相关论文: Using Programmable Graphene Channels as Weights in…

Doped graphene emerges as a strong contender for active plasmonic material in the mid-infrared wavelengths due to the versatile external-control of its permittivity-function and also its highly-compressed graphene surface plasmon (GSP)…

Graphitic nanostructures, e.g. carbon nanotubes (CNT) and graphene, have been proposed as ideal materials for spin conduction[1-7]; they have long electronic mean free paths[8] and small spin-orbit coupling[9], hence are expected to have…

Graph Neural Networks (GNNs) have become powerful tools for learning from graph-structured data, finding applications across diverse domains. However, as graph sizes and connectivity increase, standard GNN training methods face significant…

Despite the recent success of Graph Neural Networks, it remains challenging to train a GNN on large graphs with millions of nodes and billions of edges, which are prevalent in many graph-based applications. Traditional sampling-based…

Spiking Neural Networks (SNNs) with a large number of weights and varied weight distribution can be difficult to implement in emerging in-memory computing hardware due to the limitations on crossbar size (implementing dot product), the…

Sparse deep neural networks (DNNs) excel in real-world applications like robotics and computer vision, by reducing computational demands that hinder usability. However, recent studies aim to boost DNN efficiency by trimming redundant…

Graph Neural Networks (GNNs) are widely used to perform different machine learning tasks on graphs. As the size of the graphs grows, and the GNNs get deeper, training and inference time become costly in addition to the memory requirement.…

Plasticity circuits in the brain are known to be influenced by the distribution of the synaptic weights through the mechanisms of synaptic integration and local regulation of synaptic strength. However, the complex interplay of…

We present a novel trajectory traversability estimation and planning algorithm for robot navigation in complex outdoor environments. We incorporate multimodal sensory inputs from an RGB camera, 3D LiDAR, and the robot's odometry sensor to…

Predicting metro passenger flow precisely is of great importance for dynamic traffic planning. Deep learning algorithms have been widely applied due to their robust performance in modelling non-linear systems. However, traditional deep…

Algorithm unfolding creates an interpretable and parsimonious neural network architecture by implementing each iteration of a model-based algorithm as a neural layer. However, unfolding a proximal splitting algorithm with a positive…

The demand for compact, high-speed and energy-saving circuitry urges higher efficiency of spintronic devices that can offer a viable alternative for the current electronics. The route towards this goal suggests implementing two-dimensional…

We investigate the electronic structure of graphene on a series of 2D hexagonal nitride insulators hXN, X = B, Al, and Ga, with DFT calculations. A symmetry-based model Hamiltonian is employed to extract orbital parameters and spin-orbit…

Recently, distributed GNN training frameworks, such as DistDGL and PyG, have been developed to enable training GNN models on large graphs by leveraging multiple GPUs in a distributed manner. Despite these advances, their memory requirements…

The state-of-the-art deep neural networks (DNNs) have significant computational and data management requirements. The size of both training data and models continue to increase. Sparsification and pruning methods are shown to be effective…

We present a Graph Neural Network (GNN) that accurately simulates a multidisperse suspension of interacting spherical particles. Our machine learning framework is built upon the recent work of Sanchez-Gonzalez et al. ICML, PMLR, 119,…

Graph Neural Networks (GNNs) are powerful deep learning models to generate node embeddings on graphs. When applying deep GNNs on large graphs, it is still challenging to perform training in an efficient and scalable way. We propose a novel…

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in solving graph classification tasks. However, most GNN architectures aggregate information from all nodes and edges in a graph, regardless of their relevance to the…

Electrostatic gating lies in the heart of modern FET-based integrated circuits. Usually, the gate electrode has to be placed very close to the conduction channel, typically a few nanometers, in order to achieve efficient tunability.…

Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large data sizes of graphs and their vertex features make scalable training algorithms and distributed memory systems necessary. Since the…