Xiaomin Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiaomin Zhang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Po-Ling Loh
University of Cambridge
3 shared publications - Xiaojin Zhu
University of Wisconsin-Madison
2 shared publications - Yingyu Liang
University of Wisconsin-Madison University of Wisconsin-Madison University of Wisconsin-Madison The University of Hong Kong University of Wisconsin-Madison
2 shared publications - Alan McMillan
Department of Radiology, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave, Madison, WI 53792
1 shared publication - Chong Han
School of Mechanical Engineering, Xi'an Jiaotong University, xi'an, shaanxi, 710054, China
1 shared publication - Christos T. Maravelias
Department of Chemical and Biological Engineering Princeton University Princeton New Jersey USA
1 shared publication
Latest Publications
- Open Access
- 13 December 2024
- Published by MDPI AG in Tomography
- Vol. 10 (12) , 2058-2072
BAE-ViT: An Efficient Multimodal Vision Transformer for Bone Age Estimation
This research introduces BAE-ViT, a specialized vision transformer model developed for bone age estimation (BAE). This model is designed to efficiently merge image and sex data, a capability not present in traditional convolutional neural networks (CNNs). BAE-ViT employs a novel data fusion method to facilitate detailed interactions between visual and non-visual data by tokenizing non-visual information and concatenating all tokens (visual or non-visual) as the input to the model. The model underwent training on a large-scale dataset from the 2017 RSNA Pediatric Bone Age Machine Learning Challenge, where it exhibited commendable performance, particularly excelling in handling image distortions compared to existing models. The effectiveness of BAE-ViT was further affirmed through statistical analysis, demonstrating a strong correlation with the actual ground-truth labels. This study contributes to the field by showcasing the potential of vision transformers as a viable option for integrating multimodal data in medical imaging applications, specifically emphasizing their capacity to incorporate non-visual elements like sex information into the framework. This tokenization method not only demonstrates superior performance in this specific task but also offers a versatile framework for integrating multimodal data in medical imaging applications.
- 13 December 2024
- Published by MDPI AG in Tomography
- Vol. 10 (12) , 2058-2072
Open AccessBAE-ViT: An Efficient Multimodal Vision Transformer for Bone Age Estimation
This research introduces BAE-ViT, a specialized vision transformer model developed for bone age estimation (BAE). This model is designed to efficiently merge image and sex data, a capability not present in traditional convolutional neural networks (CNNs). BAE-ViT employs a novel data fusion method to facilitate detailed interactions between visual and non-visual data by tokenizing non-visual information and concatenating all tokens (visual or non-visual) as the input to the model. The model underwent training on a large-scale dataset from the 2017 RSNA Pediatric Bone Age Machine Learning Challenge, where it exhibited commendable performance, particularly excelling in handling image distortions compared to existing models. The effectiveness of BAE-ViT was further affirmed through statistical analysis, demonstrating a strong correlation with the actual ground-truth labels. This study contributes to the field by showcasing the potential of vision transformers as a viable option for integrating multimodal data in medical imaging applications, specifically emphasizing their capacity to incorporate non-visual elements like sex information into the framework. This tokenization method not only demonstrates superior performance in this specific task but also offers a versatile framework for integrating multimodal data in medical imaging applications.
- 26 February 2023
- Published by Springer Nature in Optimization Letters
- Vol. 18 (1) , 215-234
Tightening discretization-based MILP models for the pooling problem using upper bounds on bilinear terms
- 26 February 2023
- Published by Springer Nature in Optimization Letters
- Vol. 18 (1) , 215-234
Tightening discretization-based MILP models for the pooling problem using upper bounds on bilinear terms
- Open Access
On the identifiability of mixtures of ranking models
Mixtures of ranking models are standard tools for ranking problems. However, even the fundamental question of parameter identifiability is not fully understood: the identifiability of a mixture model with two Bradley-Terry-Luce (BTL) components has remained open. In this work, we show that popular mixtures of ranking models with two components (BTL, multinomial logistic models with slates of size 3, or Plackett-Luce) are generically identifiable, i.e., the ground-truth parameters can be identified except when they are from a pathological subset of measure zero. We provide a framework for verifying the number of solutions in a general family of polynomial systems using algebraic geometry, and apply it to these mixtures of ranking models to establish generic identifiability. The framework can be applied more broadly to other learning models and may be of independent interest.
Open AccessOn the identifiability of mixtures of ranking models
Mixtures of ranking models are standard tools for ranking problems. However, even the fundamental question of parameter identifiability is not fully understood: the identifiability of a mixture model with two Bradley-Terry-Luce (BTL) components has remained open. In this work, we show that popular mixtures of ranking models with two components (BTL, multinomial logistic models with slates of size 3, or Plackett-Luce) are generically identifiable, i.e., the ground-truth parameters can be identified except when they are from a pathological subset of measure zero. We provide a framework for verifying the number of solutions in a general family of polynomial systems using algebraic geometry, and apply it to these mixtures of ranking models to establish generic identifiability. The framework can be applied more broadly to other learning models and may be of independent interest.
