activity
20182021
most citedLearning to Drop: Robust Graph Neural Network via Topological Denoising

15 citations · 19 across the 7 of their papers we have counts for

collaborators

8 papers

cs.LG2021

Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series

Yinjun Wu, Jingchao Ni, Wei Cheng +7

Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging…

q-bio.GN20201 cited

SimpleChrome: Encoding of Combinatorial Effects for Predicting Gene Expression

Wei Cheng, Ghulam Murtaza, Aaron Wang

Due to recent breakthroughs in state-of-the-art DNA sequencing technology, genomics data sets have become ubiquitous. The emergence of large-scale data sets provides great opportun…

cs.LG202015 cited

Learning to Drop: Robust Graph Neural Network via Topological Denoising

Dongsheng Luo, Wei Cheng, Wenchao Yu +4

Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along edges of the given graph.…

cs.LG20201 cited

T-Net: A Semi-supervised Deep Model for Turbulence Forecasting

Denghui Zhang, Yanchi Liu, Wei Cheng +5

Accurate air turbulence forecasting can help airlines avoid hazardous turbulence, guide the routes that keep passengers safe, maximize efficiency, and reduce costs. Traditional tur…

stat.ML20201 cited

Generalizing Variational Autoencoders with Hierarchical Empirical Bayes

Wei Cheng, Gregory Darnell, Sohini Ramachandran +1

Variational Autoencoders (VAEs) have experienced recent success as data-generating models by using simple architectures that do not require significant fine-tuning of hyperparamete…

cs.IR2019

Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation

Xin Dong, Jingchao Ni, Wei Cheng +6

Recently, recommender systems have been able to emit substantially improved recommendations by leveraging user-provided reviews. Existing methods typically merge all reviews of a g…