Masashi Sugiyama
8 papers in the PaperMetrix corpus
Papers by this author
-
Masking: A New Perspective of Noisy Supervision
2018 · arXiv (Cornell University)
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 labels by an unknown noise transition matrix. …
-
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis
2019 · arXiv (Cornell University)
The notion of flat minima has played a key role in the generalization studies of deep learning models. However, existing definitions of the flatness are known to be sensitive to the rescaling of parameters. The …
-
Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero
2019 · arXiv (Cornell University)
There have been increasing challenges to solve combinatorial optimization problems by machine learning. Khalil et al. proposed an end-to-end reinforcement learning framework, S2V-DQN, which automatically learns graph embeddings to construct solutions to a wide range …
-
Binary Classification from Positive Data with Skewed Confidence
2020
Positive-confidence (Pconf) classification [Ishida et al., 2018] is a promising weakly-supervised learning method which trains a binary classifier only from positive data equipped with confidence. However, in practice, the confidence may be skewed by bias …
-
Few-shot Domain Adaptation by Causal Mechanism Transfer
2020 · International Conference on Machine Learning
We study few-shot supervised domain adaptation (DA) for regression problems, where only a few labeled target domain data and many labeled source domain data are available. Many of the current DA methods base their transfer …
-
Provably Consistent Partial-Label Learning
2020 · Neural Information Processing Systems
Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels. Even though many practical PLL methods have been proposed in the last two decades, there …
-
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
2021 · arXiv (Cornell University)
We investigate the adversarial robustness of CNNs from the perspective of channel-wise activations. By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise …
-
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning
2024 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to instance-dependent noises. In this …