Understanding and Improving Knowledge Distillation for Quantization Aware Training of Large Transformer Encoders
Minsoo Kim, Sihwa Lee, Suk-Jin Hong, Du-Seong Chang, Jungwook Choi
Abstract
Knowledge distillation (KD) has been a ubiquitous method for model compression to strengthen the capability of a lightweight model with the transferred knowledge from the teacher. In particular, KD has been employed in quantization-aware training (QAT) of Transformer encoders like BERT to improve the accuracy of the student model with the reduced-precision weight parameters. However, little is understood about which of the various KD approaches best fits the QAT of Transformers. In this work, we provide an in-depth analysis of the mechanism of KD on attention recovery of quantized large Transformers. In particular, we reveal that the previously adopted MSE loss on the attention score is insufficient for recovering the self-attention information. Therefore, we propose two KD methods; attention-map and attention-output losses. Furthermore, we explore the unification of both losses to address task-dependent preference between attention-map and output losses. The experimental results on various Transformer encoder models demonstrate that the proposed KD methods achieve state-of-the-art accuracy for QAT with sub-2-bit weight quantization.- Anthology ID:
- 2022.emnlp-main.450
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6713–6725
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.450
- DOI:
- 10.18653/v1/2022.emnlp-main.450
- Cite (ACL):
- Minsoo Kim, Sihwa Lee, Suk-Jin Hong, Du-Seong Chang, and Jungwook Choi. 2022. Understanding and Improving Knowledge Distillation for Quantization Aware Training of Large Transformer Encoders. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6713–6725, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Understanding and Improving Knowledge Distillation for Quantization Aware Training of Large Transformer Encoders (Kim et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2022.emnlp-main.450.pdf