Related papers: Self Regulated Learning Mechanism for Data Efficie…

After a large "teacher" neural network has been trained on labeled data, the probabilities that the teacher assigns to incorrect classes reveal a lot of information about the way in which the teacher generalizes. By training a small…

Deep learning models can achieve high inference accuracy by extracting rich knowledge from massive well-annotated data, but may pose the risk of data privacy leakage in practical deployment. In this paper, we present an effective…

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra computational costs to update one or more generators and their…

Knowledge distillation, a widely used model compression technique, works on the basis of transferring knowledge from a cumbersome teacher model to a lightweight student model. The technique involves jointly optimizing the task specific and…

Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…

Knowledge distillation is a popular technique for training a small student network to emulate a larger teacher model, such as an ensemble of networks. We show that while knowledge distillation can improve student generalization, it does not…

Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationship across samples with same class is often neglected. In…

Knowledge distillation (KD) is one of the most potent ways for model compression. The key idea is to transfer the knowledge from a deep teacher model (T) to a shallower student (S). However, existing methods suffer from performance…

Knowledge distillation (KD) is a new method for transferring knowledge of a structure under training to another one. The typical application of KD is in the form of learning a small model (named as a student) by soft labels produced by a…

Recent advances have indicated the strengths of self-supervised pre-training for improving representation learning on downstream tasks. Existing works often utilize self-supervised pre-trained models by fine-tuning on downstream tasks.…

Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge…

Knowledge distillation has attracted a great deal of interest recently to compress pre-trained language models. However, existing knowledge distillation methods suffer from two limitations. First, the student model simply imitates the…

Knowledge distillation transfers the knowledge from a cumbersome teacher to a small student. Recent results suggest that the student-friendly teacher is more appropriate to distill since it provides more transferable knowledge. In this…

Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning. Unlike previous…

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

Knowledge distillation is a strategy of training a student network with guide of the soft output from a teacher network. It has been a successful method of model compression and knowledge transfer. However, currently knowledge distillation…

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…