A Benchmark Study of Deep-RL Methods for Maximum Coverage Problems over Graphs
Summary: Comprehensive benchmark of five Deep-RL heuristics for graph Maximum Coverage and Influence Maximization. Finds Lazy Greedy, IMM, and OPIM generally outperform them, exposing practical shortcomings and a narrow IM regime where Deep-RL prevails. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhicheng Liang (City University of Hong Kong)
- 2. Yu Yang (City University of Hong Kong)
- 3. Xiangyu Ke (Zhejiang University)
- 4. Xiaokui Xiao (National University of Singapore)
- 5. Yunjun Gao (Zhejiang University)
BibTeX Citation
@article{liang_vldb24,
title = {{A Benchmark Study of Deep-RL Methods for Maximum Coverage Problems over Graphs}},
author = {Liang, Zhicheng and Yang, Yu and Ke, Xiangyu and Xiao, Xiaokui and Gao, Yunjun},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {11},
pages = {3666--3679},
doi = {10.14778/3681954.3682029},
url = {https://doi.org/10.14778/3681954.3682029},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 194 | Influence Maximization: Near-Optimal Time Complexity Meets Practical Efficiency | 2014 | SIGMOD | 0.000259047 |
| 296 | A Data-Based Approach to Social Influence Maximization | 2012 | VLDB | 0.00022220351 |
| 315 | Influence Maximization in Near-Linear Time: A Martingale Approach | 2015 | SIGMOD | 0.00021436156 |
| 1,478 | Online Processing Algorithms for Influence Maximization | 2018 | SIGMOD | 0.00010651983 |
| 1,531 | Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study | 2017 | SIGMOD | 0.00010472526 |
| 5,890 | An In-Depth Comparison of s-t Reliability Algorithms over Uncertain Graphs | 2019 | VLDB | 6.0496722e-05 |
| 8,795 | Finding Seeds and Relevant Tags Jointly: For Targeted Influence Maximization in Social Networks | 2018 | SIGMOD | 5.3704111e-05 |
| 11,345 | Host Profit Maximization: Leveraging Performance Incentives and User Flexibility | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,752 | Efficient Algorithms for Budgeted Influence Maximization on Massive Social Networks | 2020 | VLDB |
| 2 | 13,295 | Multi-Level Graph Representation Learning Through Predictive Community-based Partitioning | 2025 | SIGMOD |
| 3 | 10,900 | A Comprehensive Survey and Experimental Study of Learning-based Community Search | 2025 | VLDB |
| 4 | 1,919 | Holistic Influence Maximization: Combining Scalability and Efficiency with Opinion-Aware Models | 2016 | SIGMOD |
| 5 | 13,289 | Effective Clustering for Large Multi-Relational Graphs | 2026 | SIGMOD |
| 6 | 3,908 | Diversified Top-k Graph Pattern Matching | 2013 | VLDB |
| 7 | 10,913 | Inference-friendly Graph Compression for Graph Neural Networks | 2025 | VLDB |
| 8 | 11,409 | Efficient Algorithm for Budgeted Adaptive Influence Maximization: An Incremental RR-set Update Approach | 2023 | SIGMOD |
| 9 | 1,531 | Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study | 2017 | SIGMOD |
| 10 | 11,553 | SparRL: Graph Sparsification via Deep Reinforcement Learning | 2022 | SIGMOD |