Curvature-based Transformer for Molecular Property Prediction

no code implementations • 25 Jul 2023 • Yili Chen, Zhengyu Li, Zheng Wan, Hui Yu, Xian Wei

In this work, we propose Curvature-based Transformer to improve the ability of Graph Transformer neural network models to extract structural information on molecular graph data by introducing Discretization of Ricci Curvature.

Molecular Property Prediction Property Prediction

Multi-scale Geometry-aware Transformer for 3D Point Cloud Classification

no code implementations • 12 Apr 2023 • Xian Wei, Muyu Wang, Shing-Ho Jonathan Lin, Zhengyu Li, Jian Yang, Arafat Al-Jawari, Xuan Tang

At first, the MGT divides point cloud data into patches with multiple scales.

3D Point Cloud Classification Point Cloud Classification

RMMDet: Road-Side Multitype and Multigroup Sensor Detection System for Autonomous Driving

1 code implementation • 9 Mar 2023 • Xiuyu Yang, Zhuangyan Zhang, Haikuo Du, Sui Yang, Fengping Sun, Yanbo Liu, Ling Pei, Wenchao Xu, Weiqi Sun, Zhengyu Li

Then we implement muti-type sensor detection and multi-group sensors fusion in this environment, including camera-radar and camera-lidar detection based on result-level fusion.

Autonomous Driving Scheduling

A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold

no code implementations • 16 Feb 2023 • Yanhong Fei, Xian Wei, Yingjie Liu, Zhengyu Li, Mingsong Chen

Although Deep Learning (DL) has achieved success in complex Artificial Intelligence (AI) tasks, it suffers from various notorious problems (e. g., feature redundancy, and vanishing or exploding gradients), since updating parameters in Euclidean space cannot fully exploit the geometric structure of the solution space.

Transfer Learning

Improve Chinese Word Embeddings by Exploiting Internal Structure

1 code implementation • NAACL 2016 • Jian Xu, Jiawei Liu, Liangang Zhang, Zhengyu Li, Huanhuan Chen

Semantic Textual Similarity Text Classification +1