A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness

Summary: Systematic benchmark of spectral GNNs: categorizes 35 models into 27 spectral filters and implements them in a unified spectral-oriented framework that scales to million-node graphs. Cross-scale evaluations expose nontrivial efficiency/memory/effectiveness trade-offs and give practical deployment guidelines. (summarized by gpt-5-mini on Feb 11 2026)

Paper ID: he168dd28269a8e0a
Venue: SIGMOD
Year: 2026
Pagerank: 4.9769913e-05
Overall Rank: 10,531 | 29.22%
DOI: 10.1145/3749156
PDF: Download (CC BY 4.0)

Incoming Non-self Citations Over Time

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

Authors

1. Ningyi Liao (Nanyang Technological University)
2. Haoyu Liu (Nanyang Technological University)
3. Zulun Zhu (Nanyang Technological University)
4. Siqiang Luo (Nanyang Technological University)
5. Laks V.S. Lakshmanan (University of British Columbia)

BibTeX Citation

@inproceedings{liao_sigmod26,
        title = {{A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness}},
        author = {Liao, Ningyi and Liu, Haoyu and Zhu, Zulun and Luo, Siqiang and Lakshmanan, Laks V.S.},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3749156},
        url = {https://dl.acm.org/doi/10.1145/3749156},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 17 of 17 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
211	AliGraph: A Comprehensive Graph Neural Network Platform	2019	VLDB	0.00024805216
239	The Ubiquity of Large Graphs and Surprising Challenges of Graph Processing	2018	VLDB	0.00023499655
1,033	AGL: A Scalable System for Industrial-purpose Graph Machine Learning	2020	VLDB	0.00012391866
1,772	ByteGNN: Efficient Graph Neural Network Training at Large Scale	2022	VLDB	9.6746467e-05
2,440	Accelerating Large Scale Real-Time GNN Inference using Channel Pruning	2021	VLDB	8.461216e-05
2,521	HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework	2022	VLDB	8.3481558e-05
2,864	Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching	2022	VLDB	7.9264262e-05
4,624	Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning	2022	VLDB	6.4952114e-05
4,855	NeutronOrch: Rethinking Sample-based GNN Training under CPU-GPU Heterogeneous Environments	2024	VLDB	6.377545e-05
4,899	Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective	2024	VLDB	6.3628105e-05
5,127	SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization	2022	VLDB	6.259487e-05
5,346	FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training	2024	VLDB	6.1702451e-05
6,110	GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs	2024	VLDB	5.8817721e-05
6,673	Efficient Training of Graph Neural Networks on Large Graphs	2024	VLDB	5.7120259e-05
7,511	ADGNN: Towards Scalable GNN Training with Aggregation-Difference Aware Sampling	2023	SIGMOD	5.5044293e-05
8,630	D3-GNN: Dynamic Distributed Dataflow for Streaming Graph Neural Networks	2024	VLDB	5.298422e-05
10,269	BIRD: Efficient Approximation of Bidirectional Hidden Personalized PageRank	2024	VLDB	5.0480912e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	1,772	ByteGNN: Efficient Graph Neural Network Training at Large Scale	2022	VLDB
2	5,346	FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training	2024	VLDB
3	10,716	Efficient GNN Training on Giant Graphs with Collective Batching and Scheduling	2026	VLDB
4	10,263	Graph Neural Network Training Systems: A Performance Comparison of Full-Graph and Mini-Batch	2025	VLDB
5	8,363	Demystifying Graph Sparsification Algorithms in Graph Properties Preservation	2024	VLDB
6	2,440	Accelerating Large Scale Real-Time GNN Inference using Channel Pruning	2021	VLDB
7	2,598	Scalable and Efficient Full-Graph GNN Training for Large Graphs	2023	SIGMOD
8	11,465	Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours	2025	VLDB
9	4,899	Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective	2024	VLDB
10	6,673	Efficient Training of Graph Neural Networks on Large Graphs	2024	VLDB