Causal Learning Algorithms Research Articles

Multi-Granularity Causal Structure Learning

Unveiling, modeling, and comprehending the causal mechanisms underpinning natural phenomena stand as fundamental endeavors across myriad scientific disciplines. Meanwhile, new knowledge emerges when discovering causal relationships from data. Existing causal learning algorithms predominantly focus on the isolated effects of variables, overlook the intricate interplay of multiple variables and their collective behavioral patterns. Furthermore, the ubiquity of high-dimensional data exacts a substantial temporal cost for causal algorithms. In this paper, we develop a novel method called MgCSL (Multi-granularity Causal Structure Learning), which first leverages sparse auto-encoder to explore coarse-graining strategies and causal abstractions from micro-variables to macro-ones. MgCSL then takes multi-granularity variables as inputs to train multilayer perceptrons and to delve the causality between variables. To enhance the efficacy on high-dimensional data, MgCSL introduces a simplified acyclicity constraint to adeptly search the directed acyclic graph among variables. Experimental results show that MgCSL outperforms competitive baselines, and finds out explainable causal connections on fMRI datasets.

Federated Causality Learning with Explainable Adaptive Optimization

Discovering the causality from observational data is a crucial task in various scientific domains. With increasing awareness of privacy, data are not allowed to be exposed, and it is very hard to learn causal graphs from dispersed data, since these data may have different distributions. In this paper, we propose a federated causal discovery strategy (FedCausal) to learn the unified global causal graph from decentralized heterogeneous data. We design a global optimization formula to naturally aggregate the causal graphs from client data and constrain the acyclicity of the global graph without exposing local data. Unlike other federated causal learning algorithms, FedCausal unifies the local and global optimizations into a complete directed acyclic graph (DAG) learning process with a flexible optimization objective. We prove that this optimization objective has a high interpretability and can adaptively handle homogeneous and heterogeneous data. Experimental results on synthetic and real datasets show that FedCausal can effectively deal with non-independently and identically distributed (non-iid) data and has a superior performance.

Fault Injection Based Interventional Causal Learning for Distributed Applications

We apply the machinery of interventional causal learning with programmable interventions to the domain of applications management. Modern applications are modularized into interdependent components or services (e.g. microservices) for ease of development and management. The communication graph among such components is a function of application code and is not always known to the platform provider. In our solution we learn this unknown communication graph solely using application logs observed during the execution of the application by using fault injections in a staging environment. Specifically, we have developed an active (or interventional) causal learning algorithm that uses the observations obtained during fault injections to learn a model of error propagation in the communication among the components. The “power of intervention” additionally allows us to address the presence of confounders in unobserved user interactions. We demonstrate the effectiveness of our solution in learning the communication graph of well-known microservice application benchmarks. We also show the efficacy of the solution on a downstream task of fault localization in which the learned graph indeed helps to localize faults at runtime in a production environment (in which the location of the fault is unknown). Additionally, we briefly discuss the implementation and deployment status of a fault injection framework which incorporates the developed technology.

Deep causal learning for robotic intelligence.

This invited Review discusses causal learning in the context of robotic intelligence. The Review introduces the psychological findings on causal learning in human cognition, as well as the traditional statistical solutions for causal discovery and causal inference. Additionally, we examine recent deep causal learning algorithms, with a focus on their architectures and the benefits of using deep nets, and discuss the gap between deep causal learning and the needs of robotic intelligence.

