BinaryBERT: Pushing the Limit of BERT Quantization
- URL: http://arxiv.org/abs/2012.15701v1
- Date: Thu, 31 Dec 2020 16:34:54 GMT
- Title: BinaryBERT: Pushing the Limit of BERT Quantization
- Authors: Haoli Bai, Wei Zhang, Lu Hou, Lifeng Shang, Jing Jin, Xin Jiang, Qun
Liu, Michael Lyu, Irwin King
- Abstract summary: We propose BinaryBERT, which pushes BERT quantization to the limit with weight binarization.
We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscapes.
Empirical results show that BinaryBERT has negligible performance drop compared to the full-precision BERT-base.
- Score: 74.65543496761553
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The rapid development of large pre-trained language models has greatly
increased the demand for model compression techniques, among which quantization
is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT
quantization to the limit with weight binarization. We find that a binary BERT
is hard to be trained directly than a ternary counterpart due to its complex
and irregular loss landscapes. Therefore, we propose ternary weight splitting,
which initializes the binary model by equivalent splitting from a half-sized
ternary network. The binary model thus inherits the good performance of the
ternary model, and can be further enhanced by fine-tuning the new architecture
after splitting. Empirical results show that BinaryBERT has negligible
performance drop compared to the full-precision BERT-base while being
$24\times$ smaller, achieving the state-of-the-art results on GLUE and SQuAD
benchmarks.
Related papers
- Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients [51.82488018573326]
We present QP-SBGD, a novel layer-wise optimiser tailored towards training neural networks with binary weights.
BNNs reduce the computational requirements and energy consumption of deep learning models with minimal loss in accuracy.
Our algorithm is implemented layer-wise, making it suitable to train larger networks on resource-limited quantum hardware.
arXiv Detail & Related papers (2023-10-23T17:32:38Z) - MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided
Adaptation [68.30497162547768]
We propose MoEBERT, which uses a Mixture-of-Experts structure to increase model capacity and inference speed.
We validate the efficiency and effectiveness of MoEBERT on natural language understanding and question answering tasks.
arXiv Detail & Related papers (2022-04-15T23:19:37Z) - The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for
Large Language Models [23.12519490211362]
This paper studies the accuracy-compression trade-off for unstructured weight pruning in the context of BERT models.
We introduce Optimal BERT Surgeon (O-BERT-S), an efficient and accurate weight pruning method based on approximate second-order information.
We investigate the impact of this pruning method when compounding compression approaches for Transformer-based models.
arXiv Detail & Related papers (2022-03-14T16:40:31Z) - BiBERT: Accurate Fully Binarized BERT [69.35727280997617]
BiBERT is an accurate fully binarized BERT to eliminate the performance bottlenecks.
Our method yields impressive 56.3 times and 31.2 times saving on FLOPs and model size.
arXiv Detail & Related papers (2022-03-12T09:46:13Z) - Deploying a BERT-based Query-Title Relevance Classifier in a Production
System: a View from the Trenches [3.1219977244201056]
Bidirectional Representations from Transformers (BERT) model has been radically improving the performance of many Natural Language Processing (NLP) tasks.
It is challenging to scale BERT for low-latency and high- throughput industrial use cases due to its enormous size.
We successfully optimize a Query-Title Relevance (QTR) classifier for deployment via a compact model, which we name BERT Bidirectional Long Short-Term Memory (BertBiLSTM)
BertBiLSTM exceeds the off-the-shelf BERT model's performance in terms of accuracy and efficiency for the aforementioned real-world production task
arXiv Detail & Related papers (2021-08-23T14:28:23Z) - TernaryBERT: Distillation-aware Ultra-low Bit BERT [53.06741585060951]
We propose TernaryBERT, which ternarizes the weights in a fine-tuned BERT model.
Experiments on the GLUE benchmark and SQuAD show that our proposed TernaryBERT outperforms the other BERT quantization methods.
arXiv Detail & Related papers (2020-09-27T10:17:28Z) - DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference [69.93692147242284]
Large-scale pre-trained language models such as BERT have brought significant improvements to NLP applications.
We propose a simple but effective method, DeeBERT, to accelerate BERT inference.
Experiments show that DeeBERT is able to save up to 40% inference time with minimal degradation in model quality.
arXiv Detail & Related papers (2020-04-27T17:58:05Z) - TwinBERT: Distilling Knowledge to Twin-Structured BERT Models for
Efficient Retrieval [11.923682816611716]
We present TwinBERT model for effective and efficient retrieval.
It has twin-structured BERT-like encoders to represent query and document respectively.
It allows document embeddings to be pre-computed offline and cached in memory.
arXiv Detail & Related papers (2020-02-14T22:44:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.