Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers
Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-aware training (QAT) is a promising method to lower the implementation cost and energy consumption. However, aggressive quantization below 2-bit causes considerable accuracy degradation due to unstable convergence, especially when the downstream dataset is not abundant. This work proposes a proactive knowledge distillation method called Teacher Intervention (TI) for fast converging QAT of ultra-low precision pre-trained Transformers. TI intervenes layer-wise signal propagation with the intact signal from the teacher to remove the interference of propagated quantization errors, smoothing loss surface of QAT and expediting the convergence. Furthermore, we propose a gradual intervention mechanism to stabilize the recovery of subsections of Transformer layers from quantization. The proposed schemes enable fast convergence of QAT and improve the model accuracy regardless of the diverse characteristics of downstream fine-tuning tasks. We demonstrate that TI consistently achieves superior accuracy with significantly lower fine-tuning iterations on well-known Transformers of natural language processing as well as computer vision compared to the state-of-the-art QAT methods.
Code (1)
Tasks
Knowledge DistillationQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation
As edge devices become prevalent, deploying Deep Neural Networks (DNN) on edge devices has become a critical issue. However, DNN requires a high computational resource which is rarely available for edge devices. To handl…
Keyword SpottingKnowledge DistillationModel CompressionQuantizationQKD: Quantization-aware Knowledge Distillation
Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge devices. Although their combination is …
Knowledge DistillationQuantizationEfficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training
Efficient single-image super-resolution (SISR) requires balancing reconstruction fidelity, model compactness, and robustness under low-bit deployment, which is especially challenging for x3 SR. We present a deployment-or…
Image Super-ResolutionQ$^2$: Quantization-Aware Gradient Balancing and Attention Alignment for Low-Bit Quantization
Quantization-aware training (QAT) has achieved remarkable success in low-bit ($\leq$4-bit) quantization for classification networks. However, when applied to more complex visual tasks such as object detection and image s…
Image SegmentationObject DetectionAWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent
To address the enormous size of Large Language Models (LLMs), model compression methods, such as quantization and pruning, are often deployed, especially on edge devices. In this work, we focus on layer-wise post-trainin…
Model CompressionQuantization