Causal Relational Learning

  title={Causal Relational Learning},
  author={Babak Salimi and Harsh Parikh and Moe Kayali and Sudeepa Roy and Lise Getoor and Dan Suciu},
  journal={Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data},
  • Babak SalimiHarsh Parikh Dan Suciu
  • Published 7 April 2020
  • Computer Science
  • Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data
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… 

Demonstration of inferring causality from relational databases with CaRL

CaRL is proposed and demonstrated: an end-to-end system for drawing causal inference from relational data and a visual interface to wrap around CaRL is built.

Causal Data Integration

This work introduces the Causal Data Integration (CDI) problem, in which unobserved attributes are mined from external sources and a corresponding causal DAG is automatically built, and presents a system architecture for solving the CDI problem.

Causal Relationship over Knowledge Graphs

CareKG, a new formalism to express causal relationships among concepts, i.e., classes and relations, and enable causal queries over knowledge graphs using semantics of metadata is proposed and empirically evaluates the expressiveness of CareKG in a synthetic knowledge graph concerning cardinalities, class subsumption and overlap, integrity constraints.

XInsight: eXplainable Data Analysis Through The Lens of Causality

XInsight provides data analysis with qualitative and quantitative explanations of causal and non-causal semantics, which will significantly improve human understanding and confidence in the outcomes of data analysis, facilitating accurate data interpretation and decision making in the real world.

Toward Interpretable and Actionable Data Analysis with Explanations and Causality

An overview of the research toward bridging the gap between core database techniques and complementary techniques from machine learning and statistics via interdisciplinary collaborations, and employ them to applications in domains like computer science education, law, and health.

Distilling Causal Metaknowledge from Knowledge Graphs

A causal metaknowledge method for link prediction, which achieves entity-level link prediction by discovering concept-level topological causality and an efficient algorithm for discovering local causal relationships is proposed using the d -seperation criterion.

Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals

This paper empirically evaluates LEWIS on four real-world datasets and shows that it generates human-understandable explanations that improve upon state-of-the-art approaches in XAI, including the popular LIME and SHAP.

Tisane: Authoring Statistical Models via Formal Reasoning from Conceptual and Data Relationships

Tisane is presented, a mixed-initiative system for authoring generalized linear models with and without mixed-effects, and introduces a study design specification language for expressing and asking questions about relationships between variables.

HypeR: Hypothetical Reasoning With What-If and How-To Queries Using a Probabilistic Causal Approach

HypeR is developed, a framework that supports what-if and how-to queries accounting for Probabilistic dependencies among attributes captured by a probabilistic causal model and extends the SQL syntax to include the necessary operators for expressing these hypothetical queries.

Uncovering Latent Biases in Text: Method and Application to Peer Review

A novel framework to quantify bias in text caused by the visibility of subgroup membership indicators and shows evidence of biases in the review ratings that serves as “ground truth”, and shows that the proposed framework accurately detects the presence (and absence) of these biases from the review text without having access to the reviews.

Causal inference in statistics: An overview

This review presents empiricalresearcherswith recent advances in causal inference, and stresses the paradigmatic shifts that must be un- dertaken in moving from traditionalstatistical analysis to

Learning Causal Models of Relational Domains

This paper presents an algorithm, relational PC, that learns causal dependencies in a state-of-the-art relational representation, and identifies the key representational and algorithmic innovations that make the algorithm possible.

Causal inference, social networks and chain graphs

It is argued that, in some settings, chain graph models approximate the marginal distribution of a snapshot of a longitudinal data‐generating process on interacting units and is illustrated and justify a parsimonious parameterization for network data with interference and contagion.

For objective causal inference, design trumps analysis

For obtaining causal inferences that are objective, and therefore have the best chance of revealing scientific truths, carefully designed and executed randomized experiments are generally considered

Inferring Network Effects from Observational Data

It is shown that causal effects estimated on observational data with RCA are nearly as accurate as those estimated from well-designed network experiments, and can yield robust estimates of causal effects using common regression models without extensive parameter tuning.

On Learning Causal Models from Relational Data

This work describes RCD-Light, a sound and efficient constraint-based algorithm that is guaranteed to yield a correct partially-directed RCM structure with at least as many edges oriented as in that produced by RCD, the only other existing algorithm for learning RCM.

Reasoning about Independence in Probabilistic Models of Relational Data

This work provides a new representation, the abstract ground graph, that enables a sound, complete, and computationally ecient method for answering d-separation queries about relational models, and presents empirical results that demonstrate eectiveness.

Tracing data errors with view-conditioned causality

This work adapts the definitions of causality and responsibility for the case of multiple answers/views and provides a non-trivial algorithm that reduces the problem of finding causes and their responsibility to a satisfiability problem that can be solved with existing tools.

Matching as Nonparametric Preprocessing for Reducing Model Dependence in Parametric Causal Inference

A unified approach is proposed that makes it possible for researchers to preprocess data with matching and then to apply the best parametric techniques they would have used anyway and this procedure makes parametric models produce more accurate and considerably less model-dependent causal inferences.

Causal Inference Using Potential Outcomes

Causal effects are defined as comparisons of potential outcomes under different treatments on a common set of units. Observed values of the potential outcomes are revealed by the assignment