An official website of the United States government
Abstract Intelligence involves processing sensory experiences into representations useful for prediction. Understanding sensory experiences and building these contextual representations without prior knowledge of sensor models and environment is a challenging unsupervised learning problem. Current machine learning methods process new sensory data using prior knowledge defined by either domain knowledge or datasets. When datasets are not available, data acquisition is needed, though automating exploration in support of learning is still an unsolved problem. Here we develop a method that enables agents to efficiently collect data for learning a predictive sensor model—without requiring domain knowledge, human input, or previously existing data—using ergodicity to specify the data acquisition process. This approach is based entirely on data-driven sensor characteristics rather than predefined knowledge of the sensor model and its physical characteristics. We learn higher quality models with lower energy expenditure during exploration for data acquisition compared to competing approaches, including both random sampling and information maximization. In addition to applications in autonomy, our approach provides a potential model of how animals use their motor control to develop high quality models of their sensors (sight, sound, touch) before having knowledge of their sensor capabilities or their surrounding environment.
more »
« less
KCRL: A Prior Knowledge Based Causal Discovery Framework With Reinforcement Learning
Causal discovery is an important problem in many sciences that enables us to estimate causal relationships from observational data. Particularly, in the healthcare domain, it can guide practitioners in making informed clinical decisions. Several causal discovery approaches have been developed over the last few decades. The success of these approaches mostly relies on a large number of data samples. In practice, however, an infinite amount of data is never available. Fortunately, often we have some prior knowledge available from the problem domain. Particularly, in healthcare settings, we often have some prior knowledge such as expert opinions, prior RCTs, literature evidence, and systematic reviews about the clinical problem. This prior information can be utilized in a systematic way to address the data scarcity problem. However, most of the existing causal discovery approaches lack a systematic way to incorporate prior knowledge during the search process. Recent advances in reinforcement learning techniques can be explored to use prior knowledge as constraints by penalizing the agent for their violations. Therefore, in this work, we propose a framework KCRL that utilizes the existing knowledge as a constraint to penalize the search process during causal discovery. This utilization of existing information during causal discovery reduces the graph search space and enables a faster convergence to the optimal causal mechanism. We evaluated our framework on benchmark synthetic and real datasets as well as on a real-life healthcare application. We also compared its performance with several baseline causal discovery methods. The experimental findings show that penalizing the search process for constraint violation yields better performance compared to existing approaches that do not include prior knowledge.
more »
« less
- Award ID(s):
- 2118285
- PAR ID:
- 10343976
- Date Published:
- Journal Name:
- Proceedings of Machine Learning Research
- Volume:
- 182
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Complex causal networks underlie many real-world problems, from the regulatory interactions between genes to the environmental patterns used to understand climate change. Computational methods seek to infer these causal networks using observational data and domain knowledge. In this paper, we identify three key requirements for inferring the structure of causal networks for scientific discovery: (1) robustness to noise in observed measurements; (2) scalability to handle hundreds of variables; and (3) flexibility to encode domain knowledge and other structural constraints. We first formalize the problem of joint probabilistic causal structure discovery. We develop an approach using probabilistic soft logic (PSL) that exploits multiple statistical tests, supports efficient optimization over hundreds of variables, and can easily incorporate structural constraints, including imperfect domain knowledge. We compare our method against multiple well-studied approaches on biological and synthetic datasets, showing improvements of up to 20% in F1-score over the best performing baseline in realistic settings.more » « less
-
Missing data are ubiquitous in many domain such as healthcare. When these data entries are not missing completely at random, the (conditional) independence relations in the observed data may be different from those in the complete data generated by the underlying causal process.Consequently, simply applying existing causal discovery methods to the observed data may lead to wrong conclusions. In this paper, we aim at developing a causal discovery method to recover the underlying causal structure from observed data that are missing under different mechanisms, including missing completely at random (MCAR),missing at random (MAR), and missing not at random (MNAR). With missingness mechanisms represented by missingness graphs (m-graphs),we analyze conditions under which additional correction is needed to derive conditional independence/dependence relations in the complete data. Based on our analysis, we propose Miss-ing Value PC (MVPC), which extends the PC algorithm to incorporate additional corrections.Our proposed MVPC is shown in theory to give asymptotically correct results even on data that are MAR or MNAR. Experimental results on both synthetic data and real healthcare applications illustrate that the proposed algorithm is able to find correct causal relations even in the general case of MNAR.more » « less
-
Causal inference is at the heart of empirical research in natu- ral and social sciences and is critical for scientific discovery and informed decision making. The gold standard in causal inference is performing randomized controlled trials; unfortu- nately 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 sta- tistical studies and social sciences. However, existing meth- ods 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 set- tings, 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 infer- ring 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.more » « less
-
Abstract ObjectiveEarly identification of chronic diseases is a pillar of precision medicine as it can lead to improved outcomes, reduction of disease burden, and lower healthcare costs. Predictions of a patient’s health trajectory have been improved through the application of machine learning approaches to electronic health records (EHRs). However, these methods have traditionally relied on “black box” algorithms that can process large amounts of data but are unable to incorporate domain knowledge, thus limiting their predictive and explanatory power. Here, we present a method for incorporating domain knowledge into clinical classifications by embedding individual patient data into a biomedical knowledge graph. Materials and MethodsA modified version of the Page rank algorithm was implemented to embed millions of deidentified EHRs into a biomedical knowledge graph (SPOKE). This resulted in high-dimensional, knowledge-guided patient health signatures (ie, SPOKEsigs) that were subsequently used as features in a random forest environment to classify patients at risk of developing a chronic disease. ResultsOur model predicted disease status of 5752 subjects 3 years before being diagnosed with multiple sclerosis (MS) (AUC = 0.83). SPOKEsigs outperformed predictions using EHRs alone, and the biological drivers of the classifiers provided insight into the underpinnings of prodromal MS. ConclusionUsing data from EHR as input, SPOKEsigs describe patients at both the clinical and biological levels. We provide a clinical use case for detecting MS up to 5 years prior to their documented diagnosis in the clinic and illustrate the biological features that distinguish the prodromal MS state.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
