DeepGBM

Ke, Guolin; Xu, Zhenhui; Zhang, Jia; Bian, Jiang; Liu, Tie-Yan

doi:10.1145/3292500.3330858

Cited by 96 publications

(30 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the strategies to improve the performance of the deep neural network in the analysis of data of different experimental domains have been discussed in some past studies, like using a training approach [39], generalized maxout networks [40], and transfer learning [41], etc. Deep learning has better performance in the analysis of categorical feature datasets whereas tree-based learning is better in the dense numerical feature dataset [42]. Moreover, the performance of the deep learning approaches varies according to the nature and the dimensionality of the dataset [43].…”

Section: Discussionmentioning

confidence: 99%

A gradient boosting machine learning approach in modeling the impact of temperature and humidity on the transmission rate of COVID-19 in India

Shrivastav

Jha

2020

Appl Intell

View full text Add to dashboard Cite

Meteorological parameters were crucial and effective factors in past infectious diseases, like influenza and severe acute respiratory syndrome (SARS), etc. The present study targets to explore the association between the coronavirus disease 2019 (COVID-19) transmission rates and meteorological parameters. For this purpose, the meteorological parameters and COVID-19 infection data from 28th March 2020 to 22nd April 2020 of different states of India have been compiled and used in the analysis. The gradient boosting model (GBM) has been implemented to explore the effect of the minimum temperature, maximum temperature, minimum humidity, and maximum humidity on the infection count of COVID-19. The optimal performance of the GBM model has been achieved after tuning its parameters. The GBM results in the best accuracy of R 2 = 0.95 for prediction of active cases in Maharashtra, and R 2 = 0.98 for prediction of recovered cases of COVID-19 in Kerala and Rajasthan, India.

show abstract

Section: Discussionmentioning

confidence: 99%

A gradient boosting machine learning approach in modeling the impact of temperature and humidity on the transmission rate of COVID-19 in India

Shrivastav

Jha

2020

Appl Intell

View full text Add to dashboard Cite

show abstract

“…To tackle these challenges, we propose to combine deep learning and tree-based model for graft failure prediction. Our method is motivated by the success of DeepGBM [26] in recommendation tasks, where an embedding layer and a distillation network with distilled knowledge from a tree- based method are employed to handle the sparse and dense features, respectively. We will first elaborate on how we process the sparse and dense features, and then introduce the end-to-end training objective.…”

Section: Combining Deep Learning and Tree-based Model For Graft Failu...mentioning

confidence: 99%

“…( 2) and Eq. ( 3) in [26]. The output of FM and the neural network are summed to obtain the final sparse representations:…”

Section: Combining Deep Learning and Tree-based Model For Graft Failu...mentioning

confidence: 99%

“…This is not an easy task because the structures of the trees and neural networks are naturally different. Fortunately, Ke et al [26] proposes an effective tree distillation strategy by distilling the clustering patterns of the leaf nodes. First, since tree-based methods often do not use all the features but instead greedily choose the useful features, we only select the used features of a tree to train the neural network.…”

Section: Combining Deep Learning and Tree-based Model For Graft Failu...mentioning

confidence: 99%

“…Specifically, we focus on the prediction of liver 1 transplant graft failure which is one of the most important post-transplant outcomes. Motivated by the strong performance of DeepGBM [26] in recommendation tasks, we use an embedding layer to handle the sparse features and a distillation network with distilled knowledge from a tree-based model to handle the dense features. This design can not only combine the advantages of tree-based models and deep neural networks in handling the sparse and dense features, but also enable us to apply in-processing debiasing techniques to achieve fairness.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning

Ding,

Tang,

Zha

et al. 2023

Preprint

View full text Add to dashboard Cite

Liver transplant is an essential therapy performed for severe liver diseases. The fact of scarce liver resources makes the organ assigning crucial. Model for End-stage Liver Disease (MELD) score is a widely adopted criterion when making organ distribution decisions. However, it ignores post-transplant outcomes and organ/donor features. These limitations motivate the emergence of machine learning (ML) models. Unfortunately, ML models could be unfair and trigger bias against certain groups of people. To tackle this problem, this work proposes a fair machine learning framework targeting graft failure prediction in liver transplant. Specifically, knowledge distillation is employed to handle dense and sparse features by combining the advantages of tree models and neural networks. A two-step debiasing method is tailored for this framework to enhance fairness. Experiments are conducted to analyze unfairness issues in existing models and demonstrate the superiority of our method in both prediction and fairness performance.

show abstract

Laboratory methods: A concise review and update for COVID‐19 diagnosis

Nemati

Jafari

Ebrahimi

et al. 2023

Cell Biochemistry & Function

View full text Add to dashboard Cite

Since late December 2019, coronavirus disease 2019 (COVID‐19) outbreak caused by severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) has been rapidly spread across the globe. The early, safe, sensitive, and accurate diagnosis of viral infection is required to decrease and control contagious infection and improve public health surveillance. The diagnosis generally is made by detecting SARS‐CoV‐2‐related agents, including a range of nucleic acid detection‐based, immunoassay‐based, radiographic‐based, and biosensor‐based methods. This review presents the progress of various detection tools for diagnosing COVID‐19 and addresses the advantages and restrictions of each detection method. Given that diagnosis of a contagious various like SARS‐COV‐2 can improve patient survival rates and break the transmission chain, there is no surprise that significant efforts should be made to reduce the limitations of tests that lead to false‐negative results and to develop a substantial test for COVID‐19 diagnosis.

show abstract

DeepGBM

Cited by 96 publications

References 30 publications

A gradient boosting machine learning approach in modeling the impact of temperature and humidity on the transmission rate of COVID-19 in India

A gradient boosting machine learning approach in modeling the impact of temperature and humidity on the transmission rate of COVID-19 in India

Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning

Laboratory methods: A concise review and update for COVID‐19 diagnosis

Contact Info

Product

Resources

About