Abstract Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for many applications dismissing the use of DL. Having sufficient data is the first step toward any successful and trustworthy DL application. This paper presents a holistic survey on state-of-the-art techniques to deal with training DL models to overcome three challenges including small, imbalanced datasets, and lack of generalization. This survey starts by listing the learning techniques. Next, the types of DL architectures are introduced. After that, state-of-the-art solutions to address the issue of lack of training data are listed, such as Transfer Learning (TL), Self-Supervised Learning (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), and Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these solutions were followed by some related tips about data acquisition needed prior to training purposes, as well as recommendations for ensuring the trustworthiness of the training dataset. The survey ends with a list of applications that suffer from data scarcity, several alternatives are proposed in order to generate more data in each application including Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, and Cybersecurity. To the best of the authors’ knowledge, this is the first review that offers a comprehensive overview on strategies to tackle data scarcity in DL. 

/pdf/a-survey-on-deep-learning-tools-dealing-with-data-scarcity-3amzf9cp.pdf

A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

Abstract The emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) had become a global concern because of its unexpectedly high pathogenicity and transmissibility. SARS-CoV-2 variants that reduce the immune protection elicited from previous vaccination or natural infection raise challenges in controlling the spread of the pandemic. The development of universal vaccines against these variants seems to be a practical solution to alleviate the physical and economic effects caused by this disease, but it is hard to achieve. In this review, we describe the high mutation rate of RNA viruses and dynamic molecular structures of SARS-CoV-2 variants in several major neutralizing epitopes, trying to answer the question of why universal vaccines are difficult to design. Understanding the biological basis of immune evasion is crucial for combating these obstacles. We then summarize several advancements worthy of further study, including heterologous prime-boost regimens, construction of chimeric immunogens, design of protein nanoparticle antigens, and utilization of conserved neutralizing epitopes. The fact that some immunogens can induce cross-reactive immune responses against heterologous coronaviruses provides hints for universal vaccine development. We hope this review can provide inspiration to current universal vaccine studies. 

/pdf/challenges-and-developments-in-universal-vaccine-design-3d3ssqht.pdf

Challenges and developments in universal vaccine design against SARS-CoV-2 variants

Emerging SARS-CoV-2 variants of concern (VOCs) harboring multiple mutations in the spike protein raise concerns on effectiveness of current vaccines that rely on the ancestral spike protein. Here, we design a quadrivalent mosaic nanoparticle vaccine displaying spike proteins from the SARS-CoV-2 prototype and 3 different VOCs. The mosaic nanoparticle elicits equivalent or superior neutralizing antibodies against variant strains in mice and non-human primates with only small reduction in neutralization titers against the ancestral strain. Notably, it provides protection against infection with prototype and B.1.351 strains in mice. These results provide a proof of principle for the development of multivalent vaccines against pandemic and potential pre-emergent SARS-CoV-2 variants. 

/pdf/quadrivalent-mosaic-hexapro-bearing-nanoparticle-vaccine-2ypfsq26.pdf

Quadrivalent mosaic HexaPro-bearing nanoparticle vaccine protects against infection of SARS-CoV-2 variants

Vaccines based on historical virus isolates provide limited protection from continuously evolving RNA viruses, such as influenza viruses or coronaviruses, which occasionally spill over between animals and humans. Despite repeated booster immunizations, population-wide declines in the neutralization of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants have occurred. This has been compared to seasonal influenza vaccinations in humans, where the breadth of immune responses induced by repeat exposures to antigenically distinct influenza viruses is confounded by pre-existing immunity-a mechanism known as imprinting. Since its emergence, SARS-CoV-2 has evolved in a population with partial immunity, acquired by infection, vaccination or both. Here we critically examine the evidence for and against immune imprinting in host humoral responses to SARS-CoV-2 and its implications for coronavirus disease 2019 (COVID-19) booster vaccine programmes. 

