相关论文: Generative Knowledge Transfer for Neural Language …

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student neural network. Existing knowledge transfer approaches match…

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed…

Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years. In this paper, we propose a generative model based semantic communication to further improve the efficiency of image…

Graph neural networks (GNNs) have been attracting increasing popularity due to their simplicity and effectiveness in a variety of fields. However, a large number of labeled data is generally required to train these networks, which could be…

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…

Knowledge distillation is a powerful technique for transferring knowledge from a pre-trained teacher model to a student model. However, the true potential of knowledge transfer has not been fully explored. Existing approaches primarily…

Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…

Despite deep neural networks have demonstrated extraordinary power in various applications, their superior performances are at expense of high storage and computational costs. Consequently, the acceleration and compression of neural…

Self-supervised pre-trained models such as HuBERT and WavLM leverage unlabeled speech data for representation learning and offer significantly improve for numerous downstream tasks. Despite the success of these methods, their large memory…

To reduce the large computation and storage cost of a deep convolutional neural network, the knowledge distillation based methods have pioneered to transfer the generalization ability of a large (teacher) deep network to a light-weight…

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict…

Recurrent neural networks (RNNs), particularly long short-term memory (LSTM), have gained much attention in automatic speech recognition (ASR). Although some successful stories have been reported, training RNNs remains highly challenging,…

Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing. In this paper, we treat such pre-trained networks as teachers and explore how to learn a target…

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…

Many algorithms for control of multi-robot teams operate under the assumption that low-latency, global state information necessary to coordinate agent actions can readily be disseminated among the team. However, in harsh environments with…

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…

Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable…

Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents…

Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…