Knowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher.

Rongzhi Zhang Jiaming Shen Tianqi Liu 0002 Jialu Liu Michael Bendersky Marc Najork Chao Zhang 0014 Knowledge Distillation with Perturbed Loss: From a Vanilla Teacher to a Proxy Teacher. 4278-4289 2024 KDD https://doi.org/10.1145/3637528.3671851 conf/kdd/2024 db/conf/kdd/kdd2024.html#ZhangS0LBNZ24