Related papers: E2GC: Energy-efficient Group Convolution in Deep N…
The performance of neural networks has been significantly improved by increasing the number of channels in convolutional layers. However, this increase in performance comes with a higher computational cost, resulting in numerous studies…
Graph Neural Networks (GNNs) show strong promise for circuit analysis, but scaling to modern large-scale circuit graphs is limited by GPU memory and training cost, especially for deep models. We revisit deep GNNs for circuit graphs and show…
Deploying Convolutional Neural Network (CNN) models on ubiquitous Internet of Things (IoT) devices in a cloud-assisted manner to provide users with a variety of high-quality services has become mainstream. Most existing studies speed up…
Deep convolutional neural networks (CNN) have shown their good performances in many computer vision tasks. However, the high computational complexity of CNN involves a huge amount of data movements between the computational processor core…
Convolution is the most time-consuming operation in deep neural network operations, so its performance is critical to the overall performance of the neural network. The commonly used methods for convolution on GPU include the general matrix…
Graph convolutions have been a pivotal element in learning graph representations. However, recursively aggregating neighboring information with graph convolutions leads to indistinguishable node features in deep layers, which is known as…
Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significantly when they stack many layers, because of the…
Over the past years, great progress has been made in improving the computing power of general-purpose graphics processing units (GPGPUs), which facilitates the prosperity of deep neural networks (DNNs) in multiple fields like computer…
Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…
Graph Neural Networks (GNNs) have gained significant momentum recently due to their capability to learn on unstructured graph data. Dynamic GNNs (DGNNs) are the current state-of-the-art for point cloud applications; such applications (viz.…
This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution. It explores the broad "middle spectrum" area between…
Common wisdom in the graph neural network (GNN) community dictates that anisotropic models -- in which messages sent between nodes are a function of both the source and target node -- are required to achieve state-of-the-art performance.…
Deep neural networks have faced many problems in hyperspectral image classification, including the ineffective utilization of spectral-spatial joint information and the problems of gradient vanishing and overfitting that arise with…
In this paper, we present a simple and modularized neural network architecture, named interleaved group convolutional neural networks (IGCNets). The main point lies in a novel building block, a pair of two successive interleaved group…
"How much energy is consumed for an inference made by a convolutional neural network (CNN)?" With the increased popularity of CNNs deployed on the wide-spectrum of platforms (from mobile devices to workstations), the answer to this question…
Group convolutional neural networks (G-CNNs) can be used to improve classical CNNs by equipping them with the geometric structure of groups. Central in the success of G-CNNs is the lifting of feature maps to higher dimensional disentangled…
Convolutional Neural Networks (CNNs) have proven highly effective for edge and mobile vision tasks due to their computational efficiency. While many recent works seek to enhance CNNs with global contextual understanding via…
This paper presents a novel framework combining group equivariant convolutional neural networks (G-CNNs) with equivariant-aware structured pruning to produce compact, transformation-invariant models for resource-constrained environments.…
PDE-based Group Convolutional Neural Networks (PDE-G-CNNs) use solvers of evolution PDEs as substitutes for the conventional components in G-CNNs. PDE-G-CNNs can offer several benefits simultaneously: fewer parameters, inherent…
We present a PDE-based framework that generalizes Group equivariant Convolutional Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE-solvers where geometrically meaningful PDE-coefficients become the…