Random Labeling Research Articles

B - 57 Examining Symptom Patterns in Anomalous Health Incidents: a Spectral Co-Clustering Analysis Using the Post-Concussion Symptom Scale

Abstract Objective The ImPACT Post-Concussion Symptom Scale (PCSS) is widely used to document post-concussion symptoms. This study investigated the structural patterns of PCSS using spectral co-clustering on data from U.S. diplomats and their families who served in Cuba and China, who reported experiencing Anomalous Health Incidents (AHIs). Method Clinicians at the University of Pennsylvania evaluated 65 individuals with potential AHI exposure (Median age-group = 35–45 years; 73.84% in Cuba; 49.23% females). PCSS feature scores were discretized into 4-level symptom severity expressions: none, mild, moderate, and severe. The preprocessed data were fit with spectral co-clustering model to extract optimal number of biclusters, by measuring scree plot with principal component analysis and Calinski-Harabasz (CH) score. Final model was also evaluated by CH score and a random label t-test to compare the significance of the clustering results. Results Overall, spectral co-clustering yielded two biclusters with CH score of 20.29 and random label t-test of p < 0.001, suggesting reasonable clustering quality. Biclustering identified two sets of interpretable PCSS symptom characteristics. Cluster centroids X and Y (IDs retracted) were estimated using Manhattan distance, summarizing symptom characteristics of each cluster. More precisely, centroid X represented mild to moderate symptom profiles (e.g., headache, dizziness, drowsiness, and nervousness), while centroidY represented a relative absence of symptoms, except for mild nervousness and emotionality. Conclusion The spectral co-clustering of PCSS reveals patterns of elevated symptoms in one cluster and minimal symptom burden in the other, similar to outcomes observed after mild TBI. These patterns can guide future research directions and ultimately improve patient outcomes in various medical contexts.

On the interpretability of quantum neural networks

Interpretability of artificial intelligence (AI) methods, particularly deep neural networks, is of great interest. This heightened focus stems from the widespread use of AI-backed systems. These systems, often relying on intricate neural architectures, can exhibit behavior that is challenging to explain and comprehend. The interpretability of such models is a crucial component of building trusted systems. Many methods exist to approach this problem, but they do not apply straightforwardly to the quantum setting. Here, we explore the interpretability of quantum neural networks using local model-agnostic interpretability measures commonly utilized for classical neural networks. Following this analysis, we generalize a classical technique called LIME, introducing Q-LIME, which produces explanations of quantum neural networks. A feature of our explanations is the delineation of the region in which data samples have been given a random label, likely subjects of inherently random quantum measurements. We view this as a step toward understanding how to build responsible and accountable quantum AI models.

Spatial Pattern of Host Tree Size, Rather than of Host Tree Itself, Affects the Infection Likelihood of a Fungal Stem Disease.

The spatial pattern of diseased forest trees is a product of the spatial pattern of host trees and the disease itself. Previous studies have focused on describing the spatial pattern of diseased host trees, and it remains largely unknown whether an antecedent spatial pattern of host/nonhost trees affects the infection pattern of a disease and how large the effect sizes of the spatial pattern of host/nonhost trees and host size are. The results from trivariate random labeling showed that the antecedent pattern of the host ash tree, Fraxinus mandshurica, but not of nonhost tree species, impacted the infection pattern of a stem fungal disease caused by Inonotus hispidus. To investigate the effect size of the spatial pattern of ash trees, we employed the SADIE (Spatial Analysis by Distance IndicEs) aggregation index and clustering index as predictors in the GLMs. Globally, the spatial pattern (vi index) of ash trees did not affect the infection likelihood of the focal tree; however, the spatial pattern of DBH (diameter at breast height) of ash trees significantly affected the infection likelihood of the focal tree. We sampled a series of circular plots with different radii to investigate the spatial pattern effect of host size on the infection likelihood of the focal tree locally. The results showed that the location (patch/gap) of the DBH of the focal tree, rather than that of the focal tree itself, significantly affected its infection likelihood in most plots of the investigated sizes. A meta-analysis was employed to settle the discrepancy between plots of different sizes, which led to results consistent with those of global studies. The results from meta-regression showed that plot size had no significant effects.

