7 Papers
3 Citations
Xu Li is an academic researcher from University of California, Santa Barbara. The author has contributed to research in topics: Computer science & Topological graph theory. The author has an hindex of 1, co-authored 3 publications.
Chat about Author
Papers
DenseKPNET: Dense Kernel Point Convolutional Neural Networks for Point Cloud Semantic Segmentation
TL;DR: A novel deep neural network, namely, the Dense connection-based Kernel Point Network (DenseKPNet), which can greatly expand the receptive field of kernel point convolution to extract rich semantic context information and valuable geometric features from the local region effectively.
26
An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow Prediction
Shanchun Zhao,Xu Li +1 more
TL;DR: An attentional encoder-decoder dual graph convolution model with time-series correlation (AED-DGCN-TSC) for solving the spatio-temporal sequence prediction problem in the traffic domain and the results demonstrate the effectiveness of the proposed model.
•Posted Content
Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers.
TL;DR: This work proposes SAG, the first scalable adversarial attack method with Alternating Direction Method of Multipliers (ADMM), and demonstrates that SAG can significantly reduce the computation and memory overhead compared with the state-of-the-art approach, making SAG applicable towards graphs with large size of nodes and edges.
PathSAGE: Spatial Graph Attention Neural Networks with Random Path Sampling
Junhua Ma,Jiajun Li,Xueming Li,Xu Li +3 more
- 11 Mar 2022
TL;DR: A model called PathSAGE is proposed, which can learn high-order topological information and improve the model’s performance by expanding the receptive field and achieves comparable performance with the state-of-the-art models in inductive learning tasks.
Multi-Augmentation Contrastive Learning as Multi-Objective Optimization for Graph Neural Networks
Xu Li,Yongsheng Chen +1 more
TL;DR: In this article , a set of graph augmentation methods are proposed for self-supervised learning of graph neural networks (GNNs), and the Pareto optimality is used to select and balance among these possibly conflicting augmented versions, called P areto G raph C ontrastive L earning (PGCL ).