Aligning Logits Generatively for Principled Black-Box Knowledge Distillation

arXiv:2205.10490v2 Announce Type: replace
Abstract: Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server. B2KD faces challenges such as limited Internet exchange and edge-cloud disparity of data distributions. In this paper, we formalize a two-step workflow consisting of deprivatization and distillation, and theoretically provide a new optimization direction from logits to cell boundary different from direct logits alignment. With its guidance, we propose a new method Mapping-Emulation KD …

abstract arxiv box challenges cloud compression cs.ai cs.cv cs.lg data distillation edge internet knowledge paper server stat.ml type workflow