454 citations · 5.5k across the 247 of their papers we have counts for
30 papers · 1 filter
Rethinking Importance Weighting for Transfer Learning
Nan Lu, Tianyi Zhang, Tongtong Fang +2
A key assumption in supervised learning is that training and test data follow the same probability distribution. However, this fundamental assumption is not always satisfied in pra…
Learning with Proper Partial Labels
Zhenguo Wu, Jiaqi Lv, Masashi Sugiyama
Partial-label learning is a kind of weakly-supervised learning with inexact labels, where for each training example, we are given a set of candidate labels instead of only one true…
Active Refinement for Multi-Label Learning: A Pseudo-Label Approach
Cheng-Yu Hsieh, Wei-I Lin, Miao Xu +3
The goal of multi-label learning (MLL) is to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where t…
Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences
Ikko Yamane, Junya Honda, Florian Yger +1
Ordinary supervised learning is useful when we have paired training data of input and output . However, such paired data can be difficult to collect in practice. In this pap…
Positive-Unlabeled Classification under Class-Prior Shift: A Prior-invariant Approach Based on Density Ratio Estimation
Shota Nakajima, Masashi Sugiyama
Learning from positive and unlabeled (PU) data is an important problem in various applications. Most of the recent approaches for PU classification assume that the class-prior (the…
Multi-Class Classification from Single-Class Data with Confidences
Yuzhou Cao, Lei Feng, Senlin Shu +4
Can we learn a multi-class classifier from only data of a single class? We show that without any assumptions on the loss functions, models, and optimizers, we can successfully lear…
Loss function based second-order Jensen inequality and its application to particle variational inference
Futoshi Futami, Tomoharu Iwata, Naonori Ueda +2
Bayesian model averaging, obtained as the expectation of a likelihood function by a posterior distribution, has been widely used for prediction, evaluation of uncertainty, and mode…
Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning
Xin-Qiang Cai, Yao-Xiang Ding, Zi-Xuan Chen +3
In many real-world imitation learning tasks, the demonstrator and the learner have to act under different observation spaces. This situation brings significant obstacles to existin…
Probabilistic Margins for Instance Reweighting in Adversarial Training
Qizhou Wang, Feng Liu, Bo Han +5
Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more cr…
On the Robustness of Average Losses for Partial-Label Learning
Jiaqi Lv, Biao Liu, Lei Feng +6
Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL). In PLL, identification-based strategy (I…
Instance Correction for Learning with Open-set Noisy Labels
Xiaobo Xia, Tongliang Liu, Bo Han +4
The problem of open-set noisy labels denotes that part of training data have a different label space that does not contain the true class. Lots of approaches, e.g., loss correction…
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Xiaobo Xia, Tongliang Liu, Bo Han +4
In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-t…
A unified view of likelihood ratio and reparameterization gradients
Paavo Parmas, Masashi Sugiyama
Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used to estimate gradients of expectations throughout machine learning and reinforcement learning; however…
NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels
Jingfeng Zhang, Xilie Xu, Bo Han +4
Adversarial training (AT) formulated as the minimax optimization problem can effectively enhance the model's robustness against adversarial attacks. The existing AT methods mainly…
Approximating Instance-Dependent Noise via Instance-Confidence Embedding
Yivan Zhang, Masashi Sugiyama
Label noise in multiclass classification is a major obstacle to the deployment of learning systems. However, unlike the widely used class-conditional noise (CCN) assumption that th…
Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization
Zeke Xie, Li Yuan, Zhanxing Zhu +1
It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of dee…
Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information
Takayuki Osa, Voot Tangkaratt, Masashi Sugiyama
Reinforcement learning algorithms are typically limited to learning a single solution for a specified task, even though diverse solutions often exist. Recent studies showed that le…
Lower-Bounded Proper Losses for Weakly Supervised Classification
Shuhei M. Yoshida, Takashi Takenouchi, Masashi Sugiyama
This paper discusses the problem of weakly supervised classification, in which instances are given weak labels that are produced by some label-corruption process. The goal is to de…
LocalDrop: A Hybrid Regularization for Deep Neural Networks
Ziqing Lu, Chang Xu, Bo Du +3
In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas. We propose a new approach for the regularization of neural networks…
Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation
Takeshi Teshima, Masashi Sugiyama
Causal graphs (CGs) are compact representations of the knowledge of the data generating processes behind the data distributions. When a CG is available, e.g., from the domain knowl…
Guided Interpolation for Adversarial Training
Chen Chen, Jingfeng Zhang, Xilie Xu +4
To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data. However, as the training progresses…
Learning from Similarity-Confidence Data
Yuzhou Cao, Lei Feng, Yitian Xu +3
Weakly supervised learning has drawn considerable attention recently to reduce the expensive time and labor consumption of labeling massive data. In this paper, we investigate a no…
Understanding the Interaction of Adversarial Training with Noisy Labels
Jianing Zhu, Jingfeng Zhang, Bo Han +5
Noisy labels (NL) and adversarial examples both undermine trained models, but interestingly they have hitherto been studied independently. A recent adversarial training (AT) study…
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
Hanshu Yan, Jingfeng Zhang, Gang Niu +3
We investigate the adversarial robustness of CNNs from the perspective of channel-wise activations. By comparing \textit{non-robust} (normally trained) and \textit{robustified} (ad…