Research map / Bandits and online learning / Online convex optimization and games
Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback
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 linear generalization across edge activation probabilities instead of estimating edge weights independently | IMLinUCB on a Facebook subgraph · Facebook subgraph | cumulative regret | Helped |
| Evaluate IMLinUCB as the number of nodes grows on star graphs | IMLinUCB, star topology, ω=0.8 · Synthetic star graphs | regret growth exponent in L: 2.040; expected Õ(L^2) | Mixed |
| Evaluate IMLinUCB as the number of nodes grows on star graphs | IMLinUCB, star topology, ω=0.7 · Synthetic star graphs | regret growth exponent in L: 2.056; expected Õ(L^2) | Mixed |
| Evaluate IMLinUCB as the number of nodes grows on ray graphs | IMLinUCB, ray topology, ω=0.8 · Synthetic ray graphs | regret growth exponent in L: 2.488; expected Õ(L^{9/4}) | Mixed |
| Evaluate IMLinUCB as the number of nodes grows on ray graphs | IMLinUCB, ray topology, ω=0.7 · Synthetic ray graphs | regret growth exponent in L: 2.467; expected Õ(L^{9/4}) | Mixed |
Closest papers by meaning
- Efficient Online Influence Maximization under the Independent Cascade Model with Node-Level Feedback (ICML 2026 · similarity 0.94)
- Online Influence Maximization under Linear Threshold Model (NeurIPS 2020 · similarity 0.92)
- DiffIM: Differentiable Influence Minimization with Surrogate Modeling and Continuous Relaxation (AAAI 2025 · similarity 0.88)
- REM: A Scalable Reinforced Multi-Expert Framework for Multiplex Influence Maximization (AAAI 2025 · similarity 0.87)
- Hyperparametric Robust and Dynamic Influence Maximization (AAAI 2025 · similarity 0.87)
- Learning to target with network interference (NeurIPS 2026 · similarity 0.87)
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.