Efficiency for Free: Ideal Data Are Transportable Representations

TL;DR

This paper demonstrates that using a publicly available, task-agnostic prior model can generate efficient data for training, significantly reducing computational costs while maintaining accuracy in representation learning.

Contribution

It introduces the concept of task-agnostic prior models to produce efficient data, enabling faster and cost-effective representation learning.

Findings

Using a ResNet-18 prior reduces ImageNet training costs by 50%.

Efficient data from prior models maintains accuracy comparable to traditional methods.

The approach accelerates representation learning without sacrificing performance.

Abstract

Data, the seminal opportunity and challenge in modern machine learning, currently constrains the scalability of representation learning and impedes the pace of model evolution. In this work, we investigate the efficiency properties of data from both optimization and generalization perspectives. Our theoretical and empirical analysis reveals an unexpected finding: for a given task, utilizing a publicly available, task- and architecture-agnostic model (referred to as the `prior model' in this paper) can effectively produce efficient data. Building on this insight, we propose the Representation Learning Accelerator (\algopt), which promotes the formation and utilization of efficient data, thereby accelerating representation learning. Utilizing a ResNet-18 pre-trained on CIFAR-10 as a prior model to inform ResNet-50 training on ImageNet-1K reduces computational costs by 50% while maintaining the same accuracy as the model trained with the original BYOL, which requires 100% cost. Our code is available at: \url{https://github.com/LINs-lab/ReLA}.