AI Paper Atlas

Research map / Probabilistic and scientific modeling / Treatment effects

Learning Exposure Mapping Functions for Inferring Heterogeneous Peer Effects

Shishir Adhikari, Sourav Medya, Elena Zheleva

ICLR 2026 · Probabilistic and scientific modeling › Treatment effects · approach: Latent-variable causal inference · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
learn exposure mapping with EgoNetGnn (CFR head) vs best baselineGNN-TARNet-Motifs · BlogCatalog, clustering coefficientPEHE error: 2.04 -> 1.51Improved
EgoNetGnn-CFR vs INE-TARNetINE-TARNet · BlogCatalog, mutual connectionsPEHE error: 3.37 -> 2.57Improved
EgoNetGnn-CFR vs CauGramerCauGramer · BlogCatalog, attribute similarityPEHE error: 7.34 -> 4.86Improved
use CFR (balance loss) instead of TARNet headEgoNetGnn · BlogCatalog, clustering coefficientPEHE error: 1.59 -> 1.51Improved
add masked weights (ablation)EgoNetGnn-TARNet · BA, attribute similarityPEHE error: 2.37 -> 1.23Improved
add masked weights (ablation)EgoNetGnn-TARNet · BC, mutual connectionsPEHE error: 2.91 -> 2.90No clear effect
add masked weights (ablation)EgoNetGnn-TARNet · BC, clustering coefficientPEHE error: 1.98 -> 1.59Improved
add feature encoder (ablation)EgoNetGnn-TARNet · BA, attribute similarityPEHE error: 13.73 -> 1.23Improved
add feature encoder (ablation)EgoNetGnn-TARNet · BC, clustering coefficientPEHE error: 1.55 -> 1.59Hurt
add feature encoder (ablation)EgoNetGnn-TARNet · WS, clustering coefficientPEHE error: 1.91 -> 1.18Improved
learn exposure vs fraction of treated friendsEgoNetGnn · BlogCatalog, clustering coefficientcorrelation with true exposure: 0.17 -> 0.81Improved
learn exposure vs fraction of treated friendsEgoNetGnn · BlogCatalog, attribute similaritycorrelation with true exposure: 0.61 -> 0.50Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy