activity
20192021
most citedDeep Learning of High-Order Interactions for Protein Interface Prediction

50 citations · 58 across the 5 of their papers we have counts for

collaborators

8 papers

cs.CL2021

Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence

Hongyang Gao, Yi Liu, Xuan Zhang +1

We study text representation methods using deep models. Current methods, such as word-level embedding and character-level embedding schemes, treat texts as either a sequence of ato…

cs.LG2021

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

Meng Liu, Youzhi Luo, Limei Wang +13

Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning. In the research community, implementin…

eess.IV20216 cited

A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis

Yi Liu, Shuiwang Ji

Computed tomography (CT) imaging is a promising approach to diagnosing the COVID-19. Machine learning methods can be employed to train models from labeled CT images and predict whe…

cs.CV2021

CleftNet: Augmented Deep Learning for Synaptic Cleft Detection from Brain Electron Microscopy

Yi Liu, Shuiwang Ji

Detecting synaptic clefts is a crucial step to investigate the biological function of synapses. The volume electron microscopy (EM) allows the identification of synaptic clefts by…

cs.LG2020

Topology-Aware Graph Pooling Networks

Hongyang Gao, Yi Liu, Shuiwang Ji

Pooling operations have shown to be effective on computer vision and natural language processing tasks. One challenge of performing pooling operations on graph data is the lack of…

cs.IR20202 cited

Machine Learning Explanations to Prevent Overtrust in Fake News Detection

Sina Mohseni, Fan Yang, Shiva Pentyala +6

Combating fake news and misinformation propagation is a challenging task in the post-truth era. News feed and search algorithms could potentially lead to unintentional large-scale…