Research map / Learning theory and algorithms / Prediction and decision losses
Social-Inverse: Inverse Decision-making of Social Contagion Management with Task Migrations
Guangmo Tong
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| Increase the number of realizations from K=15 to K=60 (ablation) | Social-Inverse · Kronecker, DC→DE, M0.1 | performance ratio: 0.770 { (0.025)} -> 0.853 { (0.040)} | Improved |
| Use realizations from M0.1 rather than M∞ (ablation) | Social-Inverse · Kronecker, DC→DE, K=60 | performance ratio: 0.584 { (0.006)} -> 0.853 { (0.040)} | Improved |
| Increase the number of realizations from K=15 to K=60 (ablation) | Social-Inverse · Kronecker, DE→DC, M0.1 | performance ratio: 0.862 { (0.013)} -> 1.041 { (0.026)} | Improved |
| Use realizations from M0.1 rather than M∞ (ablation) | Social-Inverse · Kronecker, DE→DC, K=60 | performance ratio: 0.985 { (0.014)} -> 1.041 { (0.026)} | Improved |
| Increase the number of realizations from K=15 to K=60 (ablation) | Social-Inverse · Erdős-Rényi, DC→DE, M0.1 | performance ratio: 0.829 { (0.002)} -> 0.833 { (0.004)} | No clear effect |
| Use realizations from M0.1 rather than M∞ (ablation) | Social-Inverse · Erdős-Rényi, DC→DE, K=60 | performance ratio: 0.577 { (0.007)} -> 0.833 { (0.004)} | Improved |
| Increase the number of realizations from K=15 to K=30 (ablation) | Social-Inverse · Erdős-Rényi, DE→DC, M0.1 | performance ratio: 0.886 { (0.005)} -> 0.902 { (0.003)} | Improved |
| Increase the number of realizations from K=30 to K=60 (ablation) | Social-Inverse · Erdős-Rényi, DE→DC, M0.1 | performance ratio: 0.902 { (0.003)} -> 0.895 { (0.003)} | Hurt |
| Use realizations closer to the true diffusion model (ablation) | Social-Inverse · Task migrations; multiple graphs | performance ratio | Improved |
| Increase the number of source-task training samples when the empirical distribution is very far from the true model (ablation) | Social-Inverse · Kronecker, DC→DE, M∞ | performance ratio | Hurt |
Closest papers by meaning
- Steering the Herd: A Framework for LLM-based Control of Social Learning (ICLR 2026 · similarity 0.85)
- CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making (NeurIPS 2024 · similarity 0.84)
- Socialized Coevolution: Advancing a Better World through Cross-Task Collaboration (ICML 2025 · similarity 0.83)
- The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability (ICML 2025 · similarity 0.83)
- Massively Scalable Inverse Reinforcement Learning in Google Maps (ICLR 2024 · similarity 0.83)
- RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation (NeurIPS 2024 · similarity 0.83)
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.
