ARTFEED — Contemporary Art Intelligence

CIST: Consistent Soft-Label Temperature for Knowledge Distillation

other · 2026-05-22

A new method called CIST (Consistently Informative Soft-label Temperature) addresses limitations in knowledge distillation by assigning separate, sample-adaptive temperatures to teacher and student models. Standard fixed-temperature distillation produces inconsistent entropy in teacher soft labels, with some predictions overly sharp and others over-smoothed. CIST ensures consistently informative soft labels, improving knowledge transfer from high-capacity teacher to compact student.

Key facts

  • CIST assigns separate temperatures to teacher and student models.
  • Standard fixed-temperature distillation is sample-agnostic.
  • CIST addresses inconsistent entropy in teacher soft labels.
  • CIST improves knowledge transfer from teacher to student.
  • The method is proposed in arXiv:2605.20357.
  • Knowledge distillation transfers knowledge via matching predictive distributions.
  • Temperature scaling exposes dark knowledge beyond hard labels.
  • CIST stands for Consistently Informative Soft-label Temperature.

Entities

Sources