454 citations · 3.1k across the 117 of their papers we have counts for
10 papers · 1 filter
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
Hongxin Wei, Huiping Zhuang, Renchunzi Xie +4
In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks. Cross Entropy (CE) loss has been s…
Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning
Tingting Zhao, Ying Wang, Wei Sun +3
Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been…
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Jianan Zhou, Jianing Zhu, Jingfeng Zhang +4
Adversarial training (AT) with imperfect supervision is significant but receives limited attention. To push AT towards more practical scenarios, we explore a brand new yet challeng…
FedMT: Federated Learning with Mixed-type Labels
Qiong Zhang, Jing Peng, Xin Zhang +3
In federated learning (FL), classifiers (e.g., deep networks) are trained on datasets from multiple data centers without exchanging data across them, which improves the sample effi…
Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack
Ruize Gao, Jiongxiao Wang, Kaiwen Zhou +5
The AutoAttack (AA) has been the most reliable method to evaluate adversarial robustness when considerable computational resources are available. However, the high computational co…
Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
De Cheng, Tongliang Liu, Yixiong Ning +5
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifie…
Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Nan Lu, Zhao Wang, Xiaoxiao Li +3
Supervised federated learning (FL) enables multiple clients to share the trained model without sharing their labeled data. However, potential clients might even be reluctant to lab…
On the Effectiveness of Adversarial Training against Backdoor Attacks
Yinghua Gao, Dongxian Wu, Jingfeng Zhang +4
DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor at…
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Takashi Ishida, Ikko Yamane, Nontawat Charoenphakdee +2
There is a fundamental limitation in the prediction performance that a machine learning model can achieve due to the inevitable uncertainty of the prediction target. In classificat…
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
Haobo Wang, Ruixuan Xiao, Yixuan Li +4
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation s…