mlsanityData to 14 Oct 2026

Treatment Effect Estimation with Differentiated Networked Effect on Graph Data

arXiv 2605.24358 ↗First posted 23 May 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Estimating individual treatment effect (ITE) from observational graph data is crucial for decision-making in the fields such as commerce and medicine. This task is challenging due to interference, where individual outcomes can be influenced by the treatments and covariates of their neighbors. Existing methods attempt to model such interference for accurate ITE estimation. However, a critical issue is often overlooked: differentiated networked effect (DNE), an effect caused by local networks consisting of neighbors with varying importance and scales. Capturing DNE is vital; otherwise, we will end up with imprecise ITE estimation due to an erroneous characterization of interference, which can result in misguided decisions. To address this challenge, we propose a novel interference modeling mechanism that incorporates two partial attention mechanisms and a message amplifier. The partial attention mechanisms automatically estimate the importance of different neighbors in contributing to interference, while the message amplifier adjusts the results of the interference modeling mechanism based on the scale of neighbors, all of which enables the model to capture DNE. Experiments on three real-world graphs demonstrate that our methods outperform existing approaches for ITE estimation from graph data, which corroborates the importance of explicitly capturing DNE.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 47 of its 86 references that are in the map. First posted on arXiv 23 May 2026.

Builds on

47 of 86 references.

References · 47

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2016Layer Normalizationcited by 5,669
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  7. 2014Distributed Representations of Sentences and Documentscited by 678
  8. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
  9. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  10. 2016Learning Representations for Counterfactual Inferencecited by 329
  11. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 287
  12. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 282
35 more
  1. 2020A Survey on Causal Inferencecited by 202
  2. 2023Graph Inductive Biases in Transformers without Message Passingcited by 153
  3. 2020Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effectscited by 72
  4. 2019Learning Individual Causal Effects from Networked Observational Datacited by 56
  5. 2021Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confoundingcited by 50
  6. 2016Identification and estimation of treatment and interference effects in observational studies on networkscited by 44
  7. 2021Graph Infomax Adversarial Learning for Treatment Effect Estimation with Networked Observational Datacited by 42
  8. 2021Causal Effect Inference for Structured Treatmentscited by 39
  9. 2020Causal Inference under Networked Interference and Intervention Policy Enhancementcited by 38
  10. 2023Optimal Transport for Treatment Effect Estimationcited by 32
  11. 2019Using Embeddings to Correct for Unobserved Confounding in Networkscited by 31
  12. 2022Learning Causal Effects on Hypergraphscited by 31
  13. 2021Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Datacited by 28
  14. 2023B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confoundingcited by 28
  15. 2022StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Randomcited by 24
  16. 2024Doubly Robust Causal Effect Estimation under Networked Interference via Targeted Learningcited by 19
  17. 2024Model-agnostic meta-learners for estimating heterogeneous treatment effects over timecited by 19
  18. 2020GraphITE: Estimating Individual Effects of Graph-structured Treatmentscited by 18
  19. 2022TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendationscited by 18
  20. 2022Estimating individual treatment effects under unobserved confounding using binary instrumentscited by 18
  21. 2018Linked Causal Variational Autoencoder for Inferring Paired Spillover Effectscited by 16
  22. 2021Assessing the Causal Impact of COVID-19 Related Policies on Outbreak Dynamics: A Case Study in the UScited by 16
  23. 2023CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systemscited by 16
  24. 2019Policy Targeting under Network Interferencecited by 12
  25. 2024Rankability-enhanced Revenue Uplift Modeling Framework for Online Marketingcited by 12
  26. 2023Generalization bound for estimating causal effects from observational network datacited by 11
  27. 2020Almost-Matching-Exactly for Treatment Effect Estimation under Network Interferencecited by 7
  28. 2023Estimating Treatment Effects Under Heterogeneous Interferencecited by 7
  29. 2020Causal Inference in the Presence of Interference in Sponsored Search Advertisingcited by 6
  30. 2023Inferring Individual Direct Causal Effects Under Heterogeneous Peer Influencecited by 5
  31. 2022Empowering GNNs via Edge-Aware Weisfeiler-Leman Algorithmcited by 4
  32. 2023Estimation of individual causal effects in network setup for multiple treatmentscited by 4
  33. 2023To Predict or to Reject: Causal Effect Estimation with Uncertainty on Networked Datacited by 3
  34. 2025Enhancing Treatment Effect Estimation via Active Learning: A Counterfactual Covering Perspectivecited by 3
  35. 2022Estimating Geographic Spillover Effects of COVID-19 Policies From Large-Scale Mobility Networkscited by 2

Built on by

Not cited yet.