activity
20152023
most citedA Two-Stage Attentive Network for Single Image Super-Resolution

85 citations · 284 across the 33 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2023

Fast Adversarial Training with Smooth Convergence

Mengnan Zhao, Lihe Zhang, Yuqiu Kong +1

Fast adversarial training (FAT) is beneficial for improving the adversarial robustness of neural networks. However, previous FAT work has encountered a significant issue known as c…

cs.LG2022★ 3 cited

NodeTrans: A Graph Transfer Learning Approach for Traffic Prediction

Xueyan Yin, Feifan Li, Yanming Shen +2

Recently, deep learning methods have made great progress in traffic prediction, but their performance depends on a large amount of historical data. In reality, we may face the data…

cs.LG2022★ 17 cited

Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks

Mingqi Yang, Yanming Shen, Heng Qi +1

For learning graph representations, not all detailed structures within a graph are relevant to the given graph tasks. Task-relevant structures can be or which…

cs.LG2021

A New Perspective on the Effects of Spectrum in Graph Neural Networks

Mingqi Yang, Yanming Shen, Rui Li +3

Many improvements on GNNs can be deemed as operations on the spectrum of the underlying graph matrix, which motivates us to directly study the characteristics of the spectrum and t…

cs.LG2021★ 3 cited

Temporal Knowledge Graph Reasoning Triggered by Memories

Mengnan Zhao, Lihe Zhang, Yuqiu Kong +1

Inferring missing facts in temporal knowledge graphs is a critical task and has been widely explored. Extrapolation in temporal reasoning tasks is more challenging and gradually at…

cs.LG2020★ 3 cited

Breaking the Expressive Bottlenecks of Graph Neural Networks

Mingqi Yang, Yanming Shen, Heng Qi +1

Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressiveness of graph neural networks (GNNs), showing that the neighborhood aggregation GNNs w…