A Benchmark Study of Deep-RL Methods for Maximum Coverage Problems over Graphs
Summary: Benchmark of five Deep‑RL methods (S2VDQN, Geometric‑QN, GCOMB, RL4IM, LeNSE) on MCP and IM shows they generally underperform classical algorithms. Lazy Greedy (MCP) and IMM/OPIM (IM) dominate except when spread saturates; paper diagnoses failure modes and suggests fixes. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhicheng Liang
- 2. Yu Yang
- 3. Xiangyu Ke
- 4. Xiaokui Xiao
- 5. Yunjun Gao
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 |
|---|---|---|---|---|
| 90 | A Data-Based Approach to Social Influence Maximization | 2012 | VLDB | 0.00052068982 |
| 180 | Influence Maximization: Near-Optimal Time Complexity Meets Practical Efficiency | 2014 | SIGMOD | 0.00037135181 |
| 337 | Influence Maximization in Near-Linear Time: A Martingale Approach | 2015 | SIGMOD | 0.00027011645 |
| 1,652 | Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study | 2017 | SIGMOD | 0.00011010086 |
| 1,801 | Online Processing Algorithms for Influence Maximization | 2018 | SIGMOD | 0.00010510943 |
| 6,172 | An In-Depth Comparison of s-t Reliability Algorithms over Uncertain Graphs | 2019 | VLDB | 5.170101e-05 |
| 8,628 | Finding Seeds and Relevant Tags Jointly: For Targeted Influence Maximization in Social Networks | 2018 | SIGMOD | 4.4817474e-05 |
| 11,139 | Host Profit Maximization: Leveraging Performance Incentives and User Flexibility | 2024 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next