PrivacyCD: Hierarchical Unlearning for Protecting Student Privacy in Cognitive Diagnosis

TL;DR

This paper introduces PrivacyCD, a hierarchical unlearning algorithm tailored for cognitive diagnosis models, enabling effective removal of student data to enhance privacy without sacrificing model performance.

Contribution

It presents the first systematic study of data unlearning in CD models and proposes HIF, a novel importance-guided unlearning algorithm leveraging layer-wise parameter importance.

Findings

HIF outperforms baseline methods on real datasets.

Effective data removal with minimal impact on model utility.

First solution for privacy-preserving cognitive diagnosis models.

Abstract

The need to remove specific student data from cognitive diagnosis (CD) models has become a pressing requirement, driven by users' growing assertion of their "right to be forgotten". However, existing CD models are largely designed without privacy considerations and lack effective data unlearning mechanisms. Directly applying general purpose unlearning algorithms is suboptimal, as they struggle to balance unlearning completeness, model utility, and efficiency when confronted with the unique heterogeneous structure of CD models. To address this, our paper presents the first systematic study of the data unlearning problem for CD models, proposing a novel and efficient algorithm: hierarchical importanceguided forgetting (HIF). Our key insight is that parameter importance in CD models exhibits distinct layer wise characteristics. HIF leverages this via an innovative smoothing mechanism that combines individual and layer, level importance, enabling a more precise distinction of parameters associated with the data to be unlearned. Experiments on three real world datasets show that HIF significantly outperforms baselines on key metrics, offering the first effective solution for CD models to respond to user data removal requests and for deploying high-performance, privacy preserving AI systems