Immune imprinting and next-generation coronavirus vaccines

Convolutional neural network pruning based on multi-objective feature map selection for image classification

A bivalent nanoparticle vaccine exhibits potent cross-protection against the variants of SARS-CoV-2

Pruning is a very effective solution to alleviate the difficulty of deploying neural networks on resource-constrained devices. However, most of the existing methods focus on the inherent parameters of the network itself, but rarely consider the contribution of the output feature map. In this paper, we propose the FPC, a novel filter pruning method based on the contribution of the output feature map, which considers the diverse information carried by different output feature maps. According to the above characteristic, FPC can evaluate the contribution of output feature maps and then effectively delete low contribution part without reducing the performance of the model. In this paper, we firstly use Singular Value Decomposition (SVD) to decompose the output feature map. Then we analyze the contribution of the output feature map to the model performance. Finally, we delete the filters with lower contribution output feature maps. Extensive experimental results show that our proposed FPC can produce excellent compression results. For example, with VGG-16, we can reduce the FLOPs by 65.62% and increase the accuracy by 0.25% on CIFAR-10. With ResNet-110, we can reduce FLOPs by 50.66% and increase the accuracy by 0.09% on CIFAR-100. 

FPC: Filter pruning via the contribution of output feature map for deep convolutional neural networks acceleration

With the increase of complexity of modern software, social collaborative coding and reuse of open source software packages become more and more popular, which thus greatly enhances the development efficiency and software quality. However, the explosive growth of open source software packages exposes developers to the challenge of information overload. While this can be addressed by conventional recommender systems, they usually do not consider particular constraints of social coding such as social influence among developers and dependency relations among software packages. In this paper, we aim to model the dynamic interests of developers with both social influence and dependency constraints, and propose the Session-based Social and Dependency-aware software Recommendation (SSDRec) model. This model integrates recurrent neural network (RNN) and graph attention network (GAT) into a unified framework. A RNN is employed to model the short-term dynamic interests of developers in each session and two GATs are utilized to capture social influence from friends and dependency constraints from dependent software packages, respectively. Extensive experiments are conducted on real-world datasets and the results demonstrate that our model significantly outperforms the competitive baselines.

Session-based Social and Dependency-aware Software Recommendation

/pdf/session-based-social-and-dependency-aware-software-3dkov70q.pdf

Session-based social and dependency-aware software recommendation

The efficacy of mesenchymal stem cell (MSC) therapy in acetaminophen-induced liver injury has been investigated in animal experiments, but individual studies with a small sample size cannot be used to draw a clear conclusion. Therefore, we conducted a systematic review and meta-analysis of preclinical studies to explore the potential of using MSCs in acetaminophen- induced liver injury.Eight databases were searched for studies reporting the effects of MSCs on acetaminophen hepatoxicity. The Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines were used. SYRCLE's risk of bias tool for animal studies was applied to assess the methodological quality. A meta-analysis was performed by using RevMan 5.4 and STATA/ SE 16.0 software.Eleven studies involving 159 animals were included according to PRISMA statement guidelines. Significant associations were found for MSCs with the levels of alanine transaminase (ALT) (standardized mean difference (SMD) - 2.58, p < 0.0001), aspartate aminotransferase (AST) (SMD - 1.75, p = 0.001), glutathione (GSH) (SMD 3.7, p < 0.0001), superoxide dismutase (SOD) (SMD 1.86, p = 0.022), interleukin 10 (IL-10) (SMD 5.14, p = 0.0002) and tumor necrosis factor-α (TNF-α) (SMD - 4.48, p = 0.011) compared with those in the control group. The subgroup analysis showed that the tissue source of MSCs significantly affected the therapeutic efficacy (p < 0.05).Our meta-analysis results demonstrate that MSCs could be a potential treatment for acetaminophen- related liver injury. The protocol for this meta-analysis was prospectively registered in PROSPERO (Number: CRD42020212677). 

Mesenchymal Stem Cell Therapy for Acetaminophen-related Liver Injury: A Systematic Review and Meta-analysis of Experimental Studies In Vivo

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Joe Wang

Author Tools

Chat about Author