Fight Fire with Fire: Towards Robust Graph Neural Networks on Dynamic Graphs via Actively Defense

Summary: ADGNN: active defense for dynamic graphs that injects optimizable guardian nodes to disrupt attackers' node-injection strategies. Optimizes an active-defense objective via a gradient-based algorithm with two speedups, outperforming passive pattern-specific defenders and augmenting existing GNN defenses. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: h26c346c11868ae23
Venue: VLDB
Year: 2024
Pagerank: 5.2892731e-05
Overall Rank: 8,678 | 41.68%
DOI: 10.14778/3659437.3659457
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Haoyang Li (Hong Kong University of Science and Technology)
2. Shimin Di (Hong Kong University of Science and Technology)
3. Calvin Hong Yi Li (The Cigna Group)
4. Lei Chen (Hong Kong University of Science and Technology)
5. Xiaofang Zhou (Hong Kong University of Science and Technology)

BibTeX Citation

@article{li_vldb24,
        title = {{Fight Fire with Fire: Towards Robust Graph Neural Networks on Dynamic Graphs via Actively Defense}},
        author = {Li, Haoyang and Di, Shimin and Li, Calvin Hong Yi and Chen, Lei and Zhou, Xiaofang},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {8},
        pages = {2050--2063},
        doi = {10.14778/3659437.3659457},
        url = {https://doi.org/10.14778/3659437.3659457},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,716	Efficient GNN Training on Giant Graphs with Collective Batching and Scheduling	2026	VLDB	4.9769913e-05
11,075	Understanding Evolving Graph Structures for Large Discrete-Time Dynamic Graph Representation	2026	VLDB	4.9769913e-05
11,191	Data Enhancement for Binary Classification of Relational Data	2025	SIGMOD	4.9769913e-05

Outgoing Citations (Sorted by Pagerank)

Showing 24 of 24 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
881	APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding	2021	SIGMOD	0.00013272536
1,772	ByteGNN: Efficient Graph Neural Network Training at Large Scale	2022	VLDB	9.6746467e-05
2,442	ICS-GNN: Lightweight Interactive Community Search via Graph Neural Network	2021	VLDB	8.4581267e-05
2,941	Query Driven-Graph Neural Networks for Community Search: From Non-Attributed, Attributed, to Interactive Attributed	2022	VLDB	7.8297732e-05
3,018	Zebra: When Temporal Graph Neural Networks Meet Temporal Personalized PageRank	2023	VLDB	7.743467e-05
3,399	Orca: Scalable Temporal Graph Neural Network Training with Theoretical Guarantees	2023	SIGMOD	7.3314353e-05
3,451	Building Enclave-Native Storage Engines for Practical Encrypted Databases	2021	VLDB	7.288241e-05
3,753	G3: When Graph Neural Networks Meet Parallel Graph Processing Systems on GPUs	2020	VLDB	7.0483642e-05
3,899	Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization	2021	VLDB	6.9325861e-05
3,915	Scaling Attributed Network Embedding to Massive Graphs	2021	VLDB	6.9259863e-05
4,498	R2T: Instance-optimal Truncation for Differentially Private Query Evaluation with Foreign Keys	2022	SIGMOD	6.5733482e-05
4,567	Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting	2022	VLDB	6.5284697e-05
4,767	ETC: Efficient Training of Temporal Graph Neural Networks over Large-scale Dynamic Graphs	2024	VLDB	6.4245781e-05
4,827	DAHA: Accelerating GNN Training with Data and Hardware Aware Execution Planning	2024	VLDB	6.3893293e-05
5,055	Decoupled Graph Neural Networks for Large Dynamic Graphs	2023	VLDB	6.293158e-05
5,127	SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization	2022	VLDB	6.259487e-05
5,223	Efficient Streaming Subgraph Isomorphism with Graph Neural Networks	2021	VLDB	6.2201582e-05
6,092	METRO: A Generic Graph Neural Network Framework for Multivariate Time Series Forecasting	2022	VLDB	5.8876757e-05
6,328	EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs	2023	SIGMOD	5.8110274e-05
6,498	Operon: An Encrypted Database for Ownership-Preserving Data Management	2022	VLDB	5.7630754e-05
6,808	Residual Sensitivity for Differentially Private Multi-Way Joins	2021	SIGMOD	5.6756613e-05
7,442	A Nearly Instance-optimal Differentially Private Mechanism for Conjunctive Queries	2022	PODS	5.5241292e-05
9,537	Temporal SIR-GN: Efficient and Effective Structural Representation Learning for Temporal Graphs	2023	VLDB	5.1631953e-05
9,907	Scalable Graph Convolutional Network Training on Distributed-Memory Systems	2023	VLDB	5.1092231e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,899	Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective	2024	VLDB
2	7,511	ADGNN: Towards Scalable GNN Training with Aggregation-Difference Aware Sampling	2023	SIGMOD
3	6,465	ALG: Fast and Accurate Active Learning Framework for Graph Convolutional Networks	2021	SIGMOD
4	11,368	Faster Convergence in Mini-batch Graph Neural Networks Training with Pseudo Full Neighborhood Compensation	2025	VLDB
5	6,484	On Data-Aware Global Explainability of Graph Neural Networks	2023	VLDB
6	2,941	Query Driven-Graph Neural Networks for Community Search: From Non-Attributed, Attributed, to Interactive Attributed	2022	VLDB
7	2,598	Scalable and Efficient Full-Graph GNN Training for Large Graphs	2023	SIGMOD
8	6,673	Efficient Training of Graph Neural Networks on Large Graphs	2024	VLDB
9	6,328	EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs	2023	SIGMOD
10	5,055	Decoupled Graph Neural Networks for Large Dynamic Graphs	2023	VLDB