- 16 August 2021
- Published by Springer Nature in Machine Learning
- Vol. 110 (10) , 2763-2834
Provable training set debugging for linear regression
- 16 August 2021
- Published by Springer Nature in Machine Learning
- Vol. 110 (10) , 2763-2834
Provable training set debugging for linear regression
- Open Access
Provable Training Set Debugging for Linear Regression
We investigate problems in penalized $M$-estimation, inspired by applications in machine learning debugging. Data are collected from two pools, one containing data with possibly contaminated labels, and the other which is known to contain only cleanly labeled points. We first formulate a general statistical algorithm for identifying buggy points and provide rigorous theoretical guarantees under the assumption that the data follow a linear model. We then present two case studies to illustrate the results of our general theory and the dependence of our estimator on clean versus buggy points. We further propose an algorithm for tuning parameter selection of our Lasso-based algorithm and provide corresponding theoretical guarantees. Finally, we consider a two-person "game" played between a bug generator and a debugger, where the debugger can augment the contaminated data set with cleanly labeled versions of points in the original data pool. We establish a theoretical result showing a sufficient condition under which the bug generator can always fool the debugger. Nonetheless, we provide empirical results showing that such a situation may not occur in practice, making it possible for natural augmentation strategies combined with our Lasso debugging algorithm to succeed.
Open AccessProvable Training Set Debugging for Linear Regression
We investigate problems in penalized $M$-estimation, inspired by applications in machine learning debugging. Data are collected from two pools, one containing data with possibly contaminated labels, and the other which is known to contain only cleanly labeled points. We first formulate a general statistical algorithm for identifying buggy points and provide rigorous theoretical guarantees under the assumption that the data follow a linear model. We then present two case studies to illustrate the results of our general theory and the dependence of our estimator on clean versus buggy points. We further propose an algorithm for tuning parameter selection of our Lasso-based algorithm and provide corresponding theoretical guarantees. Finally, we consider a two-person "game" played between a bug generator and a debugger, where the debugger can augment the contaminated data set with cleanly labeled versions of points in the original data pool. We establish a theoretical result showing a sufficient condition under which the bug generator can always fool the debugger. Nonetheless, we provide empirical results showing that such a situation may not occur in practice, making it possible for natural augmentation strategies combined with our Lasso debugging algorithm to succeed.
- Open Access
PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding
We look into the task of \emph{generalizing} word embeddings: given a set of pre-trained word vectors over a finite vocabulary, the goal is to predict embedding vectors for out-of-vocabulary words, \emph{without} extra contextual information. We rely solely on the spellings of words and propose a model, along with an efficient algorithm, that simultaneously models subword segmentation and computes subword-based compositional word embedding. We call the model probabilistic bag-of-subwords (PBoS), as it applies bag-of-subwords for all possible segmentations based on their likelihood. Inspections and affix prediction experiment show that PBoS is able to produce meaningful subword segmentations and subword rankings without any source of explicit morphological knowledge. Word similarity and POS tagging experiments show clear advantages of PBoS over previous subword-level models in the quality of generated word embeddings across languages.
Open AccessPBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding
We look into the task of \emph{generalizing} word embeddings: given a set of pre-trained word vectors over a finite vocabulary, the goal is to predict embedding vectors for out-of-vocabulary words, \emph{without} extra contextual information. We rely solely on the spellings of words and propose a model, along with an efficient algorithm, that simultaneously models subword segmentation and computes subword-based compositional word embedding. We call the model probabilistic bag-of-subwords (PBoS), as it applies bag-of-subwords for all possible segmentations based on their likelihood. Inspections and affix prediction experiment show that PBoS is able to produce meaningful subword segmentations and subword rankings without any source of explicit morphological knowledge. Word similarity and POS tagging experiments show clear advantages of PBoS over previous subword-level models in the quality of generated word embeddings across languages.
- 30 November 2019
- Published by Springer Nature
- p. 554-559
Research on Multi-source Data Fusion Technology Under Power Cloud Platform
- 30 November 2019
- Published by Springer Nature
- p. 554-559
Research on Multi-source Data Fusion Technology Under Power Cloud Platform
- 1 September 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 25, 1-4
DOA estimation of multi-component LFM in complex environment using ESPRIT based on FRFT
Linear frequency modulation (LFM) signals are widely used in information systems. However, using traditional array signal process couldn't commendably estimate DOA of LFM signal, because which is a non-stationary signal. In this paper, the proposed method firstly applied the fractional Fourier Transform (FRFT) to construct the LFM signals array model, in which time-variant steering vector is changed into time-invariant one and wideband LFM signals are converted to narrowband stationary ones. Afterwards, a new improved ESPRIT method was proposed of DOA estimation which sufficiently made use of correlation and cross correlation information of covariance matrix to construct the new matrix. Then, the DOAs of coherent and non-coherent LFM signals are estimated by the signal parameters via a new improved rotation invariance technique (ESPRIT). Simulation results can not only demonstrate the effectiveness of this method, but also achieve high estimation accuracy.
- 1 September 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 25, 1-4
DOA estimation of multi-component LFM in complex environment using ESPRIT based on FRFT
Linear frequency modulation (LFM) signals are widely used in information systems. However, using traditional array signal process couldn't commendably estimate DOA of LFM signal, because which is a non-stationary signal. In this paper, the proposed method firstly applied the fractional Fourier Transform (FRFT) to construct the LFM signals array model, in which time-variant steering vector is changed into time-invariant one and wideband LFM signals are converted to narrowband stationary ones. Afterwards, a new improved ESPRIT method was proposed of DOA estimation which sufficiently made use of correlation and cross correlation information of covariance matrix to construct the new matrix. Then, the DOAs of coherent and non-coherent LFM signals are estimated by the signal parameters via a new improved rotation invariance technique (ESPRIT). Simulation results can not only demonstrate the effectiveness of this method, but also achieve high estimation accuracy.