Single Label Research Articles

Neutrophil extracellular traps are an important component of chronic myocardial inflammation in patients with heart failure

Abstract Background and aim We have previously shown that heart failure (HF) is characterized by chronic inflammation. However, the role of neutrophils (N) and extracellular neutrophil traps (NETs) in the myocardium of patients with HF is largely unknown. The present study investigated the number of neutrophils (N) and their proportion that develop NETs in HF. Methods We used quantitative confocal microscopy and NETs markers in the left ventricular biopsies obtained from 5 controls and from patients with HF due to dilated (DCM, n=7), ischemic (ICM, n=7) and inflammatory (infCMP, n=7) cardiomyopathy. We used immunolabeling for CD45 (N) and for NETs (citrullinated histone 3 (CitH3), peptidylarginine deiminase-4 (PAD-4), neutrophil elastase (NE) and myeoloperoxidase (MPO). Results Compared to the control, the number of N was 4.3-5.7 times higher in HF. Using single labeling for NETs marker revealed that 41.1±4.6% of N in DCM, 42.9±4.1% in ICM and 47.6±2.9% in infCMP developed NETs. The use of dual labeling (MPO with CitH3, MPO with PAD-4 and CitH3 with NE) resulted in 54.5±4.7% of N-developing NETs in DCM, 59.5±4.1% in ICM and 77.6%±4.2 in infCMP. The difference between N-undergoing NETs was statistically different in infCMP than in DCM.and ICM. The proportion of N-forming NETs in control tissue was less than 5% and was significantly different from that in HF patients regardless of etiology. Conclusions This is the first study to show the presence of NETs in human hearts in situ and demonstrates that NETs are an important component of chronic inflammation in HF due to cardiomyopathies.

Explaining results of path queries on graphs: Single-path results for context-free path queries

Many graph query languages use, at their core, path queries that yield node pairs (m,n) that are connected by a path of interest. For the end-user, such node pairs only give limited insight as to why this result is obtained, as the pair does not directly identify the underlying path of interest.In this paper, we propose the single-path semantics to address this limitation of path queries. Under single-path semantics, path queries evaluate to a single path connecting nodes m and n and that satisfies the conditions of the query. To put our proposal in practice, we provide an efficient algorithm for evaluating context-free path queries using the single-path semantics. Additionally, we perform a short evaluation of our techniques that shows that the single-path semantics is practically feasible, even when query results grow large.In addition, we explore the formal relationship between the single-path semantics we propose the problem of finding the shortest string in the intersection of a regular language (representing a graph) and a context-free language (representing a path query). As our formal results show, there is a distinction between the complexity of the single-path semantics for queries that use a single edge label and queries that use multiple edge labels: for queries that use a single edge label, the length of the shortest path is linearly upper bounded by the number of nodes in the graph; whereas for queries that use multiple edge labels, the length of the shortest path has a worst-case quadratic lower bound.

A multi-label legal charge prediction method based on summarization generation

Legal Charge Prediction (LCP) is a task of predicting charge labels for which a criminal should be charged based on the factual case descriptions. In recent years, the advancement of deep learning networks has led to the emergence of effective approaches for LCP through the Fine-tuning of pre-trained language models. While existing methods primarily treat it as multiple binary classifications, excelling in the single charge label given factual case descriptions, they still exhibit substantial room for improvement in multi-label LCP. This is because single-label classification methods do not effecitively deal with the relationship between multiple labels, mainly determining the likelihood of a factual description’s association to each individual charge label. Recognizing the need to enhance the relationship among multi-label charges in Fine-tuning-based discriminative charge prediction, this paper introduces a multi-label LCP method based on summarization generation. This method reconstructs the multi-label classification problem as a summarization generation task, capturing the relationship among multiple labels within the summarization content. Empirical findings from the Chinese legal domain’s CAIL2018 dataset demonstrate the method’s capacity to discern the relationship between multiple legal charge labels with Micro-F1 and Macro-F1 enhancements, compared to the fine-tuning-based approaches.

