The Impact of Quantization on the Robustness of Transformer-based Text Classifiers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Neshaei, Seyed Parsa, Boreshban, Yasaman, Ghassem-Sani, Gholamreza, Mirroshandel, Seyed Abolghasem
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916152486133760
author Neshaei, Seyed Parsa
Boreshban, Yasaman
Ghassem-Sani, Gholamreza
Mirroshandel, Seyed Abolghasem
author_facet Neshaei, Seyed Parsa
Boreshban, Yasaman
Ghassem-Sani, Gholamreza
Mirroshandel, Seyed Abolghasem
contents Transformer-based models have made remarkable advancements in various NLP areas. Nevertheless, these models often exhibit vulnerabilities when confronted with adversarial attacks. In this paper, we explore the effect of quantization on the robustness of Transformer-based models. Quantization usually involves mapping a high-precision real number to a lower-precision value, aiming at reducing the size of the model at hand. To the best of our knowledge, this work is the first application of quantization on the robustness of NLP models. In our experiments, we evaluate the impact of quantization on BERT and DistilBERT models in text classification using SST-2, Emotion, and MR datasets. We also evaluate the performance of these models against TextFooler, PWWS, and PSO adversarial attacks. Our findings show that quantization significantly improves (by an average of 18.68%) the adversarial accuracy of the models. Furthermore, we compare the effect of quantization versus that of the adversarial training approach on robustness. Our experiments indicate that quantization increases the robustness of the model by 18.80% on average compared to adversarial training without imposing any extra computational overhead during training. Therefore, our results highlight the effectiveness of quantization in improving the robustness of NLP models.
format Preprint
id arxiv_https___arxiv_org_abs_2403_05365
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Impact of Quantization on the Robustness of Transformer-based Text Classifiers
Neshaei, Seyed Parsa
Boreshban, Yasaman
Ghassem-Sani, Gholamreza
Mirroshandel, Seyed Abolghasem
Computation and Language
Machine Learning
Transformer-based models have made remarkable advancements in various NLP areas. Nevertheless, these models often exhibit vulnerabilities when confronted with adversarial attacks. In this paper, we explore the effect of quantization on the robustness of Transformer-based models. Quantization usually involves mapping a high-precision real number to a lower-precision value, aiming at reducing the size of the model at hand. To the best of our knowledge, this work is the first application of quantization on the robustness of NLP models. In our experiments, we evaluate the impact of quantization on BERT and DistilBERT models in text classification using SST-2, Emotion, and MR datasets. We also evaluate the performance of these models against TextFooler, PWWS, and PSO adversarial attacks. Our findings show that quantization significantly improves (by an average of 18.68%) the adversarial accuracy of the models. Furthermore, we compare the effect of quantization versus that of the adversarial training approach on robustness. Our experiments indicate that quantization increases the robustness of the model by 18.80% on average compared to adversarial training without imposing any extra computational overhead during training. Therefore, our results highlight the effectiveness of quantization in improving the robustness of NLP models.
title The Impact of Quantization on the Robustness of Transformer-based Text Classifiers
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2403.05365