Decoupled Graph Neural Networks for Large Dynamic Graphs

Summary: Decouples graph propagation from downstream prediction, unifying efficient handling of continuous- and discrete-time graph streams while permitting arbitrary sequence models. Demonstrates state-of-the-art results and scalability to billion-edge, hundred-million-node graphs. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 13262
Venue: VLDB
Year: 2023
Pagerank: 6.4133375e-05
Overall Rank: 4,980 | 65.84%
DOI: 10.14778/3595851.3598595

Incoming Non-self Citations Over Time

Authors

1. Yanping Zheng (Renmin University of China)
2. Zhewei Wei (Renmin University of China)
3. Jiajun Liu (Commonwealth Scientific and Industrial Research Organisation)

BibTeX Citation

@article{zheng_vldb23,
        title = {{Decoupled Graph Neural Networks for Large Dynamic Graphs}},
        author = {Zheng, Yanping and Wei, Zhewei and Liu, Jiajun},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {9},
        pages = {2239--2247},
        doi = {10.14778/3595851.3598595},
        url = {https://doi.org/10.14778/3595851.3598595},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 8 of 8 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,695	GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs	2024	VLDB	5.7990641e-05
8,503	Fight Fire with Fire: Towards Robust Graph Neural Networks on Dynamic Graphs via Actively Defense	2024	VLDB	5.4132367e-05
8,504	Enabling Window-Based Monotonic Graph Analytics with Reusable Transitional Results for Pattern-Consistent Queries	2024	VLDB	5.4132367e-05
9,546	NeutronTP: Load-Balanced Distributed Full-Graph GNN Training with Tensor Parallelism	2025	VLDB	5.2528121e-05
10,521	Efficient GNN Training on Giant Graphs with Collective Batching and Scheduling	2026	VLDB	5.093636e-05
10,620	Understanding Evolving Graph Structures for Large Discrete-Time Dynamic Graph Representation	2026	VLDB	5.093636e-05
10,835	NeutronTask: Scalable and Efficient Multi-GPU GNN Training with Task Parallelism	2025	VLDB	5.093636e-05
10,922	When Speed meets Accuracy: an Efficient and Effective Graph Model for Temporal Link Prediction	2025	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 2 of 2 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
920	APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding	2021	SIGMOD	0.00013209734
1,409	TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs	2022	VLDB	0.00010854808

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,891	DGC: Training Dynamic Graphs with Spatio-Temporal Non-Uniformity using Graph Partitioning by Chunks	2023	SIGMOD
2	4,171	Accelerating Dynamic Graph Analytics on GPUs	2018	VLDB
3	1,409	TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs	2022	VLDB
4	10,620	Understanding Evolving Graph Structures for Large Discrete-Time Dynamic Graph Representation	2026	VLDB
5	2,640	Scalable and Efficient Full-Graph GNN Training for Large Graphs	2023	SIGMOD
6	6,730	SIMPLE: Efficient Temporal Graph Neural Network Training at Scale with Dynamic Data Placement	2024	SIGMOD
7	8,454	D3-GNN: Dynamic Distributed Dataflow for Streaming Graph Neural Networks	2024	VLDB
8	11,110	Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours	2025	VLDB
9	6,630	Efficient Training of Graph Neural Networks on Large Graphs	2024	VLDB
10	6,261	EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs	2023	SIGMOD