# Minimizing Interference and Selection Bias in Network Experiment Design

arXiv: https://arxiv.org/abs/2004.07225 · HTML: https://mlsanity.com/paper/2004.07225/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [Learning Causal Effects on Hypergraphs](https://mlsanity.com/paper/2207.04049/) (2022)
- [Using Embeddings for Causal Estimation of Peer Influence in Social Networks](https://mlsanity.com/paper/2205.08033/) (2022)
- [Heterogeneous Peer Effects in the Linear Threshold Model](https://mlsanity.com/paper/2201.11242/) (2022)
- [Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach](https://mlsanity.com/paper/2505.20130/) (2025)
- [Causal Inference with Latent Variables: Recent Advances and Future Prospectives](https://mlsanity.com/paper/2406.13966/) (2024)
- [Cascade-based Randomization for Inferring Causal Effects under Diffusion Interference](https://mlsanity.com/paper/2405.12340/) (2024)
- [Causally Fair Node Classification on Non-IID Graph Data](https://mlsanity.com/paper/2505.01652/) (2025)
- [Estimating Causal Effects in Networks with Cluster-Based Bandits](https://mlsanity.com/paper/2505.04200/) (2025)

## Abstract (arXiv)

Current approaches to A/B testing in networks focus on limiting interference, the concern that treatment effects can "spill over" from treatment nodes to control nodes and lead to biased causal effect estimation. Prominent methods for network experiment design rely on two-stage randomization, in which sparsely-connected clusters are identified and cluster randomization dictates the node assignment to treatment and control. Here, we show that cluster randomization does not ensure sufficient node randomization and it can lead to selection bias in which treatment and control nodes represent different populations of users. To address this problem, we propose a principled framework for network experiment design which jointly minimizes interference and selection bias. We introduce the concepts of edge spillover probability and cluster matching and demonstrate their importance for designing network A/B testing. Our experiments on a number of real-world datasets show that our proposed framework leads to significantly lower error in causal effect estimation than existing solutions.