Research map / Probabilistic and scientific modeling / Treatment effects
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial 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 |
|---|---|---|---|
| add supervised loss L_S to baseline GAN (ablation) | baseline GAN · TCGA | sqrt(MISE): 4.18 -> 3.37 | Helped |
| add multitask generator heads (ablation) | SCIGAN + L_S · TCGA | sqrt(MISE): 3.37 -> 3.15 | Helped |
| add hierarchical discriminator (ablation) | SCIGAN + L_S + multitask · TCGA | sqrt(MISE): 3.15 -> 2.54 | Helped |
| add hierarchical discriminator (ablation) | SCIGAN + L_S + multitask · TCGA | sqrt(DPE): 0.85 -> 0.36 | Helped |
| add invariant/equivariant layers in discriminators (ablation) | SCIGAN · TCGA | sqrt(MISE): 2.54 -> 1.89 | Helped |
| add invariant/equivariant layers in discriminators (ablation) | SCIGAN · TCGA | sqrt(PE): 0.45 -> 0.25 | Helped |
| add supervised loss L_S (ablation) | baseline GAN · TCGA | sqrt(PE): 1.93 -> 0.84 | Helped |
| SCIGAN vs DRNet | SCIGAN · TCGA | sqrt(MISE): 3.64 -> 1.89 | Helped |
| SCIGAN vs GANITE as discrete dosages increase beyond 7 | SCIGAN · discrete dosages 3 to 30 | MSE | Helped |
| increase selection bias (kappa 0 to 10, alpha 1 to 8) | SCIGAN · TCGA | sqrt(MISE) | No clear effect |
Closest papers by meaning
- Adversarially Balanced Representation for Continuous Treatment Effect Estimation (AAAI 2024 · similarity 0.91)
- Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothing (AAAI 2024 · similarity 0.90)
- Extended Wasserstein-GAN Approach to Causal Distribution Learning: Density-Free Estimation and Minimax Optimality (NeurIPS 2026 · similarity 0.87)
- A Dual-module Framework for Counterfactual Estimation over Time (ICML 2024 · similarity 0.86)
- A Generative Approach for Treatment Effect Estimation under Collider Bias: From an Out-of-Distribution Perspective (ICML 2024 · similarity 0.86)
- PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect (ICML 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.