Research map / Graph learning / Graph algorithms and clustering
Deep Graph Representation Learning and Optimization for Influence Maximization
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 |
|---|---|---|---|
| Learn a latent seed-set representation and jointly learn a GNN-based diffusion model | DeepIM · IC diffusion, six real-world datasets and Synthetic | influence spread | Helped |
| Learn a latent seed-set representation and jointly learn a GNN-based diffusion model | DeepIM · LT diffusion, six real-world datasets and Synthetic | influence spread | Helped |
| Use the student diffusion model instead of the GNN diffusion model | DeepIM · IC and LT diffusion, evaluated datasets | influence spread: DeepIM_s: 13.6, 27.7, 38.5, 51.8; DeepIM: 14.1, 28.1, 39.6, 52.4 | Mixed |
| Use the student diffusion model instead of the GNN diffusion model | DeepIM · Inference runtime, graph sizes 10,000, 20,000, 30,000, 50,000 | inference runtime: 1.402s -> 0.312s; 2.798s -> 0.616s; 5.124s -> 0.847s; 12.882s -> 1.275s | Helped |
| Use latent-space seed inference with a flexible node-centrality budget constraint | DeepIM · Degree-budget-constrained influence maximization | influence spread | Helped |
| Apply DeepIM to the non-progressive SIS diffusion pattern | DeepIM · SIS, all datasets | influence spread: 10% | Helped |
Closest papers by meaning
- DeepSN: A Sheaf Neural Framework for Influence Maximization (AAAI 2025 · similarity 0.92)
- REM: A Scalable Reinforced Multi-Expert Framework for Multiplex Influence Maximization (AAAI 2025 · similarity 0.90)
- DiffIM: Differentiable Influence Minimization with Surrogate Modeling and Continuous Relaxation (AAAI 2025 · similarity 0.89)
- Graph Bayesian Optimization for Multiplex Influence Maximization (AAAI 2024 · similarity 0.89)
- Hyperparametric Robust and Dynamic Influence Maximization (AAAI 2025 · similarity 0.86)
- Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning (AAAI 2024 · 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.