相关论文: Private Model Compression via Knowledge Distillati…

With the emergence of smart cities, Internet of Things (IoT) devices as well as deep learning technologies have witnessed an increasing adoption. To support the requirements of such paradigm in terms of memory and computation, joint and…

The deep complex convolution recurrent network (DCCRN) achieves excellent speech enhancement performance by utilizing the audio spectrum's complex features. However, it has a large number of model parameters. We propose a smaller model,…

On-device Deep Neural Networks (DNNs) have recently gained more attention due to the increasing computing power of the mobile devices and the number of applications in Computer Vision (CV), Natural Language Processing (NLP), and Internet of…

Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build…

Modern recommender systems operate in a fully server-based fashion. To cater to millions of users, the frequent model maintaining and the high-speed processing for concurrent user requests are required, which comes at the cost of a huge…

The remarkable successes of deep learning models across various applications have resulted in the design of deeper networks that can solve complex problems. However, the increasing depth of such models also results in a higher storage and…

Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for…

Noise suppression (NS) models have been widely applied to enhance speech quality. Recently, Deep Learning-Based NS, which we denote as Deep Noise Suppression (DNS), became the mainstream NS method due to its excelling performance over…

Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech recognition. However, their superior performance comes at the…

Knowledge distillation is considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. We quantify the compression capacity of knowledge distillation and the…

Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are…

Singing Voice Detection (SVD) has been an active area of research in music information retrieval (MIR). Currently, two deep neural network-based methods, one based on CNN and the other on RNN, exist in literature that learn optimized…

Knowledge distillation which learns a lightweight student model by distilling knowledge from a cumbersome teacher model is an attractive approach for learning compact deep neural networks (DNNs). Recent works further improve student network…

The recent developments of Diffusion Models (DMs) enable generation of astonishingly high-quality synthetic samples. Recent work showed that the synthetic samples generated by the diffusion model, which is pre-trained on public data and…

Knowledge distillation is an effective approach to transferring knowledge from a teacher neural network to a student target network for satisfying the low-memory and fast running requirements in practice use. Whilst being able to create…

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic…

Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees,…

As a promising solution for model compression, knowledge distillation (KD) has been applied in recommender systems (RS) to reduce inference latency. Traditional solutions first train a full teacher model from the training data, and then…

Transformer-based reinforcement learning has emerged as a strong candidate for sequential control in residential energy management. In particular, the Decision Transformer can learn effective battery dispatch policies from historical data,…

The deployment of deep neural networks on resource-constrained devices necessitates effective model com- pression strategies that judiciously balance the reduction of model size with the preservation of performance. This study introduces a…