Manipulating Predictions over Discrete Inputs in Machine Teaching
This addresses the need for efficient data manipulation in machine teaching for discrete inputs, with applications in both corrective and malicious scenarios, though it is incremental in scope.
The paper tackles the problem of manipulating machine learning model predictions in the discrete domain by optimizing training data, achieving superior performance in efficiency and effectiveness compared to baselines.
Machine teaching often involves the creation of an optimal (typically minimal) dataset to help a model (referred to as the `student') achieve specific goals given by a teacher. While abundant in the continuous domain, the studies on the effectiveness of machine teaching in the discrete domain are relatively limited. This paper focuses on machine teaching in the discrete domain, specifically on manipulating student models' predictions based on the goals of teachers via changing the training data efficiently. We formulate this task as a combinatorial optimization problem and solve it by proposing an iterative searching algorithm. Our algorithm demonstrates significant numerical merit in the scenarios where a teacher attempts at correcting erroneous predictions to improve the student's models, or maliciously manipulating the model to misclassify some specific samples to the target class aligned with his personal profits. Experimental results show that our proposed algorithm can have superior performance in effectively and efficiently manipulating the predictions of the model, surpassing conventional baselines.