Related papers: Realizing Unaligned Block-wise Pruning for DNN Acc…

Recent advances in Deep Neural Networks (DNNs) have demonstrated outstanding performance across various domains. However, their large size is a challenge for deployment on resource-constrained devices such as mobile, edge, and IoT…

Executing deep neural networks (DNNs) on edge artificial intelligence (AI) devices enables various autonomous mobile computing applications. However, the memory budget of edge AI devices restricts the number and complexity of DNNs allowed…

Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously…

Pruning neural networks, which involves removing a fraction of their weights, can often maintain high accuracy while significantly reducing model complexity, at least up to a certain limit. We present a neural network pruning technique that…

Neural language models (NLMs) exist in an accuracy-efficiency tradeoff space where better perplexity typically comes at the cost of greater computation complexity. In a software keyboard application on mobile devices, this translates into…

Deep neural networks have significantly improved performance on a range of tasks with the increasing demand for computational resources, leaving deployment on low-resource devices (with limited memory and battery power) infeasible. Binary…

By executing offloaded tasks from mobile users, edge computing augments mobile user equipments (UEs) with computing/communications resources from edge nodes (ENs), enabling new services (e.g., real-time gaming). However, despite being more…

3D medical image segmentation often faces heavy resource and time consumption, limiting its scalability and rapid deployment in clinical environments. Existing efficient segmentation models are typically static and manually designed prior…

To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…

Pre-training has improved model accuracy for both classification and generation tasks at the cost of introducing much larger and slower models. Pruning methods have proven to be an effective way of reducing model size, whereas distillation…

Edge learning facilitates ubiquitous intelligence by enabling model training and adaptation directly on data-generating devices, thereby mitigating privacy risks and communication latency. However, the high computational and energy overhead…

Over the last years, a great success of deep neural networks (DNNs) has been witnessed in computer vision and other fields. However, performance and power constraints make it still challenging to deploy DNNs on mobile devices due to their…

To enable DNNs on edge devices like mobile phones, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a…

Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is a vast demand for…

The increasing pervasiveness of intelligent mobile applications requires to exploit the full range of resources offered by the mobile-edge-cloud network for the execution of inference tasks. However, due to the heterogeneity of such…

The execution of large deep neural networks (DNN) at mobile edge devices requires considerable consumption of critical resources, such as energy, while imposing demands on hardware capabilities. In approaches based on edge computing the…

Faced with the massive connection, sporadic transmission, and small-sized data packets in future cellular communication, a grant-free non-orthogonal random access (NORA) system is considered in this paper, which could reduce the access…

This paper presents a novel approach to network pruning, targeting block pruning in deep neural networks for edge computing environments. Our method diverges from traditional techniques that utilize proxy metrics, instead employing a direct…

Model-based deep learning (MBDL) is a powerful methodology for designing deep models to solve imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and…

Scaling up model size and training data has advanced foundation models for instance-level perception, achieving state-of-the-art in-domain and zero-shot performance across object detection and segmentation. However, their high computational…