activity
20162020
most citedTaking the pulse of COVID-19: A spatiotemporal perspective

122 citations · 194 across the 10 of their papers we have counts for

collaborators

17 papers

cs.SI2020

Multi-instance Domain Adaptation for Vaccine Adverse Event Detection

Junxiang Wang, Liang Zhao

Detection of vaccine adverse events is crucial to the discovery and improvement of problematic vaccines. To achieve it, traditionally formal reporting systems like VAERS support ac…

cs.AI202014 cited

Event Prediction in the Big Data Era: A Systematic Survey

Liang Zhao

Events are occurrences in specific locations, time, and semantics that nontrivially impact either our society or the nature, such as civil unrest, system failures, and epidemics. I…

cs.LG202029 cited

Interpretable Deep Graph Generation with Node-Edge Co-Disentanglement

Xiaojie Guo, Liang Zhao, Zhao Qin +3

Disentangled representation learning has recently attracted a significant amount of attention, particularly in the field of image representation learning. However, learning the dis…

physics.soc-ph2020122 cited

Taking the pulse of COVID-19: A spatiotemporal perspective

Chaowei Yang, Dexuan Sha, Qian Liu +32

The sudden outbreak of the Coronavirus disease (COVID-19) swept across the world in early 2020, triggering the lockdowns of several billion people across many countries, including…

cs.LG2020

Deep Multi-attributed Graph Translation with Node-Edge Co-evolution

Xiaojie Guo, Liang Zhao, Cameron Nowzari +3

Generalized from image and language translation, graph translation aims to generate a graph in the target domain by conditioning an input graph in the source domain. This promising…

cs.LG2020

Code-Bridged Classifier (CBC): A Low or Negative Overhead Defense for Making a CNN Classifier Robust Against Adversarial Attacks

Farnaz Behnia, Ali Mirzaeian, Mohammad Sabokrou +6

In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even…