activity
20182021
most citedAdaptive Graph Encoder for Attributed Graph Embedding

236 citations · 410 across the 10 of their papers we have counts for

collaborators

17 papers

cs.LG20218 cited

Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework

Cheng Yang, Jiawei Liu, Chuan Shi

Semi-supervised learning on graphs is an important problem in the machine learning area. In recent years, state-of-the-art classification methods based on graph neural networks (GN…

cs.CV202130 cited

Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition

Shaokang Yang, Shuai Liu, Cheng Yang +1

Fine-grained image recognition is very challenging due to the difficulty of capturing both semantic global features and discriminative local features. Meanwhile, these two features…

cond-mat.mes-hall2020

Two-dimensional Cold Electron Transport for Steep-slope Transistors

Maomao Liu, Hemendra Nath Jaiswal, Simran Shahi +10

Room-temperature Fermi-Dirac electron thermal excitation in conventional three-dimensional (3D) or two-dimensional (2D) semiconductors generates hot electrons with a relatively lon…

cs.SI20203 cited

Information Diffusion Prediction with Latent Factor Disentanglement

Haoran Wang, Cheng Yang

Information diffusion prediction is a fundamental task which forecasts how an information item will spread among users. In recent years, deep learning based methods, especially tho…

physics.optics2020

Phonon heat transport in cavity-mediated optomechanical nanoresonators

Cheng Yang, Xinrui Wei, Jiteng Sheng +1

The understanding of heat transport in nonequilibrium thermodynamics is an important research frontier, which is crucial for implementing novel thermodynamic devices, such as heat…

cs.CV20201 cited

Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation

Nan Zhuang, Cheng Yang

In this paper, we are interested in generating fine-grained cartoon faces for various groups. We assume that one of these groups consists of sufficient training data while the othe…