Ensemble framework for causality learning with heterogeneous Directed Acyclic Graphs through the lens of optimization

Directed Acyclic Graphs (DAGs) are informative graphical outputs of causal learning algorithms to visualize the causal structure among variables. In practice, different causal learning algorithms are often used to establish a comprehensive analysis pool, which leads to the challenging problem of ensembling the heterogeneous DAGs with diverse and conflicting embedded information. While naive approaches such as MEDIAN and greedy heuristics are presented in the literature, a mathematical framework to build the ensemble DAG is not investigated. Therefore, we propose a two-stage ensemble framework for causality learning with heterogeneous DAGs. In the first stage, we implement a data partitioning procedure to categorize the input data. Then, we apply multiple causal learning algorithms to each class and ensemble the results across the partitions for each method. The results across different approaches in the second stage are then ensembled to produce the final DAG. We define a novel mathematical model based on the marginal contribution concept, reflecting the collective information for each edge from input graphs. We investigate the relationship between the proposed modeling approach and well-known problems such as rank aggregation and the Traveling Salesman Problem. We also present a parametric analysis for the distance function, enriched by insights from their asymptotic behavior. We design a simulation experiment to show the computational advantage of adopting a lazy constraints solution approach. In addition to the T-cell synthetic dataset, we use the dataset of water main breaks from 2017 to 2021 in the City of Tampa, Florida, to demonstrate the framework’s applicability. The results show that the optimal solution of the proposed framework outperforms current approaches in the literature based on causality-based Structural Intervention Distance performance measures.

Evaluation Methods and Measures for Causal Learning Algorithms

The convenient access to copious multifaceted data has encouraged machine learning researchers to reconsider correlation-based learning and embrace the opportunity of causality-based learning, i.e., causal machine learning (causal learning). Recent years have, therefore, witnessed great effort in developing causal learning algorithms aiming to help artificial intelligence (AI) achieve human-level intelligence. Due to the lack of ground-truth data, one of the biggest challenges in current causal learning research is algorithm evaluations. This largely impedes the cross-pollination of AI and causal inference and hinders the two fields to benefit from the advances of the other. To bridge from conventional causal inference (i.e., based on statistical methods) to causal learning with Big Data (i.e., the intersection of causal inference and machine learning), in this survey, we review commonly used datasets, evaluation methods, and measures for causal learning using an evaluation pipeline similar to conventional machine learning. We focus on the two fundamental causal inference tasks and causality-aware machine learning tasks. Limitations of current evaluation procedures are also discussed. We, then, examine popular causal inference tools/packages and conclude with primary challenges and opportunities for benchmarking causal learning algorithms in the era of Big Data. The survey seeks to bring to the forefront the urgency of developing publicly available benchmarks and consensus-building standards for causal learning evaluation with observational data. In doing so, we hope to broaden the discussions and facilitate collaboration to advance the innovation and application of causal learning.

Causal learner: A toolbox for causal structure and Markov blanket learning

Causal Learner is a toolbox for learning causal structure and Markov blanket (MB) from data. It integrates functions for generating simulated Bayesian network data, a set of state-of-the-art global causal structure learning algorithms, a set of state-of-the-art local causal structure learning algorithms, a set of state-of-the-art MB learning algorithms, and functions for evaluating algorithms. The data generation part of Causal Learner is written in R, and the rest of Causal Learner is written in MATLAB. Causal Learner aims to provide researchers and practitioners with an open-source platform for causal learning from data and for the development and evaluation of new causal learning algorithms. The Causal Learner project is available at http://bigdata.ahu.edu.cn/causal-learner.

A new local causal learning algorithm applied in learning analytics

PurposeThe paper aims to present a new two stage local causal learning algorithm – HEISA. In the first stage, the algorithm discoveries the subset of features that better explains a target variable. During the second stage, computes the causal effect, using partial correlation, of each feature of the selected subset. Using this new algorithm, the study aims to identify the actions that lead a student succeed or failure in a course.Design/methodology/approachThe paper presents a brief review of main concepts used in this study: Causal Learning and Causal effects. The paper also discusses the results of applying the algorithm in education data set. Data used in this study was extracted from the log of actions of a Learning Management System, Moodle. These actions represent the behavior of 229 engineering students that take Algorithm and Data Structure course offered in a blended model.FindingsThe algorithm proposed in the paper identifies that features with weak relevance to a target may become relevant when computing the direct effect.Research limitations/implicationsThe algorithm needs to be improved to automatically discard attributes that are under a specific threshold of direct effect. Researchers are also encouraged to test the proposed propositions further.Practical implicationsThe algorithm presented in this paper can be used to identify the mostly relevant features given a classification task.Originality/valueThis paper computes the direct effect of a selected subset of features in a target variable to evaluate if a variable in this subset is really a cause of the target or if it is a spurious correlation.

