0

Weight-Inherited Distillation for Task-Agnostic BERT Compression

Weight-Inherited Distillation (WID) directly compresses BERT by inheriting weights and structural re-parameterization, outperforming previous knowledge distillation methods without additional alignment losses.

Year
2023
Venue
arXiv 2023
Authors
7
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2305.09098v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Knowledge Distillation (KD) is a predominant approach for BERT compression. Previous KD-based methods focus on designing extra alignment losses for the student model to mimic the behavior of the teacher model. These methods transfer the knowledge in an indirect way. In this paper, we propose a novel Weight-Inherited Distillation (WID), which directly transfers knowledge from the teacher. WID does not require any additional alignment loss and trains a compact student by inheriting the weights, showing a new perspective of knowledge distillation. Specifically, we design the row compactors and column compactors as mappings and then compress the weights via structural re-parameterization. Experimental results on the GLUE and SQuAD benchmarks show that WID outperforms previous state-of-the-art KD-based baselines. Further analysis indicates that WID can also learn the attention patterns from the teacher model without any alignment loss on attention distributions. The code is available at https://github.com/wutaiqiang/WID-NAACL2024.

Authors

7