Gang Niu

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. …

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 …

FedMT: Federated Learning with Mixed-type Labels

2022 · arXiv (Cornell University)

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 efficiency. However, the conventional FL setting assumes the same labeling …

On the Role of Label Noise in the Feature Learning Process

2025 · arXiv (Cornell University)

Deep learning with noisy labels presents significant challenges. In this work, we theoretically characterize the role of label noise from a feature learning perspective. Specifically, we consider a signal-noise data distribution, where each sample comprises …