Papers
arxiv:2110.10343

EBJR: Energy-Based Joint Reasoning for Adaptive Inference

Published on Oct 20, 2021
Authors:
,

Abstract

The Energy-Based Joint Reasoning framework combines large and small models to achieve high accuracy with low latency, using pre-trained models without architecture changes or re-training.

AI-generated summary

State-of-the-art deep learning models have achieved significant performance levels on various benchmarks. However, the excellent performance comes at a cost of inefficient computational cost. Light-weight architectures, on the other hand, achieve moderate accuracies, but at a much more desirable latency. This paper presents a new method of jointly using the large accurate models together with the small fast ones. To this end, we propose an Energy-Based Joint Reasoning (EBJR) framework that adaptively distributes the samples between shallow and deep models to achieve an accuracy close to the deep model, but latency close to the shallow one. Our method is applicable to out-of-the-box pre-trained models as it does not require an architecture change nor re-training. Moreover, it is easy to use and deploy, especially for cloud services. Through a comprehensive set of experiments on different down-stream tasks, we show that our method outperforms strong state-of-the-art approaches with a considerable margin. In addition, we propose specialized EBJR, an extension of our method where we create a smaller specialized side model that performs the target task only partially, but yields an even higher accuracy and faster inference. We verify the strengths of our methods with both theoretical and experimental evaluations.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2110.10343 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2110.10343 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2110.10343 in a Space README.md to link it from this page.

Collections including this paper 1