most citedWhen Does Self-Supervision Help Graph Convolutional Networks?

65 citations · 87 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG202065 cited

When Does Self-Supervision Help Graph Convolutional Networks?

Yuning You, Tianlong Chen, Zhangyang Wang +1

Self-supervision as an emerging technique has been employed to train convolutional neural networks (CNNs) for more transferrable, generalizable, and robust representation learning…

q-bio.MN2020

Network-principled deep generative models for designing drug combinations as graph sets

Mostafa Karimi, Arman Hasanzadeh, Yang shen

Combination therapy has shown to improve therapeutic efficacy while reducing side effects. Importantly, it has become an indispensable strategy to overcome resistance in antibiotic…

cs.LG2020

L-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

Yuning You, Tianlong Chen, Zhangyang Wang +1

Graph convolution networks (GCN) are increasingly popular in many applications, yet remain notoriously hard to train over large graph datasets. They need to compute node representa…

q-bio.BM20195 cited

Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts

Mostafa Karimi, Di Wu, Zhangyang Wang +1

Predicting compound-protein affinity is critical for accelerating drug discovery. Recent progress made by machine learning focuses on accuracy but leaves much to be desired for int…

cs.LG201914 cited

Learning to Optimize in Swarms

Yue Cao, Tianlong Chen, Zhangyang Wang +1

Learning to optimize has emerged as a powerful framework for various optimization and machine learning tasks. Current such "meta-optimizers" often learn in the space of continuous…

q-bio.BM20193 cited

Bayesian active learning for optimization and uncertainty quantification in protein docking

Yue Cao, Yang Shen

Motivation: Ab initio protein docking represents a major challenge for optimizing a noisy and costly "black box"-like function in a high-dimensional space. Despite progress in this…