Transfer Learning using Representation Learning in Massive Open Online Courses
This work addresses the challenge of timely intervention and feedback in MOOCs by enhancing predictive models for student behavior, though it appears incremental as it builds on existing transfer learning methods.
The paper tackled the problem of poor prediction performance when transferring student dropout models across MOOCs by proposing an automated transductive transfer learning approach using representation learning with auto-encoders, resulting in improved model transferability across similar and dissimilar courses.
In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must rely on models trained from the historical data of previously offered courses. It is possible to transfer models, but they often have poor prediction performance. One reason is features that inadequately represent predictive attributes common to both courses. We present an automated transductive transfer learning approach that addresses this issue. It relies on problem-agnostic, temporal organization of the MOOC clickstream data, where, for each student, for multiple courses, a set of specific MOOC event types is expressed for each time unit. It consists of two alternative transfer methods based on representation learning with auto-encoders: a passive approach using transductive principal component analysis and an active approach that uses a correlation alignment loss term. With these methods, we investigate the transferability of dropout prediction across similar and dissimilar MOOCs and compare with known methods. Results show improved model transferability and suggest that the methods are capable of automatically learning a feature representation that expresses common predictive characteristics of MOOCs.