Complementary label learning (CLL) requires annotators to give
irrelevan...
The need to learn from positive and unlabeled data, or PU learning, aris...
Backdoor attacks have been shown to be a serious security threat against...
Positive-unlabeled (PU) learning deals with binary classification proble...
In 3D face reconstruction, orthogonal projection has been widely employe...
Actuated by the growing attention to personal healthcare and the pandemi...
For the scalability of industrial online advertising systems, a two-stag...
The goal of multi-label learning (MLL) is to associate a given instance ...
In online advertising, auto-bidding has become an essential tool for
adv...
Partial-label (PL) learning is a typical weakly supervised classificatio...
In e-commerce advertising, the ad platform usually relies on auction
mec...
Ordinary (pointwise) binary classification aims to learn a binary classi...
To drive purchase in online advertising, it is of the advertiser's great...
Partial-label learning (PLL) is a multi-class classification problem, wh...
In E-commerce, advertising is essential for merchants to reach their tar...
Partial-label learning is one of the important weakly supervised learnin...
In the early history of positive-unlabeled (PU) learning, the sample
sel...
It is challenging to train deep neural networks robustly on the
industri...
We consider the recovery of a low-rank matrix from its clipped observati...
We consider a challenging multi-label classification problem where both
...
Training robust deep networks is challenging under noisy labels. Current...
Feature missing is a serious problem in many applications, which may lea...