相关论文: The Pupil Has Become the Master: Teacher-Student M…

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

The burgeoning complexity of contemporary deep learning models, while achieving unparalleled accuracy, has inadvertently introduced deployment challenges in resource-constrained environments. Knowledge distillation, a technique aiming to…

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…

Music classification has been one of the most popular tasks in the field of music information retrieval. With the development of deep learning models, the last decade has seen impressive improvements in a wide range of classification tasks.…

Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network. However, there has been little research on how the concept of distillation can be leveraged…

Ensemble models comprising of deep Convolutional Neural Networks (CNN) have shown significant improvements in model generalization but at the cost of large computation and memory requirements. In this paper, we present a framework for…

Pre-trained language models have become an integral component of question-answering systems, achieving remarkable performance. However, for practical deployment, it is crucial to perform knowledge distillation to maintain high performance…

Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that…

We present a novel framework of knowledge distillation that is capable of learning powerful and efficient student models from ensemble teacher networks. Our approach addresses the inherent model capacity issue between teacher and student…

It is well known that a speech recognition system that combines multiple acoustic models trained on the same data significantly outperforms a single-model system. Unfortunately, real time speech recognition using a whole ensemble of models…

Knowledge distillation has emerged as an effective strategy for compressing large language models' (LLMs) knowledge into smaller, more efficient student models. However, standard one-shot distillation methods often produce suboptimal…

Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as…

Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restricted systems. This…

This paper contributes a new State Of The Art (SOTA) for Semantic Textual Similarity (STS). We compare and combine a number of recently proposed sentence embedding methods for STS, and propose a novel and simple ensemble knowledge…

This paper proposes a novel knowledge distillation-based learning method to improve the classification performance of convolutional neural networks (CNNs) without a pre-trained teacher network, called exit-ensemble distillation. Our method…

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…

Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge for edge deployment. Embedding matrices, typically, contain…

Algorithmic efficiency techniques such as distillation (\cite{hinton2015distillation}) are useful in improving model quality without increasing serving costs, provided a larger teacher model is available for a smaller student model to learn…

Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are…

Ensembling is a universally useful approach to boost the performance of machine learning models. However, individual models in an ensemble were traditionally trained independently in separate stages without information access about the…