4 citations · 16 across the 19 of their papers we have counts for
20 papers
Quantifying and Understanding Uncertainty in Large Reasoning Models
Yangyi Li, Chenxu Zhao, Mengdi Huai
Large Reasoning Models (LRMs) have recently demonstrated significant improvements in complex reasoning. While quantifying generation uncertainty in LRMs is crucial, traditional met…
Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning
Aobo Chen, Chenxu Zhao, Chenglin Miao +1
Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LR…
Selective Forgetting for Large Reasoning Models
Tuan Le, Wei Qian, Mengdi Huai
Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermedia…
Uncertainty-aware Language Guidance for Concept Bottleneck Models
Yangyi Li, Mengdi Huai
Concept Bottleneck Models (CBMs) provide inherent interpretability by first mapping input samples to high-level semantic concepts, followed by a combination of these concepts for t…
Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models
Wei Qian, Chenxu Zhao, Yangyi Li +1
The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledgeable learning systems. As these systems are i…
Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering
Yangyi Li, Mengdi Huai
Large language models (LLMs) have shown strong capabilities, enabling concise, context-aware answers in question answering (QA) tasks. The lack of transparency in complex LLMs has…
Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten
Wei Qian, Chenxu Zhao, Yangyi Li +2
Currently, various uncertainty quantification methods have been proposed to provide certainty and probability estimates for deep learning models' label predictions. Meanwhile, with…
Membership Inference Attacks with False Discovery Rate Control
Chenxu Zhao, Wei Qian, Aobo Chen +1
Recent studies have shown that deep learning models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model…
Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning
Jiaqi Wang, Chenxu Zhao, Lingjuan Lyu +3
This paper presents FedType, a simple yet pioneering framework designed to fill research gaps in heterogeneous model aggregation within federated learning (FL). FedType introduces…
Synthesizing Multimodal Electronic Health Records via Predictive Diffusion Models
Yuan Zhong, Xiaochen Wang, Jiaqi Wang +5
Synthesizing electronic health records (EHR) data has become a preferred strategy to address data scarcity, improve data quality, and model fairness in healthcare. However, existin…
Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgotten
Wei Qian, Aobo Chen, Chenxu Zhao +2
In education data mining (EDM) communities, machine learning has achieved remarkable success in discovering patterns and structures to tackle educational challenges. Notably, fairn…
Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Prediction
Wei Qian, Chenxu Zhao, Yangyi Li +3
Despite the recent progress in deep neural networks (DNNs), it remains challenging to explain the predictions made by DNNs. Existing explanation methods for DNNs mainly focus on po…
AdvST: Revisiting Data Augmentations for Single Domain Generalization
Guangtao Zheng, Mengdi Huai, Aidong Zhang
Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an ef…
Improving Interpretation Faithfulness for Vision Transformers
Lijie Hu, Yixin Liu, Ninghao Liu +3
Vision Transformers (ViTs) have achieved state-of-the-art performance for various vision tasks. One reason behind the success lies in their ability to provide plausible innate expl…
Automated Natural Language Explanation of Deep Visual Neurons with Large Models
Chenxu Zhao, Wei Qian, Yucheng Shi +2
Deep neural networks have exhibited remarkable performance across a wide range of real-world tasks. However, comprehending the underlying reasons for their effectiveness remains a…
MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation
Yuan Zhong, Suhan Cui, Jiaqi Wang +7
Health risk prediction is one of the fundamental tasks under predictive modeling in the medical domain, which aims to forecast the potential health risks that patients may face in…
White-box Membership Inference Attacks against Diffusion Models
Yan Pang, Tianhao Wang, Xuhui Kang +2
Diffusion models have begun to overshadow GANs and other generative models in industrial applications due to their superior image generation performance. The complex architecture o…
Inductive Graph Unlearning
Cheng-Long Wang, Mengdi Huai, Di Wang
As a way to implement the "right to be forgotten" in machine learning, \textit{machine unlearning} aims to completely remove the contributions and information of the samples to be…
Understanding and Enhancing Robustness of Concept-based Models
Sanchit Sinha, Mengdi Huai, Jianhui Sun +1
Rising usage of deep neural networks to perform decision making in critical applications like medical diagnosis and financial analysis have raised concerns regarding their reliabil…
SEAT: Stable and Explainable Attention
Lijie Hu, Yixin Liu, Ninghao Liu +3
Currently, attention mechanism becomes a standard fixture in most state-of-the-art natural language processing (NLP) models, not only due to outstanding performance it could gain,…