Neural correlates of systemic lidocaine administration in healthy adults measured by functional MRI: a single arm open label study.

Intravenous lidocaine is increasingly used as a nonopioid analgesic, but how it acts in the brain is incompletely understood. We conducted a functional MRI study of pain response, resting connectivity, and cognitive task performance in volunteers to elucidate the effects of lidocaine at the brain-systems level. We enrolled 27 adults (age 22-55 yr) in this single-arm, open-label study. Pain response task and resting-state functional MRI scans at 3 T were obtained at baseline and then with a constant effect-site concentration of lidocaine. Electric nerve stimulation, titrated in advance to 7/10 intensity, was used for the pain task (five times every 10 s). Group-level differences in pain task-evoked responses (primary outcome, focused on the insula) and in resting connectivity were compared between baseline and lidocaine conditions, using adjusted P<0.05 to account for multiple comparisons. Pain ratings and performance on a brief battery of computer-based tasks were also recorded. Lidocaine infusion was associated with decreased pain-evoked responses in the insula (left: Z=3.6, P<0.001, right: Z=3.6, P=0.004) and other brain areas including the cingulate gyrus, thalamus, and primary sensory cortex. Resting-state connectivity showed significant diffuse reductions in both region-to-region and global connectivity measures with lidocaine. Small decreases in pain intensity and unpleasantness and worse memory performance were also seen with lidocaine. Lidocaine was associated with broad reductions in functional MRI response to acute pain and modulated whole-brain functional connectivity, predominantly decreasing long-range connectivity. This was accompanied by small but significant decreases in pain perception and memory performance. NCT05501600.

A 3D approach to understanding heterogeneity in early developing autisms.

Phenotypic heterogeneity in early language, intellectual, motor, and adaptive functioning (LIMA) features are amongst the most striking features that distinguish different types of autistic individuals. Yet the current diagnostic criteria uses a single label of autism and implicitly emphasizes what individuals have in common as core social-communicative and restricted repetitive behavior difficulties. Subtype labels based on the non-core LIMA features may help to more meaningfully distinguish types of autisms with differing developmental paths and differential underlying biology. Unsupervised data-driven subtypes were identified using stability-based relative clustering validation on publicly available Mullen Scales of Early Learning (MSEL) and Vineland Adaptive Behavior Scales (VABS) data (n = 615; age = 24-68months) from the National Institute of Mental Health Data Archive (NDA). Differential developmental trajectories between subtypes were tested on longitudinal data from NDA and from an independent in-house dataset from UCSD. A subset of the UCSD dataset was also tested for subtype differences in functional and structural neuroimaging phenotypes and relationships with blood gene expression. The current subtyping model was also compared to early language outcome subtypes derived from past work. Two autism subtypes can be identified based on early phenotypic LIMA features. These data-driven subtypes are robust in the population and can be identified in independent data with 98% accuracy. The subtypes can be described as Type I versus Type II autisms differentiated by relatively high versus low scores on LIMA features. These two types of autisms are also distinguished by different developmental trajectories over the first decade of life. Finally, these two types of autisms reveal striking differences in functional and structural neuroimaging phenotypes and their relationships with gene expression and may highlight unique biological mechanisms. Sample sizes for the neuroimaging and gene expression dataset are relatively small and require further independent replication. The current work is also limited to subtyping based on MSEL and VABS phenotypic measures. This work emphasizes the potential importance of stratifying autism by a Type I versus Type II distinction focused on LIMA features and which may be of high prognostic and biological significance.