An Efficient and Versatile Variational Method for High-Dimensional Data Classification

High-dimensional data classification is a fundamental task in machine learning and imaging science. In this paper, we propose an efficient and versatile multi-class semi-supervised classification method for classifying high-dimensional data and unstructured point clouds. To begin with, a warm initialization is generated by using a fuzzy classification method such as the standard support vector machine or random labeling. Then an unconstraint convex variational model is proposed to purify and smooth the initialization, followed by a step which is to project the smoothed partition obtained previously to a binary partition. These steps can be repeated, with the latest result as a new initialization, to keep improving the classification quality. We show that the convex model of the smoothing step has a unique solution and can be solved by a specifically designed primal–dual algorithm whose convergence is guaranteed. We test our method and compare it with the state-of-the-art methods on several benchmark data sets. Thorough experimental results demonstrate that our method is superior in both the classification accuracy and computation speed for high-dimensional data and point clouds.

A novel bayesian network-based ensemble classifier chains for multi-label classification

In this paper, we address the challenges of random label ordering and limited interpretability associated with Ensemble Classifier Chains (ECC) by introducing a novel ECC method, ECC-MOO&BN, which integrates Bayesian Networks (BN) and Multi-Objective Optimization (MOO). This approach is designed to concurrently overcome these ECC limitations. The ECC-MOO&BN method focuses on extracting diverse and interpretable label orderings for the ECC classifier. We initiated this process by employing mutual information to investigate label relationships and establish the initial structures of the BN. Subsequently, an enhanced NSGA-II algorithm was applied to develop a series of Directed Acyclic Graphs (DAGs) that effectively balance the likelihood and complexity of the BN structure. The rationale behind using the MOO method lies in its ability to optimize both complexity and likelihood simultaneously, which not only diversifies DAG generation but also helps avoid overfitting during the production of label orderings. The DAGs, once sorted topologically, yielded a series of label orderings, which were then seamlessly integrated into the ECC framework for addressing multi-label classification (MLC) problems. Experimental results show that when benchmarked against eleven leading-edge MLC algorithms, our proposed method achieves the highest average ranking across seven evaluation criteria on nine out of thirteen MLC datasets. The results of the Friedman test and Nemenyi test also indicate that the performance of the proposed method has a significant advantage compared to other algorithms.

Further results on random walk labelings

In a previous work, we defined and studied random walk labelings of graphs. These are graph labelings that are obtainable by performing a random walk on the graph, such that each vertex is labeled upon its first visit. In this work, we calculate the number of random walk labelings of several natural graph families: The wheel, fan, barbell, lollipop, tadpole, friendship, and snake graphs. Additionally, we prove several combinatorial identities that emerged during the calculations.

Rethinking Regularization with Random Label Smoothing

Regularization helps to improve machine learning techniques by penalizing the models during training. Such approaches act in either the input, internal, or output layers. Regarding the latter, label smoothing is widely used to introduce noise in the label vector, making learning more challenging. This work proposes a new label regularization method, Random Label Smoothing, that attributes random values to the labels while preserving their semantics during training. The idea is to change the entire label into fixed arbitrary values. Results show improvements in image classification and super-resolution tasks, outperforming state-of-the-art techniques for such purposes.

Machine Failure Prediction Using Multilabel Classification Methods

Early detection of machine failure is crucial in every industrial setting as it may prevent unexpected process downtimes as well as system failures. However, machine learning (ML) models are increasingly being utilized to forecast system failures in industrial maintenance, and among them, multilabel classification techniques act as efficient methods. Therefore, this study analyzed machine failure data with five types of machine failures. Initially, a feature selection approach was also carried out in this study to determine the variables which directly cause machine failure. Furthermore, multilabel k-nearest neighbours (MLkNN), multilabel adaptive resonance associative map (MLARAM), and multilabel twin support vector machine classifier (MLTSVM) in adapted algorithms, Binary Relevance, ClassifierChain, and LabelPowerSet in problem transformation approaches, and Random Label Space Partitioning with Label Powerset (RakelD) in ensemble classifiers were employed. To train these models, both the original data set as well as data frame after the feature selection was used, and hamming loss, accuracy, macro, and micro averages were calculated for each of these classifiers. According to the results, MLkNN in adapted algorithms and LabelPowerset in problem transformation approaches performed better than other classifiers used in this study. Therefore, it can be concluded that MLkNN and LabelPowerset could be used to classify multilabel with positive results. KEYWORDS: adapted algorithms, ensemble classifiers, feature selection, machine failure, machine learning, multilabel classification, problem transformation.

