---
title: "Network Effect Decomposition for Causal Effect Estimation under Network Interference"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07879v1"
permalink: "https://feed.astralor.com/items/itm_1f4e994347299d62c4806e16"
published: "2026-11-05T12:00:31.000Z"
score: 57
channel: "ai"
tags: ["Network Effect Decomposition","Causal Effect Estimation","Network Interference Estimating","Existing","Estimating","Net","NEDNet"]
---

# Network Effect Decomposition for Causal Effect Estimation under Network Interference

## At a glance

Estimating causal effects from observational network data requires accounting for both individual treatment and neighborhood exposure. Existing outcome models commonly incorporate these intervention variables into a joi…

## Key points

- Estimating causal effects from observational network data requires accounting for both individual treatment and neighborhood exposure.
- Existing outcome models commonly incorporate these intervention variables into a joint predictor and estimate causal effects through prediction contrasts, leaving the corresponding response components implicit.
- We propose the $\underline{N}$etwork $\underline{E}$ffect $\underline{D}$ecomposition $\underline{Net}$work (NEDNet), which parameterizes the conditional outcome response as a query-invariant pre-treatment baseline plus…

## Full text

Estimating causal effects from observational network data requires accounting for both individual treatment and neighborhood exposure. Existing outcome models commonly incorporate these intervention variables into a joint predictor and estimate causal effects through prediction contrasts, leaving the corresponding response components implicit. We propose the $\underline{N}$etwork $\underline{E}$ffect $\underline{D}$ecomposition $\underline{Net}$work (NEDNet), which parameterizes the conditional outcome response as a query-invariant pre-treatment baseline plus separate treatment- and exposure-response pathways. Path-specific neighborhood contextualization supplies local pre-treatment information to the two pathways. We characterize the fitted response through a unique reference-normalized decomposition, which is equivalent to a zero mixed treatment--exposure contrast. Experiments on semi-synthetic benchmarks derived from BlogCatalog and Flickr show that NEDNet achieves the lowest PEHE among the compared methods for individual, peer, and total effects across homogeneous and covariate-heterogeneous response settings.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_1f4e994347299d62c4806e16