59 citations · 181 across the 11 of their papers we have counts for
11 papers
NodeMixup: Tackling Under-Reaching for Graph Neural Networks
Weigang Lu, Ziyu Guan, Wei Zhao +2
Graph Neural Networks (GNNs) have become mainstream methods for solving the semi-supervised node classification problem. However, due to the uneven location distribution of labeled…
Zero Stability Well Predicts Performance of Convolutional Neural Networks
Liangming Chen, Long Jin, Mingsheng Shang
The question of what kind of convolutional neural network (CNN) structure performs well is fascinating. In this work, we move toward the answer with one more step by connecting zer…
Decoupling the Depth and Scope of Graph Neural Networks
Hanqing Zeng, Muhan Zhang, Yinglong Xia +6
State-of-the-art Graph Neural Networks (GNNs) have limited scalability with respect to the graph and model sizes. On large graphs, increasing the model depth often means exponentia…
Activated Gradients for Deep Neural Networks
Mei Liu, Liangming Chen, Xiaohao Du +2
Deep neural networks often suffer from poor performance or even training failure due to the ill-conditioned problem, the vanishing/exploding gradient problem, and the saddle point…
Deep Graph Neural Networks with Shallow Subgraph Samplers
Hanqing Zeng, Muhan Zhang, Yinglong Xia +6
While Graph Neural Networks (GNNs) are powerful models for learning representations on graphs, most state-of-the-art models do not have significant accuracy gain beyond two to thre…
Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
Muhan Zhang, Pan Li, Yinglong Xia +2
In this paper, we provide a theory of using graph neural networks (GNNs) for multi-node representation learning (where we are interested in learning a representation for a set of m…
Deforming the Loss Surface to Affect the Behaviour of the Optimizer
Liangming Chen, Long Jin, Xiujuan Du +2
In deep learning, it is usually assumed that the optimization process is conducted on a shape-fixed loss surface. Differently, we first propose a novel concept of deformation mappi…
Deforming the Loss Surface
Liangming Chen, Long Jin, Xiujuan Du +2
In deep learning, it is usually assumed that the shape of the loss surface is fixed. Differently, a novel concept of deformation operator is first proposed in this paper to deform…
Introspective Generative Modeling: Decide Discriminatively
Justin Lazarow, Long Jin, Zhuowen Tu
We study unsupervised learning by developing introspective generative modeling (IGM) that attains a generator using progressively learned deep convolutional neural networks. The ge…
Introspective Classification with Convolutional Nets
Long Jin, Justin Lazarow, Zhuowen Tu
We propose introspective convolutional networks (ICN) that emphasize the importance of having convolutional neural networks empowered with generative capabilities. We employ a recl…
Object Detection Free Instance Segmentation With Labeling Transformations
Long Jin, Zeyu Chen, Zhuowen Tu
Instance segmentation has attracted recent attention in computer vision and existing methods in this domain mostly have an object detection stage. In this paper, we study the intri…