Research map / Graph learning / Graph algorithms and clustering
LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use subgraph navigation with an InfoNCE-trained embedding | LeNSE · Wiki-MVC | Ratio: 1.094 | Helped |
| Use subgraph navigation with an InfoNCE-trained embedding | LeNSE · Wiki-BMC | Ratio: 0.981 | No clear effect |
| Use subgraph navigation with an InfoNCE-trained embedding | LeNSE · Wiki-IM | Ratio: 0.960 | No clear effect |
| replace InfoNCE with Cross-Entropy (ablation) | LeNSE · Facebook-MVC | Ratio: 0.968 -> 0.907 | Hurt |
| replace InfoNCE with Ordinal loss (ablation) | LeNSE · Facebook-MVC | Ratio: 0.968 -> 0.880 | Hurt |
| replace InfoNCE with Cross-Entropy (ablation) | LeNSE · Wiki-MVC | Ratio: 1.094 -> 0.899 | Hurt |
| replace InfoNCE with Ordinal loss (ablation) | LeNSE · Wiki-MVC | Ratio: 1.094 -> 0.931 | Hurt |
| replace InfoNCE with Cross-Entropy (ablation) | LeNSE · Facebook-BMC | Ratio: 0.960 -> 0.647 | Hurt |
| replace InfoNCE with Ordinal loss (ablation) | LeNSE · Facebook-BMC | Ratio: 0.960 -> 0.650 | Hurt |
| replace InfoNCE with Cross-Entropy (ablation) | LeNSE · Wiki-BMC | Ratio: 0.981 -> 0.391 | Hurt |
| replace InfoNCE with Ordinal loss (ablation) | LeNSE · Wiki-BMC | Ratio: 0.981 -> 0.603 | Hurt |
| replace InfoNCE with Cross-Entropy (ablation) | LeNSE · Facebook-IM | Ratio: 0.979 -> 0.663 | Hurt |
Closest papers by meaning
- Learning Combinatorial Optimization Algorithms over Graphs (NeurIPS 2017 · similarity 0.89)
- $\texttt{STRCMP}$: Integrating Graph Structural Priors with Language Models for Combinatorial Optimization (NeurIPS 2025 · similarity 0.87)
- Neural Graduated Assignment for Maximum Common Edge Subgraphs (ICLR 2026 · similarity 0.87)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.86)
- COMBHelper: A Neural Approach to Reduce Search Space for Graph Combinatorial Problems (AAAI 2024 · similarity 0.85)
- Bayesian Optimization of Functions over Node Subsets in Graphs (NeurIPS 2024 · similarity 0.85)
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.