Amina: an Arabic multi-purpose integral news articles dataset

AbstractElectronic newspapers are one of the most common sources of Modern Standard Arabic. Existing datasets of Arabic news articles typically provide a title, body, and single label. Ignoring important features, like the article author, image, tags, and publication date, can degrade the efficacy of classification models. In this paper, we propose the Arabic multi-purpose integral news articles (AMINA) dataset. AMINA is a large-scale Arabic news corpus with over 1,850,000 articles collected from 9 Arabic newspapers from different countries. It includes all the article features: title, tags, publication date and time, location, author, article image and its caption, and the number of visits. To test the efficacy of the proposed dataset, three tasks were developed and validated: article textual content (classification and generation) and article image classification. For content classification, we experimented the performance of several state-of-the-art Arabic NLP models including AraBERT and CAMeL-BERT, etc. For content generation, the reformer architecture is adopted as a character text generation model. For image classification applied on Al-Sharq and Youm7 news portals, we have compared the performance of 10 pre-trained models including ConvNeXt, MaxViT, ResNet18, etc. The overall study verifies the significance and contribution of our newly introduced Arabic articles dataset. The AMINA dataset has been released at https://huggingface.co/datasets/MohamedZayton/AMINA.

Label distribution learning for compound facial expression recognition in‐the‐wild: A comparative study

AbstractHuman emotional states encompass both basic and compound facial expressions. However, current works primarily focus on basic expressions, consequently neglecting the broad spectrum of human emotions encountered in practical scenarios. Compound facial expressions involve the simultaneous manifestation of multiple emotions on an individual's face. This phenomenon reflects the complexity and richness of human states, where facial features dynamically convey a combination of feelings. This study embarks on a pioneering exploration of Compound Facial Expression Recognition (CFER), with a distinctive emphasis on leveraging the Label Distribution Learning (LDL) paradigm. This strategic application of LDL aims to address the ambiguity and complexity inherent in compound expressions, marking a significant departure from the dominant Single Label Learning (SLL) and Multi‐Label Learning (MLL) paradigms. Within this framework, we rigorously investigate the potential of LDL for a critical challenge in Facial Expression Recognition (FER): recognizing compound facial expressions in uncontrolled environments. We utilize the recently introduced RAF‐CE dataset, meticulously designed for compound expression assessment. By conducting a comprehensive comparative analysis pitting LDL against conventional SLL and MLL approaches on RAF‐CE, we aim to definitively establish LDL's superiority in handling this complex task. Furthermore, we assess the generalizability of LDL models trained on RAF‐CE by evaluating their performance on the EmotioNet and RAF‐DB Compound datasets. This demonstrates their effectiveness without domain adaptation. To solidify these findings, we conduct a comprehensive comparative analysis of 12 cutting‐edge LDL algorithms on RAF‐CE, S‐BU3DFE, and S‐JAFFE datasets, providing valuable insights into the most effective LDL techniques for FER in‐the‐wild.

Dealing with partial labels by knowledge distillation

Partial label learning (PLL) is a weakly supervised methodology dealing with tasks that have annotation problems by replacing the single label with a collection of candidate labels. Compared to single labels, utilizing partial labels faces challenges: (1) The limited supervision and sensitivity to the false positive candidates; (2) Situations where the ground truth is not in the candidate label sets (noisy PLs). However, in the case that there exists a subset of samples that can be easily labeled (referred to as clean samples), the existing PLL paradigm needlessly assigns these instances with partial labels randomly. To better utilize the clean samples, and alleviate the obstacles of adopting partial labels, we proposed a specific Partial Label Knowledge Distillation (PLKD) framework to distill the knowledge from the samples with low annotating cost, further guiding partial label samples with limited supervision in these scenarios. The teacher model of PLKD was pre-trained on the clean samples with a single label, which can reduce the effect of noisy PLs when training on the remaining PLL samples. Additionally, recognizing that the existing candidate labels are sampled under the uniform distribution, which may not reflect real-life scenarios, we also proposed a label-specific candidate generation method. Correspondingly, a new loss function based on our generation method is presented to evaluate the distinction between partial labels and predictions. Furthermore, we also present a partial-label guided version, denoted as PLKD-pl, to alleviate the teacher’s risk of over-confidence when the distribution between the clean set and partial label set varies widely. Extensive experimental evaluations have been conducted to demonstrate the superiority of PLKD over six state-of-the-art counterparts.

