Random label noises (or observational noises) widely exist in practical
...
The conventional understanding of adversarial training in generative
adv...
It is well-known that stochastic gradient noise (SGN) acts as implicit
r...
Despite the empirical success in various domains, it has been revealed t...
Knowledge distillation is a strategy of training a student network with ...
We consider the fundamental problem of how to automatically construct su...
Convolutional Neural Networks (CNNs) are known to rely more on local tex...
We comprehensively reveal the learning dynamics of deep neural networks ...
The scarcity of class-labeled data is a ubiquitous bottleneck in a wide ...
The wide deployment of deep neural networks, though achieving great succ...
Randomized classifiers have been shown to provide a promising approach f...
Regularization plays a crucial role in machine learning models, especial...
Transfer learning have been frequently used to improve deep neural netwo...
Data-driven modeling of human motions is ubiquitous in computer graphics...
The design of deep graph models still remains to be investigated and the...
The randomness in Stochastic Gradient Descent (SGD) is considered to pla...
Neural architecture search (NAS) recently attracts much research attenti...
Convolutional neural networks (CNNs) have achieved remarkable performanc...
We attempt to interpret how adversarially trained convolutional neural
n...
Though neural networks have achieved much progress in various applicatio...
Deep learning achieves state-of-the-art results in many areas. However r...
Deep learning achieves state-of-the-art results in many areas. However r...
The spatio-temporal graph learning is becoming an increasingly important...
Spatio-temporal prediction plays an important role in many application a...
The effectiveness of Graph Convolutional Networks (GCNs) has been
demons...
Graph Convolutional Networks(GCNs) play a crucial role in graph learning...
Deep neural networks have been widely deployed in various machine learni...
Most previous works usually explained adversarial examples from several
...
We interpret the variational inference of the Stochastic Gradient Descen...
The ever-increasing size of modern datasets combined with the difficulty...
In statistics and machine learning, approximation of an intractable
inte...
Most artificial intelligence models have limiting ability to solve new t...
Understanding the generalization of deep learning has raised lots of con...
State-of-the-art deep neural networks are known to be vulnerable to
adve...
The goal of traffic forecasting is to predict the future vital indicator...
It is widely observed that deep learning models with learned parameters
...
Distant supervision significantly reduces human efforts in building trai...
Minimizing non-convex and high-dimensional objective functions is
challe...
We consider convex-concave saddle point problems with a separable struct...
Monte Carlo sampling for Bayesian posterior inference is a common approa...
We consider a generic convex-concave saddle point problem with separable...