Papers › AutoBERT-Zero: Evolving BERT Backbone from Scratch

AutoBERT-Zero: Evolving BERT Backbone from Scratch

15 Jul 2021arXiv:2107.07445archive 2025-07-28

Jiahui Gao, Hang Xu, Han Shi, Xiaozhe Ren, Philip L. H. Yu, Xiaodan Liang, Xin Jiang, Zhenguo Li

Transformer-based pre-trained language models like BERT and its variants have recently achieved promising performance in various natural language processing (NLP) tasks. However, the conventional paradigm constructs the backbone by purely stacking the manually designed global self-attention layers, introducing inductive bias and thus leads to sub-optimal. In this work, we make the first attempt to automatically discover novel pre-trained language model (PLM) backbone on a flexible search space containing the most fundamental operations from scratch. Specifically, we propose a well-designed search space which (i) contains primitive math operations in the intra-layer level to explore novel attention structures, and (ii) leverages convolution blocks to be the supplementary for attentions in the inter-layer level to better learn local dependency. To enhance the efficiency for finding promising architectures, we propose an Operation-Priority Neural Architecture Search (OP-NAS) algorithm, which optimizes both the search algorithm and evaluation of candidate models. Specifically, we propose Operation-Priority (OP) evolution strategy to facilitate model search via balancing exploration and exploitation. Furthermore, we design a Bi-branch Weight-Sharing (BIWS) training strategy for fast model evaluation. Extensive experiments show that the searched architecture (named AutoBERT-Zero) significantly outperforms BERT and its variants of different model capacities in various downstream tasks, proving the architecture's transfer and scaling abilities. Remarkably, AutoBERT-Zero-base outperforms RoBERTa-base (using much more data) and BERT-large (with much larger model size) by 2.4 and 1.4 higher score on GLUE test set.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Inductive Bias Language Modelling Math Neural Architecture Search Semantic Textual Similarity

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Semantic Textual Similarity	MRPC	AutoBERT-Zero (Large)	Accuracy	90.7%	#10 of 45	Archive leaderboard	report
Semantic Textual Similarity	MRPC	AutoBERT-Zero (Base)	Accuracy	90.5%	#12 of 45	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Convolution Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections