Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours

Summary: Directed 10k+ GPU-hour design-space search using a unified, optimized TGNN codebase to remove implementation/benchmarking confounds and fairly compare modules. Finds modern neighbor sampling + attention outperform uniform/MLP‑Mixer; static node memory competitive and memory choice should follow dataset repetition patterns. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 14439
Venue: VLDB
Year: 2025
Pagerank: 5.093636e-05
Overall Rank: 11,110 | 23.78%
DOI: 10.14778/3717755.3717758

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Yuxin Yang (University of Southern California)
2. Hongkuan Zhou (University of Southern California)
3. Rajgopal Kannan (U.S. Army Combat Capabilities Development Command Army Research Office)
4. Viktor Prasanna (University of Southern California)

BibTeX Citation

@article{yang_vldb25,
        title = {{Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours}},
        author = {Yang, Yuxin and Zhou, Hongkuan and Kannan, Rajgopal and Prasanna, Viktor},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {4},
        pages = {956--969},
        doi = {10.14778/3717755.3717758},
        url = {https://doi.org/10.14778/3717755.3717758},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 6 of 6 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
3,210	Zebra: When Temporal Graph Neural Networks Meet Temporal Personalized PageRank	2023	VLDB	7.6352864e-05
3,634	Orca: Scalable Temporal Graph Neural Network Training with Theoretical Guarantees	2023	SIGMOD	7.2358691e-05
4,549	Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning	2022	VLDB	6.6364104e-05
5,205	ETC: Efficient Training of Temporal Graph Neural Networks over Large-scale Dynamic Graphs	2024	VLDB	6.318626e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,309	A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness	2026	SIGMOD
2	6,630	Efficient Training of Graph Neural Networks on Large Graphs	2024	VLDB
3	9,349	Temporal SIR-GN: Efficient and Effective Structural Representation Learning for Temporal Graphs	2023	VLDB
4	10,620	Understanding Evolving Graph Structures for Large Discrete-Time Dynamic Graph Representation	2026	VLDB
5	5,316	Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective	2024	VLDB
6	10,907	Effective and Efficient Distributed Temporal Graph Learning through Hotspot Memory Sharing	2025	VLDB
7	5,205	ETC: Efficient Training of Temporal Graph Neural Networks over Large-scale Dynamic Graphs	2024	VLDB
8	4,980	Decoupled Graph Neural Networks for Large Dynamic Graphs	2023	VLDB
9	6,730	SIMPLE: Efficient Temporal Graph Neural Network Training at Scale with Dynamic Data Placement	2024	SIGMOD
10	1,409	TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs	2022	VLDB