Online Causal Structure Learning in the Presence of Latent Variables

In this thesis, we propose to use Causal Models, which play a central role in dealing with uncertainty in Artificial Intelligence (AI). Causal models can be created based on information, data, or both. Regardless of the source of informa- tion used to create the model, there may be inaccuracies, or the application area may vary. Therefore, the model needs constant improvement during use. Most of existing learning algorithms are batch. However, industrial companies store vast amounts of data every day in real-world. Existing batch methods cannot process the significant quantity of continuously incoming data in a reasonable amount of time and memory. Therefore, batch methods may become computationally expen- sive and infeasible for large dataset. In this way, we present three online causal structure learning algorithms to fill this gap. These algorithms can track changes in a causal structure and process data in a dynamic real-time manner. Standard causal structure learning algorithms assume that causal structure does not change during the data collection process, but in real-world scenarios, it does often change. The online causal structure learning algorithms we present here can revise corre- lation values without reprocessing the entire dataset and use an existing model to avoid re-learning the causal links in the prior model, which still fit data. The algorithms update the correlations of causes and effects with the weight estima- tion of each causal interaction. Proposed algorithms are tested on synthetic and real-world datasets. The online causal structure learning algorithms outperformed a well known batch algorithm (FCI) by a large margin in learning the changed causal structure correctly and efficiently when latent variables were present.