Research map / Probabilistic and scientific modeling / Treatment effects
Causal Representation Learning with Optimal Compression and Complex Treatments
Wanting Liang, Haoang Chi, Zhiheng Zhang
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 |
|---|---|---|---|
| add any multi-treatment balancing strategy (Pairwise, OVA, Aggregation) | Base Model · Semi-synthetic, K=4 | PEHE: 0.796 -> 0.711 (OVA), 0.727 (Pairwise), 0.722 (Agg-T) | Improved |
| use One-vs-All instead of Pairwise balancing at small K (ablation) | balancing strategy · Semi-synthetic, K=4 | PEHE: 0.727 -> 0.711 | Improved |
| use Treatment Aggregation (HSIC) instead of Pairwise balancing at small K (ablation) | balancing strategy · Semi-synthetic, K=4 | PEHE: 0.727 -> 0.722 | No clear effect |
| use strong regularization alpha=5.0 with Pairwise balancing at large K (ablation) | Pairwise balancing · Semi-synthetic, K=20 | PEHE: PEHE above 1.3 | Hurt |
| use Treatment Aggregation instead of Pairwise as K grows to 20 (ablation) | balancing strategy · Semi-synthetic, K=20 | PEHE and stability: Agg-T PEHE about 1.0 across all alpha vs Pairwise above 1.3 at alpha=5.0 | Improved |
| tune alpha per strategy (ablation) | balancing strategies · Semi-synthetic, K=4 | best alpha: OVA 0.1, Aggregation 0.5, Pairwise 5.0 | Improved |
| use generative Multi-Treatment CausalEGM instead of the unadjusted base | CausalEGM · UCI Digits | PEHE: 0.79 -> 0.65 | Improved |
| use generative CausalEGM instead of discriminative OVA | balancing strategy · UCI Digits | PEHE: 0.24 vs 0.65 | Hurt |
Closest papers by meaning
- Coupling Generative Modeling and an Autoencoder with the Causal Bridge (NeurIPS 2025 · similarity 0.88)
- Towards Causal Foundation Model: on Duality between Optimal Balancing and Attention (ICML 2024 · similarity 0.87)
- Identifying Representations for Intervention Extrapolation (ICLR 2024 · similarity 0.86)
- Causal Representation Learning via Counterfactual Intervention (AAAI 2024 · similarity 0.86)
- A Sparsity Principle for Partially Observable Causal Representation Learning (ICML 2024 · similarity 0.85)
- Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection (NeurIPS 2026 · similarity 0.85)
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.
