knowledge-decoupling

This paper proposes a training-time backdoor defense called Trapping and Removing (TR), which introduces a lightweight shortcut branch as a honeypot to trap backdoor knowledge and then discards it, enhanced by a knowledge decoupling strategy with entropy-based weight assignment.

本文介绍了知识-几何解耦（KGD），一种用于流式推荐系统中预训练-迁移的方法。它将预训练的行为知识与任务特定的几何结构分离，使得模型能够持续刷新而互不干扰，并报告相比基线提升4%-12%，且已在Shopee成功部署。