Pin‐Yu Chen

On the Supermodularity of Active Graph-based Semi-supervised Learning with Stieltjes Matrix Regularization

2018 · arXiv (Cornell University)

Active graph-based semi-supervised learning (AG-SSL) aims to select a small set of labeled examples and utilize their graph-based relation to other unlabeled examples to aid in machine learning tasks. It is also closely related to …

Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent

2020 · arXiv (Cornell University)

Despite the great achievements of the modern deep neural networks (DNNs), the vulnerability/robustness of state-of-the-art DNNs raises security concerns in many application domains requiring high reliability. Various adversarial attacks are proposed to sabotage the learning …

Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks

2021 · arXiv (Cornell University)

The use of language is subject to variation over time as well as across social groups and knowledge domains, leading to differences even in the monolingual scenario. Such variation in word usage is often called …

Fast Training of Provably Robust Neural Networks by SingleProp

2021 · arXiv (Cornell University)

Recent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees. However, these techniques can be computationally costly due to the use of certification during training. We develop a new …

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

2021 · arXiv (Cornell University)

Unsupervised domain adaptation (UDA) enables cross-domain learning without target domain labels by transferring knowledge from a labeled source domain whose distribution differs from that of the target. However, UDA is not always successful and several …

RADAR: Robust AI-Text Detection via Adversarial Learning

2023 · arXiv (Cornell University)

Recent advances in large language models (LLMs) and the intensifying popularity of ChatGPT-like applications have blurred the boundary of high-quality text generation between humans and machines. However, in addition to the anticipated revolutionary changes to …

It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition

2024 · arXiv (Cornell University)

Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. Specifically, an LLM is utilized to carry …

The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models

2024 · arXiv (Cornell University)

Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic results in application. Previous works on this problem mainly focused …

Quantum Machine Learning: An Interplay Between Quantum Computing and Machine Learning

2024 · arXiv (Cornell University)

Quantum machine learning (QML) is a rapidly growing field that combines quantum computing principles with traditional machine learning. It seeks to revolutionize machine learning by harnessing the unique capabilities of quantum mechanics and employs machine …