Cost-Efficient Hierarchical Knowledge Extraction with Deep Reinforcement Learning

We present a new classification task where a sample is represented by a tree -- a hierarchy of sets of objects and theirs properties. Individually for each sample, the task is to sequentially request pieces of information to build the hierarchy, where each new information can be further analyzed, and eventually provide a classification decision. Each piece of information has a real-valued cost and the objective is to maximize the accuracy in presence of a per-sample budget. Many problems can be represented in this manner, such as targeted advertising, medical diagnosis or malware detection. We build our method with a deep reinforcement learning algorithm and a set of techniques to process the hierarchical input and the complex action space. We demonstrate the method on seven relational classification datasets.