The rawly collected training data often comes with separate noisy labels collected from
multiple imperfect annotators (eg, via crowdsourcing). A typical way of using these separate …

There are demographic biases present in current facial recognition (FR) models. To
measure these biases across different ethnic and gender subgroups, we introduce our …

A rising trend in theoretical deep learning is to understand why deep learning works through
Neural Tangent Kernel (NTK)[jgh18], a kernel method that is equivalent to using gradient …

Both long-tailed and noisily labeled data frequently appear in real-world applications and
impose significant challenges for learning. Most prior works treat either problem in an …

The knowledge distillation-based approaches have recently yielded state-of-the-art (SOTA)
results for cross-lingual NER tasks in zero-shot scenarios. These approaches typically …

Adaptive gradient methods, eg, ADAM, have achieved tremendous success in data-driven
machine learning, especially deep learning. Employing adaptive learning rates according to …

Large-scale models, abundant data, and dense computation are the pivotal pillars of deep
neural networks. The present-day deep learning models have made significant strides in …

Artificial intelligence (AI) empowered by deep learning, has been profoundly transforming
the world. However, the excessive size of these models remains a central obstacle that limits …

We consider the problem of fine-tuning pre-trained language models with a small amount of
trusted data (high-fidelity) and a larger amount of data with noisy labels (low-fidelity). We …