Matching in Selective and Balanced Representation Space for Treatment Effects Estimation

Chu, Zhixuan; Rathbun, Stephen L.; Li, Sheng

doi:10.1145/3340531.3412037

Cited by 22 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model used to generate the continuous outcome variable Y in this simulation is the partially linear regression model (Eq. (4.10)), extending the ideas described in [7,18]: ∼ Bernoulli(e 0 ((C , Z ) )). The function τ ((C , A ) ) describes the true treatment effect as a function of the values of adjustment variables A and confounders C. The function g((C , A ) ) can have an influence on outcome regardless of treatment assignment.…”

Section: Synthetic Datasetmentioning

confidence: 62%

Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World Data

Chu¹,

Rathbun²,

Li³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The foremost challenge to causal inference with real-world data is to handle the imbalance in the covariates with respect to different treatment options, caused by treatment selection bias. To address this issue, recent literature has explored domain-invariant representation learning based on different domain divergence metrics (e.g., Wasserstein distance, maximum mean discrepancy, position-dependent metric, and domain overlap). In this paper, we reveal the weaknesses of these strategies, i.e., they lead to the loss of predictive information when enforcing the domain invariance; and the treatment effect estimation performance is unstable, which heavily relies on the characteristics of the domain distributions and the choice of domain divergence metrics. Motivated by information theory, we propose to learn the Infomax and Domain-Independent Representations to solve the above puzzles. Our method utilizes the mutual information between the global feature representations and individual feature representations, and the mutual information between feature representations and treatment assignment predictions, in order to maximally capture the common predictive information for both treatment and control groups. Moreover, our method filters out the influence of instrumental and irrelevant variables, and thus it effectively increases the predictive ability of potential outcomes. Experimental results on both the synthetic and real-world datasets show that our method achieves state-of-the-art performance on causal effect inference. Moreover, our method exhibits reliable prediction performances when facing data with different characteristics of data distributions, complicated variable types, and severe covariate imbalance.

show abstract

Section: Synthetic Datasetmentioning

confidence: 62%

Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World Data

Chu¹,

Rathbun²,

Li³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A common approach for confounding adjustment is using the propensity score, i.e., the probability of a unit being assigned to a particular level of intervention, given the background covariates (Rosenbaum and Rubin 1983). In confounding adjustment, although including all confounders is important, this does not mean that including more variables is better (Chu, Rathbun, and Li 2020;Greenland 2008;Schisterman, Cole, and Platt 2009). For example, conditioning on instrumental variables that are associated with the intervention assignment but not with the outcome except through the intervention can increase both bias and variance of estimated causal effects (Myers et al 2011).…”

Section: Preliminarymentioning

confidence: 99%

Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction

Chu,

Hu,

Cui

et al. 2024

AAAI

View full text Add to dashboard Cite

Since artificial intelligence has seen tremendous recent successes in many areas, it has sparked great interest in its potential for trustworthy and interpretable risk prediction. However, most models lack causal reasoning and struggle with class imbalance, leading to poor precision and recall. To address this, we propose a Task-Driven Causal Feature Distillation model (TDCFD) to transform original feature values into causal feature attributions for the specific risk prediction task. The causal feature attribution helps describe how much contribution the value of this feature can make to the risk prediction result. After the causal feature distillation, a deep neural network is applied to produce trustworthy prediction results with causal interpretability and high precision/recall. We evaluate the performance of our TDCFD method on several synthetic and real datasets, and the results demonstrate its superiority over the state-of-the-art methods regarding precision, recall, interpretability, and causality.

show abstract

“…Then it directly applies the learned projection matrix to all the samples and finds every treatment sample's matched control sample in the subspace. In addition, another work [35] performs matching in the selective and balanced representation space to estimate treatment effects. It seamlessly integrates deep feature selection and deep representation learning for causal inference together.…”

Section: Matching Based On Representationmentioning

confidence: 99%

A Survey on Causal Inference

Yao

Chu

et al. 2021

ACM Trans. Knowl. Discov. Data

Self Cite

261

131

View full text Add to dashboard Cite

Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy, and economics, for decades. Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well-known causal inference frameworks. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine, and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.

show abstract

Matching in Selective and Balanced Representation Space for Treatment Effects Estimation

Cited by 22 publications

References 28 publications

Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World Data

Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World Data

Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction

A Survey on Causal Inference

Contact Info

Product

Resources

About