SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.09755 · 2021

RomeBERT: Robust Training of Multi-Exit BERT

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

BERT has achieved superior performances on Natural Language Understanding (NLU) tasks. However, BERT possesses a large number of parameters and demands certain resources to deploy. For acceleration, Dynamic Early Exiting for BERT (DeeBERT) has been proposed recently, which incorporates multiple exits and adopts a dynamic early-exit mechanism to ensure efficient inference. While obtaining an efficiency-performance tradeoff, the performances of early exits in multi-exit BERT are significantly worse than late exits. In this paper, we leverage gradient regularized self-distillation for RObust training of Multi-Exit BERT (RomeBERT), which can effectively solve the performance imbalance problem between early and late exits. Moreover, the proposed RomeBERT adopts a one-stage joint training strategy for multi-exits and the BERT backbone while DeeBERT needs two stages that require more training time. Extensive experiments on GLUE datasets are performed to demonstrate the superiority of our approach. Our code is available at https://github.com/romebert/RomeBERT.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2101.09755")
get_code_for_paper("2101.09755")
have("2101.09755")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2101.09755.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2101.09755.svg)](https://syntology.ai/paper/2101.09755)

Connect an agent — have() is free.