Development of an immunoprecipitation assay for detecting anti‐3‐hydroxy‐3‐methylglutaryl‐coenzyme A reductase autoantibodies using a non‐radioactive biotinylated recombinant protein

AbstractObjectivesA variety of myositis‐specific autoantibodies have been identified in sera from patients with idiopathic inflammatory myopathies, and they play a crucial role in tailoring personalized disease management. In particular, autoantibodies against 3‐hydroxy‐3‐methylglutaryl‐coenzyme A reductase (HMGCR) are now recognized as a key tool for diagnosing immune‐mediated necrotizing myopathy. The current gold standard for detecting anti‐HMGCR autoantibodies involves immunoprecipitation (IP) using radiolabeled proteins from cell extracts or purified proteins produced by in vitro transcription/translation (IVTT). Unfortunately, this radioisotope labeling is technically intricate and not suitable for routine laboratory use. To address this, we developed a novel assay called “Bio‐IVTT‐IP” for detecting anti‐HMGCR autoantibodies, which uses a nonradioactive biotinylated recombinant HMGCR protein produced by IVTT.MethodsWe collected 14 clinical specimens containing anti‐HMGCR autoantibodies from patients with immune‐mediated necrotizing myopathy, which were validated using the gold standard IP assay, and a set of 35 control samples from patients with other autoimmune diseases, such as systemic lupus erythematosus.ResultsThe Bio‐IVTT‐IP assay successfully identified 14 clinical samples positive for anti‐HMGCR. We confirmed that the performance of the Bio‐IVTT‐IP assay was completely consistent with that of the gold standard IP assay using radiolabeled proteins. Notably, no immunoprecipitates were found in control samples from patients with other autoimmune diseases.ConclusionsThese findings show that the Bio‐IVTT‐IP assay can serve as a potential alternative to the gold standard IP assay for detecting anti‐HMGCR autoantibodies. It can be considered a practical immunodiagnostic tool for diagnosing immune‐mediated necrotizing myopathy, particularly owing to its accessibility in routine laboratory settings.

AlgoDM: algorithm to perform aspect-based sentiment analysis using IDistance matrix

Sentiment analysis is a method of analyzing data to identify its intent. It identifies the emotional tone of a text body. Aspect-based sentiment analysis is a text analysis technique that identifies the aspect and the sentiment associated with each aspect. Different organizations use aspect-based sentiment analysis to analyze opinions about a product, service, or idea. Traditional sentiment analysis methods analyze the complete text and assign a single sentiment label to it. They do not handle the tasks of aspect association, dealing with multiple aspects and inclusion of linguistic concepts together as a system. In this article, AlgoDM, an algorithm to perform aspect-based sentiment analysis is proposed. AlgoDM uses a novel concept of IDistance matrix to extract aspects, associate aspects with sentiment words, and determine the sentiment associated with each aspect. The IDistance matrix is constructed to calculate the distance between aspects and the words expressing the sentiment related to the aspect. It works at the sentence level and identifies the opinion expressed on each aspect appearing in the sentence. It also evaluates the overall sentiment expressed in the sentence. The proposed algorithm can perform sentiment analysis of any opinionated text.

Efficacy of Heart Revival, an Ayurvedic formulation, in hypertension and related risks – An exploratory single arm open label trial

Efficacy of Heart Revival, an Ayurvedic formulation, in hypertension and related risks – An exploratory single arm open label trial

Strain tracking with uncertainty quantification.

