454 citations · 2.5k across the 132 of their papers we have counts for
16 papers · 1 filter
Privacy-preserving Stochastic Gradual Learning
Bo Han, Ivor W. Tsang, Xiaokui Xiao +3
It is challenging for stochastic optimizations to handle large-scale sensitive data safely. Recently, Duchi et al. proposed private sampling strategy to solve privacy leakage in st…
SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
Bo Han, Gang Niu, Xingrui Yu +4
Given data with noisy labels, over-parameterized deep networks can gradually memorize the data, and fit everything in the end. Although equipped with corrections for noisy labels,…
Target-Independent Active Learning via Distribution-Splitting
Xiaofeng Cao, Ivor W. Tsang, Xiaofeng Xu +1
To reduce the label complexity in Agnostic Active Learning (A^2 algorithm), volume-splitting splits the hypothesis edges to reduce the Vapnik-Chervonenkis (VC) dimension in version…
XAI Beyond Classification: Interpretable Neural Clustering
Xi Peng, Yunnan Li, Ivor W. Tsang +3
In this paper, we study two challenging problems in explainable AI (XAI) and data clustering. The first is how to directly design a neural network with inherent interpretability, r…
A Structured Perspective of Volumes on Active Learning
Xiaofeng Cao, Ivor W. Tsang, Guandong Xu
Active Learning (AL) is a learning task that requires learners interactively query the labels of the sampled unlabeled instances to minimize the training outputs with human supervi…
Understanding VAEs in Fisher-Shannon Plane
Huangjie Zheng, Jiangchao Yao, Ya Zhang +2
In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the unce…
Matrix Co-completion for Multi-label Classification with Missing Features and Labels
Miao Xu, Gang Niu, Bo Han +3
We consider a challenging multi-label classification problem where both feature matrix $\X$ and label matrix $\Y$ have missing entries. An existing method concatenated $\X$ and $\Y…
A Divide-and-Conquer Approach to Geometric Sampling for Active Learning
Xiaofeng Cao
Active learning (AL) repeatedly trains the classifier with the minimum labeling budget to improve the current classification model. The training process is usually supervised by an…
Masking: A New Perspective of Noisy Supervision
Bo Han, Jiangchao Yao, Gang Niu +4
It is important to learn various types of classifiers given training data with noisy labels. Noisy labels, in the most popular noise model hitherto, are corrupted from ground-truth…
Label Embedding with Partial Heterogeneous Contexts
Yaxin Shi, Donna Xu, Yuangang Pan +2
Label embedding plays an important role in many real-world applications. To enhance the label relatedness captured by the embeddings, multiple contexts can be adopted. However, the…
Variational Composite Autoencoders
Jiangchao Yao, Ivor Tsang, Ya Zhang
Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable. Previous variational autoencoders can be low…
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
Bo Han, Quanming Yao, Xingrui Yu +5
Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during train…
Complementary Attributes: A New Clue to Zero-Shot Learning
Xiaofeng Xu, Ivor W. Tsang, Chuancai Liu
Zero-shot learning (ZSL) aims to recognize unseen objects using disjoint seen objects via sharing attributes. The generalization performance of ZSL is governed by the attributes, w…
Millionaire: A Hint-guided Approach for Crowdsourcing
Bo Han, Quanming Yao, Yuangang Pan +4
Modern machine learning is migrating to the era of complex models, which requires a plethora of well-annotated data. While crowdsourcing is a promising tool to achieve this goal, e…
VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning
Fanhua Shang, Kaiwen Zhou, Hongying Liu +5
In this paper, we propose a simple variant of the original SVRG, called variance reduced stochastic gradient descent (VR-SGD). Unlike the choices of snapshot and starting points in…
Degeneration in VAE: in the Light of Fisher Information Loss
Huangjie Zheng, Jiangchao Yao, Ya Zhang +1
While enormous progress has been made to Variational Autoencoder (VAE) in recent years, similar to other deep networks, VAE with deep networks suffers from the problem of degenerat…