Search

Your search keyword '"Tao, Yaling"' showing total 32 results
Start Over Author "Tao, Yaling"
32 results on '"Tao, Yaling"'

2. Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation

Author

Tao, Yaling, Takagi, Kentaro, and Nakata, Kouta

Subjects
Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition
Abstract

Clustering is one of the most fundamental tasks in machine learning. Recently, deep clustering has become a major trend in clustering techniques. Representation learning often plays an important role in the effectiveness of deep clustering, and thus can be a principal cause of performance degradation. In this paper, we propose a clustering-friendly representation learning method using instance discrimination and feature decorrelation. Our deep-learning-based representation learning method is motivated by the properties of classical spectral clustering. Instance discrimination learns similarities among data and feature decorrelation removes redundant correlation among features. We utilize an instance discrimination method in which learning individual instance classes leads to learning similarity among instances. Through detailed experiments and examination, we show that the approach can be adapted to learning a latent space for clustering. We design novel softmax-formulated decorrelation constraints for learning. In evaluations of image clustering using CIFAR-10 and ImageNet-10, our method achieves accuracy of 81.5% and 95.4%, respectively. We also show that the softmax-formulated constraints are compatible with various neural networks., Comment: 15 pages, ICLR2021

Published
2021

3. Investigating Critical Risk Factors in Liver Cancer Prediction

Author

Li, Jinpeng, Tao, Yaling, and Cai, Ting

Subjects
Computer Science - Machine Learning
Abstract

We exploit liver cancer prediction model using machine learning algorithms based on epidemiological data of over 55 thousand peoples from 2014 to the present. The best performance is an AUC of 0.71. We analyzed model parameters to investigate critical risk factors that contribute the most to prediction., Comment: 8 pages, 4 figures, conference paper

Published
2021

4. A novel nested gene Aff3ir participates in vascular remodeling by enhancing endothelial cell differentiation in mice

Author

Zhao, Yue, primary, Ehteramyan, Mazdak, additional, Li, Yi, additional, Bai, Xuefeng, additional, Huang, Lei, additional, Gao, Yingtang, additional, Angbohang, Angshumonik, additional, Yang, Xiaoping, additional, Lynham, Steven, additional, Margariti, Andriana, additional, Shah, Ajay M., additional, Tao, Yaling, additional, Cai, Ting, additional, Li, Tong, additional, Zhang, Min, additional, and Zeng, Lingfang, additional

Published
2024
Full Text
View/download PDF

5. RDEC: Integrating Regularization into Deep Embedded Clustering for Imbalanced Datasets

Author

Tao, Yaling, Takagi, Kentaro, and Nakata, Kouta

Subjects
Computer Science - Machine Learning
Abstract

Clustering is a fundamental machine learning task and can be used in many applications. With the development of deep neural networks (DNNs), combining techniques from DNNs with clustering has become a new research direction and achieved some success. However, few studies have focused on the imbalanced-data problem which commonly occurs in real-world applications. In this paper, we propose a clustering method, regularized deep embedding clustering (RDEC), that integrates virtual adversarial training (VAT), a network regularization technique, with a clustering method called deep embedding clustering (DEC). DEC optimizes cluster assignments by pushing data more densely around centroids in latent space, but it is sometimes sensitive to the initial location of centroids, especially in the case of imbalanced data, where the minor class has less chance to be assigned a good centroid. RDEC introduces regularization using VAT to ensure the model's robustness to local perturbations of data. VAT pushes data that are similar in the original space closer together in the latent space, bunching together data from minor classes and thereby facilitating cluster identification by RDEC. Combining the advantages of DEC and VAT, RDEC attains state-of-the-art performance on both balanced and imbalanced benchmark/real-world datasets. For example, accuracies are as high as 98.41% on MNIST dataset and 85.45% on a highly imbalanced dataset derived from the MNIST, which is nearly 8% higher than the current best result., Comment: 16 pages, 6 figures, accepted by ACML2018

Published
2018

10. A novel nested geneAff3irparticipates in vascular remodelling by enhancing endothelial cell differentiation in mice

Author

Zhao, Yue, primary, Ehteramyan, Mazdak, additional, Li, Yi, additional, Bai, Xuefeng, additional, Huang, Lei, additional, Gao, Yingtang, additional, Angbohang, Angshumonik, additional, Yang, Xiaoping, additional, Lynham, Steven, additional, Margariti, Andriana, additional, Shah, Ajay M, additional, Tao, Yaling, additional, Cai, Ting, additional, Li, Tong, additional, Zhang, Min, additional, and Zeng, Lingfang, additional

Published
2023
Full Text
View/download PDF

11. On split regular BiHom-Poisson color algebras

Author

Tao Yaling and Cao Yan

Subjects
bihom-lie color algebra, bihom-poisson algebra, root space, root system, 17b75, 17a60, 17b22, 17b65, Mathematics, QA1-939
Abstract

The purpose of this paper is to introduce the class of split regular BiHom-Poisson color algebras, which can be considered as the natural extension of split regular BiHom-Poisson algebras and of split regular Poisson color algebras. Using the property of connections of roots for this kind of algebras, we prove that such a split regular BiHom-Poisson color algebra LL is of the form L=⊕[α]∈Λ/∼I[α]L={\oplus }_{\left[\alpha ]\in \Lambda \text{/} \sim }{I}_{\left[\alpha ]} with I[α]{I}_{\left[\alpha ]} a well described (graded) ideal of LL, satisfying [I[α],I[β]]+I[α]I[β]=0\left[{I}_{\left[\alpha ]},{I}_{\left[\beta ]}]+{I}_{\left[\alpha ]}{I}_{\left[\beta ]}=0 if [α]≠[β]\left[\alpha ]\ne \left[\beta ]. In particular, a necessary and sufficient condition for the simplicity of this algebra is determined, and it is shown that LL is the direct sum of the family of its simple (graded) ideals.