The ability to detect and quantify microbiota over time has a plethora of clinical, basic science, and public health applications. One of the primary means of tracking microbiota is through sequencing technologies. When the microorganism of interest is well characterized or known a priori , targeted sequencing is often used. In many applications, however, untargeted bulk (shotgun) sequencing is more appropriate; for instance, the tracking of infection transmission events and nucleotide variants across multiple genomic loci, or studying the role of multiple genes in a particular phenotype. Given these applications, and the observation that pathogens (e.g. Clostridioides difficile, Escherichia coli, Salmonella enterica ) and other taxa of interest can reside at low relative abundance in the gastrointestinal tract, there is a critical need for algorithms that accurately track low-abundance taxa with strain level resolution. Here we present a sequence quality- and time-aware model, ChronoStrain , that introduces uncertainty quantification to gauge low-abundance species and significantly outperforms the current state-of-the-art on both real and synthetic data. ChronoStrain leverages sequences' quality scores and the samples' temporal information to produce a probability distribution over abundance trajectories for each strain tracked in the model. We demonstrate Chronostrain's improved performance in capturing post-antibiotic Escherichia coli strain blooms among women with recurrent urinary tract infections (UTIs) from the UTI Microbiome (UMB) Project. Other strain tracking models on the same data either show inconsistent temporal colonization or can only track consistently using very coarse groupings. In contrast, our probabilistic outputs can reveal the relationship between low-confidence strains present in the sample that cannot be reliably assigned a single reference label (either due to poor coverage or novelty) while simultaneously calling high-confidence strains that can be unambiguously assigned a label. We also analyze samples from the Early Life Microbiota Colonisation (ELMC) Study demonstrating the algorithm's ability to correctly identify Enterococcus faecalis strains using paired sample isolates as validation.

Multi-task deep learning strategy for map-type classification

ABSTRACT The information contained in a map is always represented by text, symbols, and map-type. Among them, map-type is a critical element that denotes the category and theme of map content, which can support map content extraction, map retrieval, and other map data mining tasks. However, the representations of map-type are always so complex and diverse that relies on multiple descriptive labels. Traditional deep learning methods regarding map-type classification are developed by single label, which only supports single-task classification. This means these approaches might overlook the common features among multiple map-type. In this paper, we propose a framework of multi-task deep learning strategy for employing the state-of-the-art deep convolutional neural network models, including ResNet50, MobileNetV2, and Inception-v3, to conduct efficient multi-label map-type classification. Specifically, we develop the dedicated classification module and label selection layer, and integrate them into the backbone of the deep convolutional network model. The experiments revealed that our proposed multi-task classification strategy can achieve greater accuracy in map-type classification, with less processing time required compared to state-of-the-art deep learning regarding map-type classification. This proves that multi-task classification strategy could be competitive to recognize and discover the complex map-type information.

Speechformer-CTC: Sequential modeling of depression detection with speech temporal classification

Speech-based automatic depression detection systems have been extensively explored over the past few years. Typically, each speaker is assigned a single label (Depressive or Non-depressive), and most approaches formulate depression detection as a speech classification task without explicitly considering the non-uniformly distributed depression pattern within segments, leading to low generalizability and robustness across different scenarios. However, depression corpora do not provide fine-grained labels (at the phoneme or word level) which makes the dynamic depression pattern in speech segments harder to track using conventional frameworks. To address this, we propose a novel framework, Speechformer-CTC, to model non-uniformly distributed depression characteristics within segments using a Connectionist Temporal Classification (CTC) objective function without the necessity of input–output alignment. Two novel CTC-label generation policies, namely the Expectation-One-Hot and the HuBERT policies, are proposed and incorporated in objectives on various granularities. Additionally, experiments using Automatic Speech Recognition (ASR) features are conducted to demonstrate the compatibility of the proposed method with content-based features. Our results show that the performance of depression detection, in terms of Macro F1-score, is improved on both DAIC-WOZ (English) and CONVERGE (Mandarin) datasets. On the DAIC-WOZ dataset, the system with HuBERT ASR features and a CTC objective optimized using HuBERT policy for label generation achieves 83.15% F1-score, which is close to state-of-the-art without the need for phoneme-level transcription or data augmentation. On the CONVERGE dataset, using Whisper features with the HuBERT policy improves the F1-score by 9.82% on CONVERGE1 (in-domain test set) and 18.47% on CONVERGE2 (out-of-domain test set). These findings show that depression detection can benefit from modeling non-uniformly distributed depression patterns and the proposed framework can be potentially used to determine significant depressive regions in speech utterances.

