Advanced Dropout: A Model-Free Methodology for Bayesian Dropout Optimization

NRGCNMDA: Microbe-Drug Association Prediction Based on Residual Graph Convolutional Networks and Conditional Random Fields

The process of discovering new drugs related to microbes through traditional biological methods is lengthy and costly. In response to these issues, a new computational model (NRGCNMDA) is proposed to predict microbe-drug associations. First, Node2vec is used to extract potential associations between microorganisms and drugs, and a heterogeneous network of microbes and drugs is constructed. Then, a Graph Convolutional Network incorporating a fusion residual network mechanism (REGCN) is utilized to learn meaningful high-order similarity features. In addition, conditional random fields (CRF) are applied to ensure that microbes and drugs have similar feature embeddings. Finally, unobserved microbe-drug associations are scored based on combined embeddings. The experimental findings demonstrate that the NRGCNMDA approach outperforms several existing deep learning methods, and its AUC and AUPR values are 95.16% and 93.02%, respectively. The case study demonstrates that NRGCNMDA accurately predicts drugs associated with Enterococcus faecalis and Listeria monocytogenes, as well as microbes associated with ibuprofen and tetracycline.

Deep Class-Incremental Learning From Decentralized Data

In this article, we focus on a new and challenging decentralized machine learning paradigm in which there are continuous inflows of data to be addressed and the data are stored in multiple repositories. We initiate the study of data-decentralized class-incremental learning (DCIL) by making the following contributions. First, we formulate the DCIL problem and develop the experimental protocol. Second, we introduce a paradigm to create a basic decentralized counterpart of typical (centralized) CIL approaches, and as a result, establish a benchmark for the DCIL study. Third, we further propose a decentralized composite knowledge incremental distillation (DCID) framework to transfer knowledge from historical models and multiple local sites to the general model continually. DCID consists of three main components, namely, local CIL, collaborated knowledge distillation (KD) among local models, and aggregated KD from local models to the general one. We comprehensively investigate our DCID framework by using a different implementation of the three components. Extensive experimental results demonstrate the effectiveness of our DCID framework. The source code of the baseline methods and the proposed DCIL is available at https://github.com/Vision-Intelligence-and-Robots-Group/DCIL.

MCDAL: Maximum Classifier Discrepancy for Active Learning

Recent state-of-the-art active learning methods have mostly leveraged generative adversarial networks (GANs) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyperparameters. In contrast to these methods, in this article, we propose a novel active learning framework that we call Maximum Classifier Discrepancy for Active Learning (MCDAL) that takes the prediction discrepancies between multiple classifiers. In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them. Intuitively, the discrepancies in the auxiliary classification layers' predictions indicate the uncertainty in the prediction. In this regard, we propose a novel method to leverage the classifier discrepancies for the acquisition function for active learning. We also provide an interpretation of our idea in relation to existing GAN-based active learning methods and domain adaptation frameworks. Moreover, we empirically demonstrate the utility of our approach where the performance of our approach exceeds the state-of-the-art methods on several image classification and semantic segmentation datasets in active learning setups.

Deep learning approach for early prediction of COVID-19 mortality using chest X-ray and electronic health records

BACKGROUND

An artificial-intelligence (AI) model for predicting the prognosis or mortality of coronavirus disease 2019 (COVID-19) patients will allow efficient allocation of limited medical resources. We developed an early mortality prediction ensemble model for COVID-19 using AI models with initial chest X-ray and electronic health record (EHR) data.

RESULTS

We used convolutional neural network (CNN) models (Inception-ResNet-V2 and EfficientNet) for chest X-ray analysis and multilayer perceptron (MLP), Extreme Gradient Boosting (XGBoost), and random forest (RF) models for EHR data analysis. The Gradient-weighted Class Activation Mapping and Shapley Additive Explanations (SHAP) methods were used to determine the effects of these features on COVID-19. We developed an ensemble model (Area under the receiver operating characteristic curve of 0.8698) using a soft voting method with weight differences for CNN, XGBoost, MLP, and RF models. To resolve the data imbalance, we conducted F1-score optimization by adjusting the cutoff values to optimize the model performance (F1 score of 0.77).

CONCLUSIONS

Our study is meaningful in that we developed an early mortality prediction model using only the initial chest X-ray and EHR data of COVID-19 patients. Early prediction of the clinical courses of patients is helpful for not only treatment but also bed management. Our results confirmed the performance improvement of the ensemble model achieved by combining AI models. Through the SHAP method, laboratory tests that indicate the factors affecting COVID-19 mortality were discovered, highlighting the importance of these tests in managing COVID-19 patients.

Convergence of deep convolutional neural networks

Convergence of deep neural networks as the depth of the networks tends to infinity is fundamental in building the mathematical foundation for deep learning. In a previous study, we investigated this question for deep networks with the Rectified Linear Unit (ReLU) activation function and with a fixed width. This does not cover the important convolutional neural networks where the widths are increased from layer to layer. For this reason, we first study convergence of general ReLU networks with increased widths and then apply the results obtained to deep convolutional neural networks. It turns out the convergence reduces to convergence of infinite products of matrices with increased sizes, which has not been considered in the literature. We establish sufficient conditions for convergence of such infinite products of matrices. Based on the conditions, we present sufficient conditions for pointwise convergence of general deep ReLU networks with increasing widths, and as well as pointwise convergence of deep ReLU convolutional neural networks.

Development of Machine-Learning Model to Predict COVID-19 Mortality: Application of Ensemble Model and Regarding Feature Impacts

This study was designed to develop machine-learning models to predict COVID-19 mortality and identify its key features based on clinical characteristics and laboratory tests. For this, deep-learning (DL) and machine-learning (ML) models were developed using receiver operating characteristic (ROC) area under the curve (AUC) and F1 score optimization of 87 parameters. Of the two, the DL model exhibited better performance (AUC 0.8721, accuracy 0.84, and F1 score 0.76). However, we also blended DL with ML, and the ensemble model performed the best (AUC 0.8811, accuracy 0.85, and F1 score 0.77). The DL model is generally unable to extract feature importance; however, we succeeded by using the Shapley Additive exPlanations method for each model. This study demonstrated both the applicability of DL and ML models for classifying COVID-19 mortality using hospital-structured data and that the ensemble model had the best predictive ability.

Object-Agnostic Transformers for Video Referring Segmentation

Video referring segmentation focuses on segmenting out the object in a video based on the corresponding textual description. Previous works have primarily tackled this task by devising two crucial parts, an intra-modal module for context modeling and an inter-modal module for heterogeneous alignment. However, there are two essential drawbacks of this approach: (1) it lacks joint learning of context modeling and heterogeneous alignment, leading to insufficient interactions among input elements; (2) both modules require task-specific expert knowledge to design, which severely limits the flexibility and generality of prior methods. To address these problems, we here propose a novel Object-Agnostic Transformer-based Network, called OATNet, that simultaneously conducts intra-modal and inter-modal learning for video referring segmentation, without the aid of object detection or category-specific pixel labeling. More specifically, we first directly feed the sequence of textual tokens and visual tokens (pixels rather than detected object bounding boxes) into a multi-modal encoder, where context and alignment are simultaneously and effectively explored. We then design a novel cascade segmentation network to decouple our task into coarse-grained segmentation and fine-grained refinement. Moreover, considering the difficulty of samples, a more balanced metric is provided to better diagnose the performance of the proposed method. Extensive experiments on two popular datasets, A2D Sentences and J-HMDB Sentences, demonstrate that our proposed approach noticeably outperforms state-of-the-art methods.