Marzieh S. Tahaei
Research Subjects
Research Interests
Marzieh S. Tahaei has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Mehdi Rezagholizadeh
Huawei Noah's Ark Lab
2 shared publications - Vahid Partovi Nia
Huawei Noah's Ark Lab
2 shared publications - Ali Edalati
McGill University
1 shared publication - Ali Ghodsi
University of Waterloo
1 shared publication - Alireza Ghaffari
Huawei Noah's Ark Lab Montreal Canada
1 shared publication - Boxing Chen
Research Center Huawei Noah's Ark Lab Montreal Canada
1 shared publication
Latest Publications
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2129-2145
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
Parsa Kavehzadeh, Mojtaba Valipour, Marzieh Tahaei, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh. Findings of the Association for Computational Linguistics: EACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2129-2145
Open AccessSorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference
Parsa Kavehzadeh, Mojtaba Valipour, Marzieh Tahaei, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh. Findings of the Association for Computational Linguistics: EACL 2024. 2024.
- Open Access
Is Integer Arithmetic Enough for Deep Learning Training?
The ever-increasing computational complexity of deep learning models makes their training and deployment difficult on various cloud and edge platforms. Replacing floating-point arithmetic with low-bit integer arithmetic is a promising approach to save energy, memory footprint, and latency of deep learning models. As such, quantization has attracted the attention of researchers in recent years. However, using integer numbers to form a fully functional integer training pipeline including forward pass, back-propagation, and stochastic gradient descent is not studied in detail. Our empirical and mathematical results reveal that integer arithmetic seems to be enough to train deep learning models. Unlike recent proposals, instead of quantization, we directly switch the number representation of computations. Our novel training method forms a fully integer training pipeline that does not change the trajectory of the loss and accuracy compared to floating-point, nor does it need any special hyper-parameter tuning, distribution adjustment, or gradient clipping. Our experimental results show that our proposed method is effective in a wide variety of tasks such as classification (including vision transformers), object detection, and semantic segmentation.
Open AccessIs Integer Arithmetic Enough for Deep Learning Training?
The ever-increasing computational complexity of deep learning models makes their training and deployment difficult on various cloud and edge platforms. Replacing floating-point arithmetic with low-bit integer arithmetic is a promising approach to save energy, memory footprint, and latency of deep learning models. As such, quantization has attracted the attention of researchers in recent years. However, using integer numbers to form a fully functional integer training pipeline including forward pass, back-propagation, and stochastic gradient descent is not studied in detail. Our empirical and mathematical results reveal that integer arithmetic seems to be enough to train deep learning models. Unlike recent proposals, instead of quantization, we directly switch the number representation of computations. Our novel training method forms a fully integer training pipeline that does not change the trajectory of the loss and accuracy compared to floating-point, nor does it need any special hyper-parameter tuning, distribution adjustment, or gradient clipping. Our experimental results show that our proposed method is effective in a wide variety of tasks such as classification (including vision transformers), object detection, and semantic segmentation.
- Open Access
KronA: Parameter Efficient Tuning with Kronecker Adapter
Fine-tuning a Pre-trained Language Model (PLM) on a specific downstream task has been a well-known paradigm in Natural Language Processing. However, with the ever-growing size of PLMs, training the entire model on several downstream tasks becomes very expensive and resource-hungry. Recently, different Parameter Efficient Tuning (PET) techniques are proposed to improve the efficiency of fine-tuning PLMs. One popular category of PET methods is the low-rank adaptation methods which insert learnable truncated SVD modules into the original model either sequentially or in parallel. However, low-rank decomposition suffers from limited representation power. In this work, we address this problem using the Kronecker product instead of the low-rank representation. We introduce KronA, a Kronecker product-based adapter module for efficient fine-tuning of Transformer-based PLMs. We apply the proposed methods for fine-tuning T5 on the GLUE benchmark to show that incorporating the Kronecker-based modules can outperform state-of-the-art PET methods.
Open AccessKronA: Parameter Efficient Tuning with Kronecker Adapter
Fine-tuning a Pre-trained Language Model (PLM) on a specific downstream task has been a well-known paradigm in Natural Language Processing. However, with the ever-growing size of PLMs, training the entire model on several downstream tasks becomes very expensive and resource-hungry. Recently, different Parameter Efficient Tuning (PET) techniques are proposed to improve the efficiency of fine-tuning PLMs. One popular category of PET methods is the low-rank adaptation methods which insert learnable truncated SVD modules into the original model either sequentially or in parallel. However, low-rank decomposition suffers from limited representation power. In this work, we address this problem using the Kronecker product instead of the low-rank representation. We introduce KronA, a Kronecker product-based adapter module for efficient fine-tuning of Transformer-based PLMs. We apply the proposed methods for fine-tuning T5 on the GLUE benchmark to show that incorporating the Kronecker-based modules can outperform state-of-the-art PET methods.