Related papers: Robust Distillation for Worst-class Performance
Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher. These existing distillation approaches simply focus on the improvement of…
Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model. Despite the success of KD in the classification task, applying KD to recommender models is…
Knowledge distillation transfers knowledge from a high capacity teacher to a compact student using a mixture of hard and soft losses. On imbalanced data, a fixed weighting between hard and soft losses becomes brittle the learning process.…
We focus on the problem of training a deep neural network in generations. The flowchart is that, in order to optimize the target network (student), another network (teacher) with the same architecture is first trained, and used to provide…
Knowledge distillation (KD) is a simple and successful method to transfer knowledge from a teacher to a student model solely based on functional activity. However, current KD has a few shortcomings: it has recently been shown that this…
Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…
Knowledge distillation is a popular machine learning technique that aims to transfer knowledge from a large 'teacher' network to a smaller 'student' network and improve the student's performance by training it to emulate the teacher. In…
We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…
Despite the success of Deep Learning (DL), the deployment of modern DL models requiring large computational power poses a significant problem for resource-constrained systems. This necessitates building compact networks that reduce…
Knowledge distillation provides an effective way to transfer knowledge via teacher-student learning, where most existing distillation approaches apply a fixed pre-trained model as teacher to supervise the learning of student network. This…
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…
Knowledge Distillation, as a model compression technique, has received great attention. The knowledge of a well-performed teacher is distilled to a student with a small architecture. The architecture of the small student is often chosen to…
Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In…
Data-Free Robustness Distillation (DFRD) aims to transfer the robustness from the teacher to the student without accessing the training data. While existing methods focus on overall robustness, they overlook the robust fairness issues,…
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…
Self-supervised speech pre-training enables deep neural network models to capture meaningful and disentangled factors from raw waveform signals. The learned universal speech representations can then be used across numerous downstream tasks.…
Knowledge distillation compresses a larger neural model (teacher) into smaller, faster student models by training them to match teacher outputs. However, the internal computational transformations that occur during this process remain…
Pre-trained language models achieve outstanding performance in NLP tasks. Various knowledge distillation methods have been proposed to reduce the heavy computation and storage requirements of pre-trained language models. However, from our…
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student. Existing methods focus on excavating the knowledge hints and transferring the whole knowledge to the student. However,…