Gated subspace alignment with drift compensation for parameter-efficient Class-Incremental Learning

Jianye Gu, Shucheng Huang, Tian Li, Senbao Zhang, Mingxing Li · 2026

Read Gated subspace alignment with drift compensation for parameter-efficient Class-Incremental Learning by Jianye Gu, Shucheng Huang, Tian Li, Senbao Zhang, Mingxing Li (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0348270.txt.

Description

Jianye Gu and co-workers tackle a stubborn problem for learning machines: adding new categories over time without forgetting old ones. As models expand their inner feature spaces, memories of earlier classes drift and blur. Their 2026 method freezes the core network and adds tiny gated adapters for each new task, building separate subspaces that still share information through attention.

A learned mapping then lines old class memories up inside the newest space, all without revisiting old training data. Benchmark tests showed better accuracy and stronger resistance to forgetting than rival approaches. Keeping the core frozen also kept computing costs low. The design suits tools that must keep learning on the job, from photo sorting to medical screening.

Catalog record

CREATORJianye Gu, Shucheng Huang, Tian Li, Senbao Zhang, Mingxing Li
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE65266
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0348270

Browse the full library · About the Tower of Babel