Published
2021
Full Text
View/download PDF

15. Early Cenozoic Drainage Evolution and Surface Uplift of the Eastern Tibetan Plateau: Insights From the Ninglang Basin

Author

Zhao, Xudong, primary, Zhang, Huiping, additional, Lease, Richard O., additional, Wang, Ying, additional, Pang, Jianzhang, additional, Li, Yifei, additional, Wang, Ping, additional, Zhang, Jiawei, additional, Xie, Hao, additional, Wang, Yizhou, additional, Tao, Yaling, additional, Ma, Zifa, additional, Xiong, Jianguo, additional, and Zhang, Peizhen, additional

Published
2023
Full Text
View/download PDF

25. The Clinical and Pathological Analysis of Ovarian Borderline Serous Papillary Epithelioma: A Report of Six Cases

Author

Tao Yaling, Manzhen Zuo, Huamei Song, Dan-Dan Quan, Wang Yan, Du Hongying, and Aihua Chen

Subjects
endocrine system, medicine.medical_specialty, 030219 obstetrics & reproductive medicine, endocrine system diseases, Epithelioma, Adenoma, business.industry, Retrospective cohort study, General Medicine, medicine.disease, female genital diseases and pregnancy complications, 03 medical and health sciences, Ovarian tumor, Serous fluid, 0302 clinical medicine, 030220 oncology & carcinogenesis, Ophthalmology, Carcinoma, medicine, Radiology, business, Pathological, Three gorges
Abstract

Introduction: Ovarian borderline serous papillary epithelioma is a rare epithelial ovarian tumor between adenoma and carcinoma. This study was carried out to compare six cases of ovarian borderline serous papillary epithelioma. Case Presentation: This retrospective study was conducted on 6 patients with ovarian borderline serous papillary epithelioma regarding clinical symptoms, auxiliary examination, treatment process, and prognosis. These six patients were diagnosed with the disease from January 2010 to June 2013 in the People’s hospital of three Gorges university, Yichang, Hubei, China. Two patients were diagnosed with ovarian surface serous papillary epithelioma. One patient was diagnosed with ovarian surface serous papillary epithelioma transferred to bilateral fallopian tubes. One patient was diagnosed with ovarian borderline serous papillary epithelioma while parts of tissues had become cancerous. One patient was diagnosed with ovarian borderline serous papillary epithelioma with pelvic lymph node metastasis, which had transferred to bilateral fallopian tubes, omentum majus, and epityphlon. One patient was diagnosed with ovarian surface serous papillary epithelioma with epithelial hyperplasia. All the six patients received surgical resection. Conclusions: We recommend ovarian borderline serous papillary epithelioma evaluation for patients as preoperative observations, intraoperative careful exploration, and pathological diagnosis in order to find and timely treat ovarian borderline serous papillary epithelioma patients.

Published
2016

30. Association between the COMT Val158Met polymorphism and risk of cancer: evidence from 99 case–control studies

Author

Quan Zhou, Aihua Chen, Huamei Song, Manzhen Zuo, Wang Yan, Tao Yaling, Jing Tao, and Wei Li

Subjects
Oncology, medicine.medical_specialty, Subgroup analysis, medicine.disease_cause, Bioinformatics, OncoTargets and Therapy, susceptibility, polymorphism, Internal medicine, Genetic model, medicine, cancer, Pharmacology (medical), Original Research, Bladder cancer, business.industry, Case-control study, Heterozygote advantage, Odds ratio, Esophageal cancer, medicine.disease, COMT, meta-analysis, Carcinogenesis, business
Abstract

Quan Zhou, Yan Wang, Aihua Chen, Yaling Tao, Huamei Song, Wei Li, Jing Tao, Manzhen ZuoDepartment of Gynecology and Obstetrics, The People’s Hospital of Three Gorges University, The First People’s Hospital of Yichang, Yichang, People’s Republic of ChinaAbstract: Catechol-O-methyltransferase (COMT) plays a central role in DNA repair and estrogen-induced carcinogenesis. Many recent epidemiologic studies have investigated the association between the COMT Val158Met polymorphism and cancer risk, but the results are inconclusive. In this study, we performed a meta-analysis to investigate the association between cancer susceptibility and COMT Val158Met in different genetic models. Overall, no significant associations were found between COMT Val158Met polymorphism and cancer risk (homozygote model: odds ratio [OR] =1.05, 95% confidence interval [CI] = [0.98, 1.13]; heterozygote model: OR =1.01, 95% CI = [0.98, 1.04]; dominant model: OR =1.02, 95% CI [0.97, 1.06], and recessive model: OR =1.03, 95% CI [0.97, 1.09]). In the subgroup ­analysis of cancer type, COMT Val158Met was significantly associated with increased risks of ­bladder cancer in recessive model, and esophageal cancer in homozygote model, heterozygote model, and dominant model. Subgroup analyses based on ethnicities, COMT Val158Met was significantly associated with increased risk of cancer in homozygote and recessive model among Asians. In addition, homozygote, recessive, and dominant models were significantly associated with increased cancer risk in the subgroup of allele-specific polymerase chain reaction genotyping. Significant associations were not observed when data were stratified by the source of the controls. In summary, this meta-analysis suggested that COMT Val158Met polymorphism might not be a risk factor for overall cancer risk, but it might be involved in cancer development at least in some ethnic groups (Asian) or some specific cancer types (bladder and esophageal cell cancer). Further evaluations of more preclinical and epidemiological ­studies are required.Keywords: COMT, polymorphism, cancer, meta-analysis, susceptibility

Published
2015

Catalog

Books, media, physical & digital resources
See catalog results