Inferring Network Effects from Observational Data

Arbour, David; Garant, Dan; Jensen, David

doi:10.1145/2939672.2939791

Cited by 23 publications

(28 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But in these studies the units are still homogeneous (e.g., people connected by a social network), and they are unable to capture different entities of interests like papers, authors, reviews and their complex many-to-many relationships that we focus on in CaRL. There has been prior work on learning causality from relational data [3,21,22,24]; it focuses on discovering the structure of probabilistic graphical models for this data. These models were originally proposed for Statistical Relational Learning, which aims to model a joint probability distribution over relational data amenable for probabilistic reasoning rather than causal inference [8].…”

Section: Background On Causalitymentioning

confidence: 99%

See 1 more Smart Citation

Causal Relational Learning

Salimi

Parikh

Kayali

et al. 2020

Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

Causal inference is at the heart of empirical research in natural and social sciences and is critical for scientific discovery and informed decision making. The gold standard in causal inference is performing randomized controlled trials; unfortunately these are not always feasible due to ethical, legal, or cost constraints. As an alternative, methodologies for causal inference from observational data have been developed in statistical studies and social sciences. However, existing methods critically rely on restrictive assumptions such as the study population consisting of homogeneous elements that can be represented in a single flat table, where each row is referred to as a unit. In contrast, in many real-world settings, the study domain naturally consists of heterogeneous elements with complex relational structure, where the data is naturally represented in multiple related tables. In this paper, we present a formal framework for causal inference from such relational data. We propose a declarative language called CaRL for capturing causal background knowledge and assumptions, and specifying causal queries using simple Datalog-like rules. CaRL provides a foundation for inferring causality and reasoning about the effect of complex interventions in relational domains. We present an extensive experimental evaluation on real relational data to illustrate the applicability of CaRL in social sciences and healthcare.

show abstract

Section: Background On Causalitymentioning

confidence: 99%

“…We assume that the relational causal model is non-recursive, therefore, the causal graph is a DAG 4 . 3 This fact, along with the declarative nature of the language, makes CaRL Example 3.6. Given the skeleton Δ in Figure 1, Φ generates the following grounded rules:…”

Section: Relational Causal Graphsmentioning

confidence: 99%

Causal Relational Learning

Salimi

Parikh

Kayali

et al. 2020

Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

show abstract

“…Then, the outcome of a node is dependent on two variables: the individual treatment and the set of treatments in the network: Y v (Z v , A). We can define the average treatment effect (ATE) and the average peer effect (APE) (Arbour, Garant, and Jensen 2016;Fatemi and Zheleva 2020) as:…”

Section: Causal Inference In Ltmmentioning

confidence: 99%

“…For example, a user (e.g., Angelo in Figure 1) might buy sunglasses (outcome) if their friends already bought them (contagion). Prior work has studied the role of SCMs in the presence of interference (Ogburn and VanderWeele 2014;Bhattacharya, Malinsky, and Shpitser 2020) and the estimation of average peer effects (Arbour, Garant, and Jensen 2016) but not peer effect heterogeneity.…”

Section: Introductionmentioning

confidence: 99%

Heterogeneous Peer Effects in the Linear Threshold Model

Tran¹,

Zheleva²

2022

Preprint

View full text Add to dashboard Cite

The Linear Threshold Model is a widely used model that describes how information diffuses through a social network. According to this model, an individual adopts an idea or product after the proportion of their neighbors who have adopted it reaches a certain threshold. Typical applications of the Linear Threshold Model assume that thresholds are either the same for all network nodes or randomly distributed, even though some people may be more susceptible to peer pressure than others. To address individual-level differences, we propose causal inference methods for estimating individual thresholds that can more accurately predict whether and when individuals will be affected by their peers. We introduce the concept of heterogeneous peer effects and develop a Structural Causal Model which corresponds to the Linear Threshold Model and supports heterogeneous peer effect identification and estimation. We develop two algorithms for individual threshold estimation, one based on causal trees and one based on causal meta-learners. Our experimental results on synthetic and realworld datasets show that our proposed models can better predict individual-level thresholds in the Linear Threshold Model and thus more precisely predict which nodes will get activated over time.

show abstract

“…Although the condition of no interference is often assumed, there are cases when the inter-dependence between instances matters. For example, with spillover effect or treatment entanglement, treatment of an instance may causally influence the outcomes of its neighbors in a given graph connecting instances [11,114,138]. The second assumption, consistency, means that the observed outcome is independent of the how the treatment is assigned.…”

Section: Potential Outcome Frameworkmentioning

confidence: 99%

A Survey of Learning Causality with Data: Problems and Methods

Guo,

Cheng,

et al. 2018

Preprint

View full text Add to dashboard Cite

The era of big data provides researchers with convenient access to copious data. However, we often have little knowledge of such data. The increasing prevalence of massive data challenges the traditional methods of learning causality because they were developed for the cases with limited amount of data and strong prior causal knowledge. This survey aims to close the gap between big data and learning causality with a comprehensive and structured review of both traditional and frontier methods followed by a discussion about some open problems of learning causality. We begin with preliminaries of learning causality. Then we categorize and revisit methods of learning causality for typical problems and different data types. After that, we discuss the connections between learning causality and machine learning. At the end, some open problems are presented to show the great potential of learning causality with data.

show abstract

Inferring Network Effects from Observational Data

Cited by 23 publications

References 17 publications

Causal Relational Learning

Causal Relational Learning

Heterogeneous Peer Effects in the Linear Threshold Model

A Survey of Learning Causality with Data: Problems and Methods

Contact Info

Product

Resources

About