A Survey on Causal Inference

Yao, Liuyi; Chu, Zhixuan; Li, Sheng; Li, Yaliang; Gao, Jing; Zhang, Aidong

doi:10.1145/3444944

Cited by 261 publications

(164 citation statements)

References 156 publications

Supporting

Mentioning

131

Contrasting

Order By: Relevance

“…Let X denote the random variable of paper features, T denote the random variable of treatments (i.e., venue), Y (t) denote the random variable of the potential outcome when the paper is published in venue t ∈ T , and Y T denote the random variable of the factual outcome. In this paper, we make three common assumptions for causal inference [26]:…”

Section: Nmentioning

confidence: 99%

See 1 more Smart Citation

Poincare: Recommending Publication Venues via Treatment Effect Estimation

Sato,

Yamada,

Kashima

2020

Preprint

View full text Add to dashboard Cite

Choosing a publication venue for an academic paper is a crucial step in the research process. However, in many cases, decisions are based on the experience of researchers, which often leads to suboptimal results. Although some existing methods recommend publication venues, they just recommend venues where a paper is likely to be published. In this study, we aim to recommend publication venues from a different perspective. We estimate the number of citations a paper will receive if the paper is published in each venue and recommend the venue where the paper has the most potential impact. However, there are two challenges to this task. First, a paper is published in only one venue, and thus, we cannot observe the number of citations the paper would receive if the paper were published in another venue. Secondly, the contents of a paper and the publication venue are not statistically independent; that is, there exist selection biases in choosing publication venues. In this paper, we propose to use a causal inference method to estimate the treatment effects of choosing a publication venue effectively and to recommend venues based on the potential influence of papers. Figure 1: Illustration (synthetic data): Each point represents a research paper, and the position indicates the contents (e.g., fields of study) of the paper. Association-based recommender systems recommend venues based on the likelihood of the venue. In contrast, our proposed method Poincare recommends venues based on potential influence.

show abstract

Section: Nmentioning

confidence: 99%

“…Künzel et al [11] proposed some strategies (meta-learners) for estimating treatment effects. Yao et al [26] provided an extensive survey of causal inference.…”

Section: Introductionmentioning

confidence: 99%

Poincare: Recommending Publication Venues via Treatment Effect Estimation

Sato,

Yamada,

Kashima

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In [28], the authors argue that distribution invariance is often too strict a requirement and they propose to use counterfactual variance to measure the domain overlap. Thus, for the domain adaptation problem under causal inference settings, which is the best measurement for the imbalanced domains remains unsettled and is highly relies on the characteristics of the distributions of domains and the hyperparameter of regularization term for imbalance mitigation [25]. Besides, despite the empirical success of such methods, enforcing balance can, to various extents, remove predictive information and lead to a loss in predictive power, regardless of which type of domain divergence metric is employed [1].…”

Section: Introductionmentioning

confidence: 99%

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

“…Guo et al [16] focus on reviewing the methodologies for causal effect estimation and causal structure learning, as well as discussing the connections between causal inference and ML. Yao et al [22] specifically survey causal effect estimation methods and tools under the potential outcome framework. Another survey by Spirtes and Zhang [23] reviews semiparametric score-based methods for learning causal structure with i.i.d.…”

Section: Introductionmentioning

confidence: 99%

Evaluation Methods and Measures for Causal Learning Algorithms

Liu¹,

Guo²,

Moraffah³

et al. 2022

Preprint

View full text Add to dashboard Cite

A Survey on Causal Inference

Cited by 261 publications

References 156 publications

Poincare: Recommending Publication Venues via Treatment Effect Estimation

Poincare: Recommending Publication Venues via Treatment Effect Estimation

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

Evaluation Methods and Measures for Causal Learning Algorithms

Contact Info

Product

Resources

About