Cen Chen

Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations

2020 · arXiv (Cornell University)

Information-seeking conversation systems are increasingly popular in real-world applications, especially for e-commerce companies. To retrieve appropriate responses for users, it is necessary to compute the matching degrees between candidate responses and users' queries with historical …

Towards Scalable and Privacy-Preserving Deep Neural Network via Algorithmic-Cryptographic Co-design

2020 · arXiv (Cornell University)

Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build privacy preserving DNN models …

Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons

2022 · arXiv (Cornell University)

The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones. In this paper, we propose a novel backdoor …

TransPrompt v2: Transferable Prompt-based Fine-tuning for Few-shot Text Classification

2022 · Research Square

Abstract Recent studies have shown that prompt-based fine-tuning improves the performance of large Pre-trained Language Models (PLMs) for few-shot text classification. Specifically, this type of method transforms the text classification task into the inherent Masked …

Communication Efficient Federated Learning via Channel-wise Dynamic Pruning

2023

Federated Learning (FL) received widespread attention in 5G mobile edge networks (MENs) as it enables collaborative training deep learning models without disclosing users' private data. As the increasing number of parameters in the machine learning …

UPFL: Unsupervised Personalized Federated Learning towards New Clients

2023 · arXiv (Cornell University)

Personalized federated learning has gained significant attention as a promising approach to address the challenge of data heterogeneity. In this paper, we address a relatively unexplored problem in federated learning. When a federated model has …

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness

2023 · arXiv (Cornell University)

A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimization and its variants. However, the …

ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Early Exiting is one of the most popular methods to achieve efficient inference. Current early exiting methods adopt the (weighted) sum of the cross entropy loss of all internal classifiers as the objective function during …