CLEAN: Psychometrically Consistent Incremental Cognitive Diagnosis under Concept-Space Expansion via Architectural Isolation
Read the original on arXiv Machine Learning →CLEAN (Continual Learning with Expandable and Architecturally Isolated Networks) is an incremental cognitive diagnosis framework that allows the concept space to grow while guaranteeing that historical diagnoses remain unchanged. It achieves this by freezing past diagnostic functions, applying orthogonal column masking to prevent gradient interference, and adding expandable full‑rank branches with micro‑variance initialization for new concepts. Experiments on three large‑scale educational datasets show that CLEAN attains zero Representation Drift, preserving old‑item metrics exactly while performing competitively on new items.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.