Effects of the Swiss Franc/Euro Exchange Rate Floor on the Calibration of Probability Forecasts

Probability forecasts of the Swiss franc/euro (CHF/EUR) exchange rate are generated before, surrounding and after the placement of a floor on the CHF/EUR by the Swiss National Bank (SNB). The goal is to determine whether the exchange rate floor has a positive, negative or insignificant effect on the calibration of the probability forecasts from three time-series models: a vector autoregression (VAR) model, a VAR model augmented with the LiNGAM causal learning algorithm, and a univariate autoregressive model built on the independent components (ICs) of an independent component analysis (ICA). Score metric rankings of forecasts and plots of calibration functions are used in an attempt to identify the preferred time-series model based on forecast performance. The study not only finds evidence that the floor on the CHF/EUR has a negative impact on the forecasting performance of all three time-series models but also that the policy change by the SNB altered the causal structure underlying the six major currencies.

Causal Discovery Using Regression-Based Conditional Independence Tests

Conditional independence (CI) testing is an important tool in causal discovery. Generally, by using CI tests, a set of Markov equivalence classes w.r.t. the observed data can be estimated by checking whether each pair of variables x and y is d-separated, given a set of variables Z. Due to the curse of dimensionality, CI testing is often difficult to return a reliable result for high-dimensional Z. In this paper, we propose a regression-based CI test to relax the test of x ⊥ y|Z to simpler unconditional independence tests of x − f(Z) ⊥ y−g(Z), and x−f(Z) ⊥ Z or y−g(Z) ⊥ Z under the assumption that the data-generating procedure follows additive noise models (ANMs). When the ANM is identifiable, we prove that x − f(Z) ⊥ y − g(Z) ⇒ x ⊥ y|Z. We also show that 1) f and g can be easily estimated by regression, 2) our test is more powerful than the state-of-the-art kernel CI tests, and 3) existing causal learning algorithms can infer much more causal directions by using the proposed method.

Learning Causal Graphs with Latent Confounders in Weak Faithfulness Violations

Learning causal models hidden in the background of observational data has been a difficult issue. Dealing with latent common causes and selection bias for constructing causal models in real data is often necessary because observing all relevant variables is difficult. Ancestral graph models are effective and useful for representing causal models with some information of such latent variables. The causal faithfulness condition, which is usually assumed for determining the models, is known to often be weakly violated in statistical view points for finite data. One of the authors developed a constraint-based causal learning algorithm that is robust against the weak violations while assuming no latent variables. In this study, we applied and extended the thoughts of the algorithm to the inference of ancestral graph models. The practical validity and effectiveness of the algorithm are also confirmed by using some standard datasets in comparison with FCI and RFCI algorithms.

The assembly of miRNA-mRNA-protein regulatory networks using high-throughput expression data.

Inference of gene regulatory networks from high throughput measurement of gene and protein expression is particularly attractive because it allows the simultaneous discovery of interactive molecular signals for numerous genes and proteins at a relatively low cost. We developed two score-based local causal learning algorithms that utilized the Markov blanket search to identify direct regulators of target mRNAs and proteins. These two algorithms were specifically designed for integrated high throughput RNA and protein data. Simulation study showed that these algorithms outperformed other state-of-the-art gene regulatory network learning algorithms. We also generated integrated miRNA, mRNA, and protein expression data based on high throughput analysis of primary trophoblasts, derived from term human placenta and cultured under standard or hypoxic conditions. We applied the new algorithms to these data and identified gene regulatory networks for a set of trophoblastic proteins found to be differentially expressed under the specified culture conditions.