Research map / Graph learning / Graph algorithms and clustering
GCOMB: Learning Budget-constrained Combinatorial Algorithms over Billion-sized Graphs
Sahil Manchanda, AKASH MITTAL, Anuj Dhawan, Sourav Medya, Sayan Ranu, Ambuj Singh
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add Q-learning on top of GCN node scores instead of selecting top-b nodes by predicted marginal gain (ablation) | GCOMB · MCP, Gowalla and YouTube | coverage improvement (%): up to 10% | Improved |
| Add noise predictor to prune poor nodes (ablation) | GCOMB · MCP, Gowalla | running time | Improved |
| Add noise predictor to prune poor nodes (ablation) | GCOMB · MCP, Gowalla | coverage | Improved |
| GCOMB versus Greedy on random bipartite graphs | GCOMB · MCP BP graphs, b=15 | coverage: 0.89 vs 0.89 on BP-2k | No clear effect |
| GCOMB versus GCN-TreeSearch | GCOMB · MCP BP-2k, b=15 | coverage: 0.86 -> 0.89 | Improved |
Closest papers by meaning
- Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial Optimization (ICLR 2025 · similarity 0.90)
- Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search (NeurIPS 2018 · similarity 0.90)
- COMBHelper: A Neural Approach to Reduce Search Space for Graph Combinatorial Problems (AAAI 2024 · similarity 0.87)
- Chaining 2-FWL GNNs for Combinatorial Graph Alignment (NeurIPS 2026 · similarity 0.87)
- Generalizing CNNs to graphs with learnable neighborhood quantization (NeurIPS 2024 · similarity 0.86)
- TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
