Federated learning-outcome prediction with multi-layer privacy protection

Learning-outcome prediction (LOP) is a long-standing and critical problem in educational routes. Many studies have contributed to developing effective models while often suffering from data shortage and weak generalization to various institutions due to the privacy-protection issue.

To address this challenge, a research team led by Zhang YUPEI published their new research on 15 December 2024 in Frontiers of Computer Science co-published by Higher Education Press and Springer Nature.

The team proposed a distributed grade prediction model, dubbed FecMap, by exploiting the federated learning (FL) framework that preserves the private data of local clients and communicates with others through a global generalized model. FecMap considers local subspace learning (LSL) and multi-layer privacy protection (MPP) to achieve client-specific classifiers of high performance on LOP per institution.

In the research, they achieve FecMap in an iteration manner with all datasets distributed on clients by training a local neural network composed of a global part, a local part, and a classification head in clients and averaging the global parts from clients on the server.

The experiment are performed online using three higher-educational datasets of student academic records. The experimental data shows that FecMap benefits from the proposed LSL and MPP and achieves steady performance on the task of LOP, compared with the state-of-the-art models.

Future work can focus on designing a more effective local model for accurately predicting the learning-outcome, and achieving industrial implementation practice to facilitate more users to use.

DOI: 10.1007/s11704-023-2791-8