A Siamese network optimization using genetic algorithm for brain diseases

AbstractThe complex nature of human brain tissues is important in ensuring accurate diagnosis to save human lives. Research on early detection of brain diseases has gained significant prominence within medical intelligence using highly complex model architectures with only a single label that cannot be verified. This paper introduces an innovative approach to Siamese Network Genetic Algorithm (SN‐GA) leveraging Siamese contrastive learning for classifying brain images across diverse diseases. Our core architecture is a Bi‐Convolutional Neural Network (Bi‐CNN) optimized by a genetic algorithm to enhance brain image classification. Specifically, five widely recognized transfer learning‐based architectures, namely AlexNet, Efficient‐B0, VGG‐16, ResNet‐50, and Inception‐v3, have been incorporated to evaluate the effectiveness of the proposed SN‐GA system. The performance of these models has been rigorously analyzed and compared using two distinct datasets: Brain tumors and Alzheimer's datasets. The experimental results robustly affirm the efficacy of the proposed Siamese model, yielding exceptional levels of accuracy, precision, and recall, all peaking at 97%. These findings underscore the potential and resilience of the optimized Siamese network in the context of brain disease classification, emphasizing its significance in advancing the field of medical imaging and diagnosis, with implications for early intervention and patient care.

A Semi-Automatic Magnetic Resonance Imaging Annotation Algorithm Based on Semi-Weakly Supervised Learning.

The annotation of magnetic resonance imaging (MRI) images plays an important role in deep learning-based MRI segmentation tasks. Semi-automatic annotation algorithms are helpful for improving the efficiency and reducing the difficulty of MRI image annotation. However, the existing semi-automatic annotation algorithms based on deep learning have poor pre-annotation performance in the case of insufficient segmentation labels. In this paper, we propose a semi-automatic MRI annotation algorithm based on semi-weakly supervised learning. In order to achieve a better pre-annotation performance in the case of insufficient segmentation labels, semi-supervised and weakly supervised learning were introduced, and a semi-weakly supervised learning segmentation algorithm based on sparse labels was proposed. In addition, in order to improve the contribution rate of a single segmentation label to the performance of the pre-annotation model, an iterative annotation strategy based on active learning was designed. The experimental results on public MRI datasets show that the proposed algorithm achieved an equivalent pre-annotation performance when the number of segmentation labels was much less than that of the fully supervised learning algorithm, which proves the effectiveness of the proposed algorithm.

MSTSENet: Multiscale Spectral–Spatial Transformer with Squeeze and Excitation network for hyperspectral image classification

Hyperspectral image (HSI) classification pertains to the task of assigning a single label to each pixel by analyzing its spectral–spatial characteristics. Convolutional Neural Networks (CNNs) have garnered significant attention on account of their remarkable performance in feature representation. However, these approaches possess a restricted capacity to acquire highly similar spectral features. Recently, Attention-based approaches have been devised as a means to surmount the limitations inherent in CNNs. In this paper, we address a novel architecture for spectral–spatial feature extraction and HSI classification. The framework efficiently amalgamates the robustness and efficacy of three modern backbone networks, i.e., Multiscale CNN, Squeeze and Excitation (SE), and Transformer named MSTSENet. Initially, the multiscale convolution module integrates three branches of 3D convolution layers, each employing distinct kernel sizes, facilitating multiscale and multi-resolution feature extraction. Subsequently, the SE module enhances the inter-channel relationship by adaptively recalibrating the feature weight. The strategic fusion of the SE module with multiscale CNN strengthens deep feature extraction while introducing a minimal increment in overall parameters. Lastly, the Transformer module orchestrates information aggregation across different spectral–spatial regions, accurately modeling long-range contextual dependencies and capturing dominant feature representations. To evaluate the model performance, comprehensive experiments have been carried out on widely used benchmark HSI datasets. The overall accuracy of 98.74%, 99.83%, and 99.98% is achieved over the Indian Pines, Pavia University, and Salinas Valley datasets, respectively. The code of this work will be accessible at https://github.com/irfan01000/MSTSENet.

