Search Results for author: Hongyang Gao

Found 15 papers, 8 papers with code

A global convergence theory for deep ReLU implicit networks via over-parameterization

no code implementations11 Oct 2021 Tianxiang Gao, Hailiang Liu, Jia Liu, Hridesh Rajan, Hongyang Gao

Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectures.

Weighted Line Graph Convolutional Networks

no code implementations1 Jan 2021 Hongyang Gao, Shuiwang Ji

Line graphs have shown to be effective in improving feature learning in graph neural networks.

Teleport Graph Convolutional Networks

no code implementations1 Jan 2021 Hongyang Gao, Shuiwang Ji

To address these limitations, we propose a teleport graph convolution layer (TeleGCL) that uses teleport functions to enable each node to aggregate information from a much larger neighborhood.

Node Classification

Topology-Aware Graph Pooling Networks

no code implementations19 Oct 2020 Hongyang Gao, Yi Liu, Shuiwang Ji

In addition, graph topology is incorporated in global voting to compute the importance score of each node globally in the entire graph.

Graph Classification

Towards Deeper Graph Neural Networks

2 code implementations18 Jul 2020 Meng Liu, Hongyang Gao, Shuiwang Ji

Based on our theoretical and empirical analysis, we propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.

Graph Representation Learning Node Classification

Kronecker Attention Networks

1 code implementation ICLR 2020 Hongyang Gao, Zhengyang Wang, Shuiwang Ji

Use of attention operators on high-order data requires flattening of the spatial or spatial-temporal dimensions into a vector, which is assumed to follow a multivariate normal distribution.

Graph Representation Learning via Hard and Channel-Wise Attention Networks

no code implementations5 Jul 2019 Hongyang Gao, Shuiwang Ji

To further reduce the requirements on computational resources, we propose the cGAO that performs attention operations along channels.

Graph Attention Graph Classification +3

Graph U-Nets

3 code implementations11 May 2019 Hongyang Gao, Shuiwang Ji

We further propose the gUnpool layer as the inverse operation of the gPool layer.

General Classification Graph Classification +2

Learning Graph Pooling and Hybrid Convolutional Operations for Text Representations

1 code implementation21 Jan 2019 Hongyang Gao, Yongjun Chen, Shuiwang Ji

Another limitation of GCN when used on graph-based text representation tasks is that, GCNs do not consider the order information of nodes in graph.

Text Categorization

ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions

2 code implementations NeurIPS 2018 Hongyang Gao, Zhengyang Wang, Shuiwang Ji

Compared to prior CNNs designed for mobile devices, ChannelNets achieve a significant reduction in terms of the number of parameters and computational cost without loss in accuracy.

General Classification

Large-Scale Learnable Graph Convolutional Networks

1 code implementation12 Aug 2018 Hongyang Gao, Zhengyang Wang, Shuiwang Ji

However, the number of neighboring units is neither fixed nor are they ordered in generic graphs, thereby hindering the applications of convolutional operations.

Document Classification Node Classification

Efficient and Invariant Convolutional Neural Networks for Dense Prediction

no code implementations24 Nov 2017 Hongyang Gao, Shuiwang Ji

In this paper, we propose a set of methods based on kernel rotation and flip to enable rotation and flip invariance in convolutional neural networks.

Semantic Segmentation

Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generation

1 code implementation19 May 2017 Lei Cai, Hongyang Gao, Shuiwang Ji

In the simplest case, the proposed multi-stage VAE divides the decoder into two components in which the second component generates refined images based on the course images generated by the first component.

Image Generation

Pixel Deconvolutional Networks

4 code implementations ICLR 2018 Hongyang Gao, Hao Yuan, Zhengyang Wang, Shuiwang Ji

When used in image generation tasks, our PixelDCL can largely overcome the checkerboard problem suffered by regular deconvolution operations.

Image Generation Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.