no code implementations • 28 Apr 2024 • Zesheng Hong, Yubiao Yue, Yubin Chen, Huanjie Lin, Yuanmei Luo, Mini Han Wang, Weidong Wang, Jialong Xu, Xiaoqi Yang, Zhenzhang Li, Sihong Xie
Recently, research has explored various out-of-distribution (OOD) detection situations and techniques to enable a trustworthy medical AI system.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 23 Apr 2024 • Chao Chen, Chenghua Guo, Rui Xu, Xiangwen Liao, Xi Zhang, Sihong Xie, Hui Xiong, Philip Yu
Graphical models, including Graph Neural Networks (GNNs) and Probabilistic Graphical Models (PGMs), have demonstrated their exceptional capabilities across numerous fields.
no code implementations • 1 Apr 2024 • Yue Sun, Chao Chen, Yuesheng Xu, Sihong Xie, Rick S. Blum, Parv Venkitasubramaniam
We theoretically derive conditions where GCNs incorporating such domain differential equations are robust to mismatched training and testing data compared to baseline domain agnostic models.
no code implementations • 22 Mar 2024 • Rui Xu, Yue Sun, Chao Chen, Parv Venkitasubramaniam, Sihong Xie
Uncertainty is critical to reliable decision-making with machine learning.
no code implementations • 11 Mar 2024 • Yazheng Liu, Xi Zhang, Sihong Xie
Graphs are ubiquitous in social networks and biochemistry, where Graph Neural Networks (GNN) are the state-of-the-art models for prediction.
no code implementations • 25 Feb 2024 • Ainara Garcia, Sihong Xie, Arielle Carr
The goal of this project was to implement RMINRES in Python and PyTorch and add it to the established Pareto front code to reduce computational cost.
no code implementations • 23 Oct 2023 • Rongsheng Wang, Qi Li, Sihong Xie
Using this observation, we subsequently proposed a new method for AI-generated texts detection based on self-consistency with masked predictions to determine whether a text is generated by LLMs.
no code implementations • 8 Jul 2023 • Chao Chen, Chenghua Guo, Guixiang Ma, Ming Zeng, Xi Zhang, Sihong Xie
Robust explanations of machine learning models are critical to establish human trust in the models.
1 code implementation • 3 Jun 2023 • Mengzhu Sun, Xi Zhang, Jianqiang Ma, Sihong Xie, Yazheng Liu, Philip S. Yu
Rumor spreaders are increasingly utilizing multimedia content to attract the attention and trust of news consumers.
no code implementations • 28 Dec 2022 • Chao Chen, Chenghua Guo, Guixiang Ma, Ming Zeng, Xi Zhang, Sihong Xie
Robust explanations of machine learning models are critical to establishing human trust in the models.
no code implementations • 15 Sep 2022 • Eric Enouen, Katja Mathesius, Sean Wang, Arielle Carr, Sihong Xie
We propose to explore the Pareto front as a manifold from a few initial optima, based on a predictor-corrector method.
no code implementations • 24 Apr 2022 • Jiaxin Liu, Yuefei Lyu, Xi Zhang, Sihong Xie
We first identify subgroup structures in the review graph that lead to discrepant accuracy in the groups.
no code implementations • 15 Jan 2022 • Yuefei Lyu, Xiaoyu Yang, Jiaxin Liu, Philip S. Yu, Sihong Xie, Xi Zhang
To discover subtle vulnerabilities, we design a powerful attacking algorithm to camouflage rumors in social networks based on reinforcement learning that can interact with and attack any black-box detectors.
no code implementations • 29 Nov 2021 • Yifei Liu, Chao Chen, Yazheng Liu, Xi Zhang, Sihong Xie
We design a user study to investigate such joint effects and use the findings to design a multi-objective optimization (MOO) algorithm to find Pareto optimal explanations that are well-balanced in simulatability and counterfactual.
no code implementations • 19 Nov 2021 • Yazheng Liu, Xi Zhang, Sihong Xie
We define the problem of explaining evolving GNN predictions and propose an axiomatic attribution method to uniquely decompose the change in a prediction to paths on computation graphs.
no code implementations • 15 Sep 2021 • Chao Chen, Yifan Shen, Guixiang Ma, Xiangnan Kong, Srinivas Rangarajan, Xi Zhang, Sihong Xie
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced.
1 code implementation • 9 Sep 2021 • Nasim Sabetpour, Adithya Kulkarni, Sihong Xie, Qi Li
The proposed Aggregation method for Sequential Labels from Crowds ($AggSLC$) jointly considers the characteristics of sequential labeling tasks, workers' reliabilities, and advanced machine learning techniques.
1 code implementation • 10 Jun 2020 • Yingtong Dou, Guixiang Ma, Philip S. Yu, Sihong Xie
We experiment on three large review datasets using various state-of-the-art spamming and detection strategies and show that the optimization algorithm can reliably find an equilibrial detector that can robustly and effectively prevent spammers with any mixed spamming strategies from attaining their practical goal.
no code implementations • 21 Apr 2020 • Yifei Liu, Chao Chen, Xi Zhang, Sihong Xie
There is no existing method to rigorously attribute the inference outcomes to the contributing factors of the graphical models.
no code implementations • 13 Aug 2019 • Chao Chen, Yifei Liu, Xi Zhang, Sihong Xie
Probabilistic inferences distill knowledge from graphs to aid human make important decisions.
no code implementations • 11 Nov 2018 • Vahid Noroozi, Sara Bahaadini, Lei Zheng, Sihong Xie, Weixiang Shao, Philip S. Yu
While neural networks for learning representation of multi-view data have been previously proposed as one of the state-of-the-art multi-view dimension reduction techniques, how to make the representation discriminative with only a small amount of labeled data is not well-studied.
Dimensionality Reduction Learning Representation Of Multi-View Data
no code implementations • 9 Nov 2018 • Shuaijun Ge, Guixiang Ma, Sihong Xie, Philip S. Yu
In terms of security, DETER is versatile enough to be vaccinated against diverse and unexpected evasions, is agnostic about evasion strategy and can be released without privacy concern.
no code implementations • 6 Dec 2017 • Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu
Functionality is of utmost importance to customers when they purchase products.
no code implementations • 6 Dec 2017 • Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu
Product compatibility and their functionality are of utmost importance to customers when they purchase products, and to sellers and manufacturers when they sell products.
no code implementations • 12 Jun 2017 • Vahid Noroozi, Lei Zheng, Sara Bahaadini, Sihong Xie, Philip S. Yu
The model consists of two complementary components.
no code implementations • 4 Dec 2016 • Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu
One important product feature is the complementary entity (products) that may potentially work together with the reviewed product.
no code implementations • 11 Aug 2016 • Chenwei Zhang, Sihong Xie, Yaliang Li, Jing Gao, Wei Fan, Philip S. Yu
We propose a novel multi-source hierarchical prediction consolidation method to effectively exploits the complicated hierarchical label structures to resolve the noisy and conflicting information that inherently originates from multiple imperfect sources.
no code implementations • 16 Oct 2013 • Sihong Xie, Xiangnan Kong, Jing Gao, Wei Fan, Philip S. Yu
Nonetheless, data nowadays are usually multilabeled, such that more than one label have to be predicted at the same time.