Convolution Neural Network Based Multi-Label Disease Detection Using Smartphone Captured Tongue Images

Purpose: Tongue image analysis for disease diagnosis is an ancient, traditional, non-invasive diagnostic technique widely used by traditional medicine practitioners. Deep learning-based multi-label disease detection models have tremendous potential for clinical decision support systems because they facilitate preliminary diagnosis. Methods: In this work, we propose a multi-label disease detection pipeline where observation and analysis of tongue images captured and received via smartphones assist in predicting the health status of an individual. Subjects, who consult collaborating physicians, voluntarily provide all images. Images thus acquired are first and foremost classified either into a diseased or a normal category by a 5-fold cross-validation algorithm using a convolutional neural network (MobileNetV2) model for binary classification. Once it predicts the diseased label, the disease prediction algorithm based on DenseNet-121 uses the image to diagnose single or multiple disease labels. Results: The MobileNetV2 architecture-based disease detection model achieved an average accuracy of 93% in distinguishing between diseased and normal, healthy tongues, whereas the multilabel disease classification model produced more than 90% accurate results for the disease class labels considered, strongly indicating a successful outcome with the smartphone-captured image dataset. Conclusion: AI-based image analysis shows promising results, and an extensive dataset could provide further improvements to this approach. Experimenting with smartphone images opens a great opportunity to provide preliminary health status to individuals at remote locations as well, prior to further treatment and diagnosis, using the concept of telemedicine.

Federated Learning With Only Positive Labels by Exploring Label Correlations.

Federated learning (FL) aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this article, we study the multilabel classification (MLC) problem under the FL setting, where trivial solution and extremely poor performance may be obtained, especially when only positive data with respect to a single class label is provided for each client. This issue can be addressed by adding a specially designed regularizer on the server side. Although effective sometimes, the label correlations are simply ignored and thus suboptimal performance may be obtained. Besides, it is expensive and unsafe to exchange user's private embeddings between server and clients frequently, especially when training model in the contrastive way. To remedy these drawbacks, we propose a novel and generic method termed federated averaging (FedAvg) by exploring label correlations (FedALCs). Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training. To further improve the safety and also reduce the communication overhead, we propose a variant to learn fixed class embedding for each client, so that the server and clients only need to exchange class embeddings once. Extensive experiments on multiple popular datasets demonstrate that our FedALC can significantly outperform the existing counterparts.

Comprehensive mapping of histamine H1 receptor mRNA in the mouse brain.

Histamine H1 receptor (H1R) in the central nervous system plays an important role in various functions, including learning and memory, aggression, feeding behaviors, and wakefulness, as evidenced by studies utilizing H1R knockout mice and pharmacological interventions. Although previous studies have reported the widespread distribution of H1R in the brains of rats, guinea pigs, monkeys, and humans, the detailed distribution in the mouse brain remains unclear. This study provides a comprehensive description of the distribution of H1R mRNA in the mouse brain using two recently developed techniques: RNAscope and in situ hybridization chain reaction, both of which offer enhanced sensitivity and resolution compared to traditional methodologies such as radioisotope labeling, which were used in previous studies. The H1R mRNA expression was observed throughout the entire brain, including key regions implicated in sleep-wake regulatory functions, such as the pedunculopontine tegmental nucleus and dorsal raphe. Additionally, strong H1R mRNA signals were identified in the paraventricular hypothalamus and ventromedial hypothalamus, which may explain the potential mechanisms underlying histamine-mediated feeding regulation. Notably, we identified strong H1R mRNA expression in previously unreported cerebral regions, such as the dorsal endopiriform nucleus, bed nucleus of the accessory olfactory tract, and postsubiculum. These findings significantly contribute to our understanding of the multifaceted roles of H1R in diverse brain functions.