相关论文: Data-Augmented Quantization-Aware Knowledge Distil…

Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. However, there exists a discrepancy on low-frequency words between the distilled and the original data,…

Beyond the complexity of CNNs that require training on large annotated datasets, the domain shift between design and operational data has limited the adoption of CNNs in many real-world applications. For instance, in person…

Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. We find that these methods break down at lower bit precision, and investigate quantization…

Data-Augmentation (DA) is known to improve performance across tasks and datasets. We propose a method to theoretically analyze the effect of DA and study questions such as: how many augmented samples are needed to correctly estimate the…

With the increasing popularity of deep learning on edge devices, compressing large neural networks to meet the hardware requirements of resource-constrained devices became a significant research direction. Numerous compression methodologies…

Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to be sensitive to hyperparameter settings and make…

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some…

Quantization has become a predominant approach for model compression, enabling deployment of large models trained on GPUs onto smaller form-factor devices for inference. Quantization-aware training (QAT) optimizes model parameters with…

Collaborative learning has emerged as a key paradigm in large-scale intelligent systems, enabling distributed agents to cooperatively train their models while addressing their privacy concerns. Central to this paradigm is knowledge…

Knowledge distillation (KD) is a substantial strategy for transferring learned knowledge from one neural network model to another. A vast number of methods have been developed for this strategy. While most method designs a more efficient…

Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the…

Non-autoregressive machine translation (NAT) systems predict a sequence of output tokens in parallel, achieving substantial improvements in generation speed compared to autoregressive models. Existing NAT models usually rely on the…

We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets,…

Knowledge Distillation (KD) is one of the approaches to reduce the size of Large Language Models (LLMs). A LLM with smaller number of model parameters (student) is trained to mimic the performance of a LLM of a larger size (teacher model)…

Knowledge Distillation (KD) based methods adopt the one-way Knowledge Transfer (KT) scheme in which training a lower-capacity student network is guided by a pre-trained high-capacity teacher network. Recently, Deep Mutual Learning (DML)…

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…

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…

The superior performance of deep learning relies heavily on a large collection of sample data, but the data insufficiency problem turns out to be relatively common in global electricity markets. How to prevent overfitting in this case…

Knowledge distillation in machine learning is the process of transferring knowledge from a large model called the teacher to a smaller model called the student. Knowledge distillation is one of the techniques to compress the large network…

Knowledge distillation (KD) enables a smaller "student" model to mimic a larger "teacher" model by transferring knowledge from the teacher's output or features. However, most KD methods treat all samples uniformly, overlooking the varying…