Research map / Probabilistic and scientific modeling / Treatment effects
Using Embeddings to Correct for Unobserved Confounding in Networks
Victor Veitch, Yixin Wang, David Blei
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 |
|---|---|---|---|
| adjust for confounding using network embeddings (A-IPTW) vs unadjusted | embedding-based causal estimator · Pokec district, high confounding | estimated ATE (truth 1.0): 4.51 -> 2.03 | Improved |
| joint training of embeddings and predictors (single-stage) instead of two-stage frozen embeddings (ablation) | embedding-based causal estimator · Pokec district, high confounding | estimated ATE (truth 1.0): 4.55 -> 2.03 | Improved |
| replace MMSBM parametric adjustment with embedding adjustment | embedding-based causal estimator · Pokec district, high confounding | estimated ATE (truth 1.0): 3.22 -> 2.03 | Improved |
| use conditional-outcome-only estimator instead of A-IPTW (ablation) | embedding-based causal estimator · Pokec age, high confounding | estimated ATE (truth 1.0): 3.40 -> 2.77 | Improved |
| use conditional-outcome-only estimator instead of A-IPTW (ablation) | embedding-based causal estimator · Pokec district, low confounding | estimated ATE (truth 1.0): 1.09 -> 1.03 | Improved |
| use IPTW g-only estimator instead of A-IPTW (ablation) | embedding-based causal estimator · Pokec district, high confounding | estimated ATE (truth 1.0): 2.03 -> 1.66 | Improved |
| use TMLE instead of A-IPTW (ablation) | embedding-based causal estimator · Pokec age, high confounding | estimated ATE (truth 1.0): 3.40 -> 3.26 | Improved |
| add exogenous confounding not captured by network (ablation) | embedding-based causal estimator · network-adjusted estimator | Pokec ATE | Mixed |
Closest papers by meaning
- A Recipe for Causal Graph Regression: Confounding Effects Revisited (ICML 2025 · similarity 0.87)
- Scores for Learning Discrete Causal Graphs with Unobserved Confounders (AAAI 2024 · similarity 0.86)
- From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks (ICML 2024 · similarity 0.86)
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.86)
- Information Loss and Disparate Effects in Network Embeddings (NeurIPS 2026 · similarity 0.86)
- A Sparsity Principle for Partially Observable Causal Representation Learning (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.
