相关论文: Growing Efficient Accurate and Robust Neural Netwo…

Graph neural networks (GNNs) have emerged as a popular strategy for handling non-Euclidean data due to their state-of-the-art performance. However, most of the current GNN model designs mainly focus on task accuracy, lacking in considering…

Graph convolutional neural networks (GCNs) generalize tradition convolutional neural networks (CNNs) from low-dimensional regular graphs (e.g., image) to high dimensional irregular graphs (e.g., text documents on word embeddings). Due to…

Graph neural networks (GNNs) are machine learning models specialized for graph data and widely used in many applications. To train GNNs on large graphs that exceed CPU memory, several systems store data on disk and conduct out-of-core…

This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved accuracy at the expense of prediction costs making them…

Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential…

Deep neural networks (DNNs) offer plenty of challenges in executing efficient computation at edge nodes, primarily due to the huge hardware resource demands. The article proposes HYDRA, hybrid data multiplexing, and runtime layer…

The last decade has witnessed the breakthrough of deep neural networks (DNNs) in many fields. With the increasing depth of DNNs, hundreds of millions of multiply-and-accumulate (MAC) operations need to be executed. To accelerate such…

Accelerated edge devices, like Nvidia's Jetson with 1000+ CUDA cores, are increasingly used for DNN training and federated learning, rather than just for inferencing workloads. A unique feature of these compact devices is their fine-grained…

Today, deep learning optimization is primarily driven by research focused on achieving high inference accuracy and reducing latency. However, the energy efficiency aspect is often overlooked, possibly due to a lack of sustainability mindset…

Deep neural networks (NNs) are considered a powerful tool for balancing the performance and complexity of multiple-input multiple-output (MIMO) receivers due to their accurate feature extraction, high parallelism, and excellent inference…

Recently, a new trend of exploring sparsity for accelerating neural network training has emerged, embracing the paradigm of training on the edge. This paper proposes a novel Memory-Economic Sparse Training (MEST) framework targeting for…

Deep Neural Networks (DNNs) on hardware is facing excessive computation cost due to the massive number of parameters. A typical training pipeline to mitigate over-parameterization is to pre-define a DNN structure first with redundant…

The detection performance of small objects in remote sensing images is not satisfactory compared to large objects, especially in low-resolution and noisy images. A generative adversarial network (GAN)-based model called enhanced…

In standard generative deep learning models, such as autoencoders or GANs, the size of the parameter set is proportional to the complexity of the generated data distribution. A significant challenge is to deploy resource-hungry deep…

This paper presents a state-of-the-art overview on how to architect, design, and optimize Deep Neural Networks (DNNs) such that performance is improved and accuracy is preserved. The paper covers a set of optimizations that span the entire…

With the increasing demand for computationally intensive services like deep learning tasks, emerging distributed computing platforms such as edge computing (EC) systems are becoming more popular. Edge computing systems have shown promising…

Collaborative inference enables resource-constrained edge devices to make inferences by uploading inputs (e.g., images) to a server (i.e., cloud) where the heavy deep learning models run. While this setup works cost-effectively for…

Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and better architectures. However, data seen in the real world are…

While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully…

Deploying Retrieval Augmented Generation (RAG) on resource-constrained edge devices is challenging due to limited memory and processing power. In this work, we propose EdgeRAG which addresses the memory constraint by pruning embeddings…