Research map / Multi-agent systems and games / Games and equilibria
Learning Quadratic Games on Networks
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 |
|---|---|---|---|
| Jointly infer graph structure and marginal benefits using the Nash-equilibrium constraint | Quadratic network games · Social network | AUC: 0.564 -> 0.575 | Helped |
| Jointly infer graph structure and marginal benefits using the Nash-equilibrium constraint | Quadratic network games · Trade network | AUC: 0.570 -> 0.622 | Helped |
| Model homophily in marginal benefits with a graph Laplacian penalty | Quadratic network games · Social network | AUC: 0.575 -> 0.576 | Helped |
| Model homophily in marginal benefits with a graph Laplacian penalty | Quadratic network games · Trade network | AUC: 0.622 -> 0.677 | Helped |
| Use the proposed learning algorithms instead of sample correlation | Quadratic network games · Social network | AUC: 0.525 -> 0.575; 0.525 -> 0.576 | Helped |
| Use the proposed learning algorithms instead of sample correlation | Quadratic network games · Trade network | AUC: 0.523 -> 0.622; 0.523 -> 0.677 | Helped |
| Increase the number of observed games (ablation) | Algorithm 1 · Synthetic ER, WS, and BA graphs | AUC | Helped |
| Increase noise intensity in marginal benefits (ablation) | Algorithm 1 · Synthetic ER, WS, and BA graphs | AUC | Hurt |
| Increase edge density (ablation) | Algorithm 1 · Synthetic ER, WS, and BA graphs | AUC | Hurt |
| Increase strategic dependence, measured by spectral radius (ablation) | Proposed methods and baselines · Synthetic ER, WS, and BA graphs | AUC | Helped |
| Use stronger homophily in marginal benefits (ablation) | Algorithm 2 · Synthetic ER, WS, and BA graphs | AUC | Helped |
| Increase the spectral radius for regularized graphical Lasso (ablation) | Regularized graphical Lasso · Synthetic ER, WS, and BA graphs | AUC | Hurt |
Closest papers by meaning
- Learning to Infer Structures of Network Games (ICML 2022 · similarity 0.92)
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.89)
- Deviate or Not: Learning Coalition Structures with Multiple-bit Observations in Games (AAAI 2025 · similarity 0.87)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.86)
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games (ICLR 2024 · similarity 0.86)
- Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games (NeurIPS 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.