75 citations · 202 across the 18 of their papers we have counts for
15 papers · 1 filter
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
Zhenlong Liu, Lei Feng, Huiping Zhuang +2
Machine learning models are susceptible to membership inference attacks (MIAs), which aim to infer whether a sample is in the training set. Existing work utilizes gradient ascent t…
Does confidence calibration improve conformal prediction?
Huajun Xi, Jianguo Huang, Kangdao Liu +2
Conformal prediction is an emerging technique for uncertainty quantification that constructs prediction sets guaranteed to contain the true label with a predefined probability. Pre…
Regression with Cost-based Rejection
Xin Cheng, Yuzhou Cao, Haobo Wang +3
Learning with rejection is an important framework that can refrain from making predictions to avoid critical mispredictions by balancing between prediction and rejection. Previous…
In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer
Yuzhou Cao, Hussein Mozannar, Lei Feng +2
Enabling machine learning classifiers to defer their decision to a downstream expert when the expert is more accurate will ensure improved safety and performance. This objective ca…
A Generalized Unbiased Risk Estimator for Learning with Augmented Classes
Senlin Shu, Shuo He, Haobo Wang +3
In contrast to the standard learning paradigm where all classes can be observed in training data, learning with augmented classes (LAC) tackles the problem where augmented classes…
DOS: Diverse Outlier Sampling for Out-of-Distribution Detection
Wenyu Jiang, Hao Cheng, Mingcai Chen +2
Modern neural networks are known to give overconfident prediction for out-of-distribution inputs when deployed in the open world. It is common practice to leverage a surrogate outl…
On the Importance of Feature Separability in Predicting Out-Of-Distribution Error
Renchunzi Xie, Hongxin Wei, Lei Feng +2
Estimating the generalization performance is practically challenging on out-of-distribution (OOD) data without ground-truth labels. While previous methods emphasize the connection…
CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning
Shiyu Tian, Hongxin Wei, Yiqun Wang +1
Partial-label learning (PLL) is an important weakly supervised learning problem, which allows each training example to have a candidate label set instead of a single ground-truth l…
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…
Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets
Hongxin Wei, Lue Tao, Renchunzi Xie +2
Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance. Recent studies found that directly training with out-of-distribution dat…
Mitigating Neural Network Overconfidence with Logit Normalization
Hongxin Wei, Renchunzi Xie, Hao Cheng +3
Detecting out-of-distribution inputs is critical for safe deployment of machine learning models in the real world. However, neural networks are known to suffer from the overconfide…
GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation
Renchunzi Xie, Hongxin Wei, Lei Feng +1
This paper studies weakly supervised domain adaptation(WSDA) problem, where we only have access to the source domain with noisy labels, from which we need to transfer useful inform…
Can Adversarial Training Be Manipulated By Non-Robust Features?
Lue Tao, Lei Feng, Hongxin Wei +3
Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability…
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
Hongxin Wei, Lue Tao, Renchunzi Xie +1
Learning with noisy labels is a practically challenging problem in weakly supervised learning. In the existing literature, open-set noises are always considered to be poisonous for…
MetaInfoNet: Learning Task-Guided Information for Sample Reweighting
Hongxin Wei, Lei Feng, Rundong Wang +1
Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance. Meta-learning algorithms are commonly designed to alleviate this…