Faculty Distillation with Optimal Transport. (arXiv:2204.11526v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2204.11526

The outpouring of various pre-trained models empowers knowledge
distillation~(KD) by providing abundant teacher resources. Meanwhile, exploring
the massive model repository to select a suitable teacher and further
extracting its knowledge become daunting challenges. Standard KD fails to
surmount two obstacles when training a student with the availability of
plentiful pre-trained teachers, i.e., the "faculty". First, we need to seek out
the most contributive teacher in the faculty efficiently rather than
enumerating all of them for a student. Second, since the …

arxiv distillation faculty lg transport