Skip to content
All papers

Distilling the Knowledge in a Neural Network

Geoffrey Hinton, Oriol Vinyals, Jeff Dean2015arXiv 2015

Read it on arxiv.org(opens in a new tab)

Why this one

The useful idea here is not that a small model can copy a big model. It is that the big model's wrong answers contain signal. A label says “cat”; a softened teacher distribution says “cat, but fox and dog are the nearby mistakes, not toaster.” That ranking is often a better training target than the dataset itself. People still get distillation wrong by treating it as generic compression, then measuring only final accuracy. For an engineer, the real question is whether you can spend training compute once to buy cheaper latency, memory, and fleet cost forever. Read this after Scaling Laws for Neural Language Models if you want the practical counterweight: scaling tells you why the teacher is expensive, distillation tells you how to stop serving it everywhere. It also sets up later inference papers like LLM.int8() and GPTQ, which shrink numbers, while this shrinks behavior.

What to take away

  • Soft targets teach similarity between classes, not just the winning label.
  • Temperature is the knob that exposes dark knowledge in the teacher distribution.
  • Distillation trades offline training cost for lower online serving cost.

Reads with

Where it lands in the course

Inference Engineering · Fewer Bytes, Fewer Steps