Graph Incremental Learning on Evolving Graphs](https://mlsanity.com/paper/2402.12987/) (2024)
- [A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks](https://mlsanity.com/paper/2406.06186/) (2024)
- [FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs](https://mlsanity.com/paper/2208.13685/) (2022)
- [Efficient Scaling of Dynamic Graph Neural Networks](https://mlsanity.com/paper/2109.07893/) (2021)
- [Personalized Graph Federated Learning with Differential Privacy](https://mlsanity.com/paper/2306.06399/) (2023)
- [Gradients Stand-in for Defending Deep Leakage in Federated Learning](https://mlsanity.com/paper/2410.08734/) (2024)
- [Graph-Level Label-Only Membership Inference Attack against Graph Neural Networks](https://mlsanity.com/paper/2503.19070/) (2025)

## Abstract (arXiv)

Dynamic graph learning (DGL) is essential for modelling evolving graph data, but existing methods suffer from significant computational overhead due to repeated full-snapshot retraining and are not well-suited for collaborative settings with partitioned data. In realistic graph systems, cross-partition edges are unavoidable, but direct sharing of graph structure between clients may violate privacy constraints. We propose DG-CoLearn, a client-oblivious collaborative dynamic graph learning framework built on incremental graph snapshot processing, which focuses computation on graph regions affected by temporal updates while preserving historical information through temporal modelling. This incremental design is consistently applied across the entire graph processing pipeline, including a server-mediated embedding exchange mechanism to enable accurate multi-hop message passing without exposing raw cross-client structural information. Extensive experiments demonstrate that DG-CoLearn achieves up to 33.8× speedup in training time and 27.4× reduction in communication overhead, while consistently improving predictive performance on both node classification (up to 13.36% F1 improvement) and link prediction (up to 8.27% MAP improvement) tasks. These results highlight the effectiveness of DG-CoLearn in bridging efficiency, scalability, and client-to-client structural privacy in collaborative dynamic graph learning.