pith. sign in

arxiv: 2006.00555 · v3 · pith:AOYCR7IFnew · submitted 2020-05-31 · 💻 cs.LG · cs.AI· stat.ML

Transferring Inductive Biases through Knowledge Distillation

classification 💻 cs.LG cs.AIstat.ML
keywords biasesinductivedistillationeffectknowledgedatadifferenthaving
0
0 comments X
read the original abstract

Having the right inductive biases can be crucial in many tasks or scenarios where data or computing resources are a limiting factor, or where training data is not perfectly representative of the conditions at test time. However, defining, designing and efficiently adapting inductive biases is not necessarily straightforward. In this paper, we explore the power of knowledge distillation for transferring the effect of inductive biases from one model to another. We consider families of models with different inductive biases, LSTMs vs. Transformers and CNNs vs. MLPs, in the context of tasks and scenarios where having the right inductive biases is critical. We study the effect of inductive biases on the solutions the models converge to and investigate how and to what extent the effect of inductive biases is transferred through knowledge distillation, in terms of not only performance but also different aspects of converged solutions.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding

    cs.CV 2026-04 unverdicted novelty 6.0

    A minimally modified vanilla Transformer called Volt achieves state-of-the-art 3D semantic and instance segmentation by using volumetric tokens, 3D rotary embeddings, and a data-efficient training recipe that scales b...