Picture for Hongyi Li

Hongyi Li

General-purpose Dataflow Model with Neuromorphic Primitives

Add code
Aug 02, 2024
Viaarxiv icon

i-Octree: A Fast, Lightweight, and Dynamic Octree for Proximity Search

Add code
Sep 15, 2023
Viaarxiv icon

A Convergent ADMM Framework for Efficient Neural Network Training

Add code
Dec 22, 2021
Figure 1 for A Convergent ADMM Framework for Efficient Neural Network Training
Figure 2 for A Convergent ADMM Framework for Efficient Neural Network Training
Figure 3 for A Convergent ADMM Framework for Efficient Neural Network Training
Figure 4 for A Convergent ADMM Framework for Efficient Neural Network Training
Viaarxiv icon

Community-based Layerwise Distributed Training of Graph Convolutional Networks

Add code
Dec 17, 2021
Figure 1 for Community-based Layerwise Distributed Training of Graph Convolutional Networks
Figure 2 for Community-based Layerwise Distributed Training of Graph Convolutional Networks
Figure 3 for Community-based Layerwise Distributed Training of Graph Convolutional Networks
Figure 4 for Community-based Layerwise Distributed Training of Graph Convolutional Networks
Viaarxiv icon

Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework

Add code
May 20, 2021
Figure 1 for Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework
Figure 2 for Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework
Figure 3 for Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework
Figure 4 for Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM framework
Viaarxiv icon