Understanding quantum machine learning also requires rethinking generalization

Quantum machine learning models have shown successful generalization performance even when trained with few data. In this work, through systematic randomization experiments, we show that traditional approaches to understanding generalization fail to explain the behavior of such quantum models. Our experiments reveal that state-of-the-art quantum neural networks accurately fit random states and random labeling of training data. This ability to memorize random data defies current notions of small generalization error, problematizing approaches that build on complexity measures such as the VC dimension, the Rademacher complexity, and all their uniform relatives. We complement our empirical results with a theoretical construction showing that quantum neural networks can fit arbitrary labels to quantum states, hinting at their memorization ability. Our results do not preclude the possibility of good generalization with few training data but rather rule out any possible guarantees based only on the properties of the model family. These findings expose a fundamental challenge in the conventional understanding of generalization in quantum machine learning and highlight the need for a paradigm shift in the study of quantum models for machine learning tasks.

Gaussian universality of perceptrons with random labels.

While classical in many theoretical settings-and in particular in statistical physics-inspired works-the assumption of Gaussian i.i.d. input data is often perceived as a strong limitation in the context of statistics and machine learning. In this study, we redeem this line of work in the case of generalized linear classification, also known as the perceptron model, with random labels. We argue that there is a large universality class of high-dimensional input data for which we obtain the same minimum training loss as for Gaussian data with corresponding data covariance. In the limit of vanishing regularization, we further demonstrate that the training loss is independent of the data covariance. On the theoretical side, we prove this universality for an arbitrary mixture of homogeneous Gaussian clouds. Empirically, we show that the universality holds also for a broad range of real data sets.

Stochastic gradient descent with random label noises: doubly stochastic models and inference stabilizer

Random label noise (or observational noise) widely exists in practical machine learning settings. While previous studies primarily focused on the effects of label noise to the performance of learning, our work intends to investigate the implicit regularization effects of label noise, under mini-batch sampling settings of stochastic gradient descent (SGD), with the assumption that label noise is unbiased. Specifically, we analyze the learning dynamics of SGD over the quadratic loss with unbiased label noise (ULN), where we model the dynamics of SGD as a stochastic differentiable equation with two diffusion terms (namely a doubly stochastic model). While the first diffusion term is caused by mini-batch sampling over the (label-noiseless) loss gradients, as in many other works on SGD (Zhu et al 2019 ICML 7654–63; Wu et al 2020 Int. Conf. on Machine Learning (PMLR) pp 10367–76), our model investigates the second noise term of SGD dynamics, which is caused by mini-batch sampling over the label noise, as an implicit regularizer. Our theoretical analysis finds such an implicit regularizer would favor some convergence points that could stabilize model outputs against perturbations of parameters (namely inference stability). Though similar phenomenon have been investigated by Blanc et al (2020 Conf. on Learning Theory (PMLR) pp 483–513), our work does not assume SGD as an Ornstein–Uhlenbeck-like process and achieves a more generalizable result with convergence of the approximation proved. To validate our analysis, we design two sets of empirical studies to analyze the implicit regularizer of SGD with unbiased random label noise for deep neural network training and linear regression. Our first experiment studies the noisy self-distillation tricks for deep learning, where student networks are trained using the outputs from well-trained teachers with additive unbiased random label noise. Our experiment shows that the implicit regularizer caused by the label noise tends to select models with improved inference stability. We also carry out experiments on SGD-based linear regression with ULN, where we plot the trajectories of parameters learned in every step and visualize the effects of implicit regularization. The results back up our theoretical findings.

First-in-Human Evaluation of Site-Specifically Labeled 89Zr-Pertuzumab in Patients with HER2-Positive Breast Cancer.

Radioimmunoconjugates targeting human epidermal growth factor receptor 2 (HER2) have shown potential to noninvasively visualize HER2-positive tumors. However, the stochastic approach that has been traditionally used to radiolabel these antibodies yields poorly defined and heterogeneous products with suboptimal invivo performance. Here, we describe a first-in-human PET study on patients with HER2-positive breast cancer evaluating the safety, biodistribution, and dosimetry of 89Zr-site-specific (ss)-pertuzumab PET, a site-specifically labeled radioimmunoconjugate designed to circumvent the limitations of random stochastic lysine labeling. Methods: Six patients with HER2-positive metastatic breast cancer were enrolled in a prospective clinical trial. Pertuzumab was site-specifically modified with desferrioxamine (DFO) via a novel chemoenzymatic strategy and subsequently labeled with 89Zr. Patients were administered 74 MBq of 89Zr-ss-pertuzumab in 20 mg of total antibody intravenously and underwent PET/CT at 1 d, 3-4 d, and 5-8 d after injection. PET imaging, whole-body probe counts, and blood draws were performed to assess the pharmacokinetics, biodistribution, and dosimetry. Results: 89Zr-ss-pertuzumab PET/CT was used to assess HER2 status and heterogeneity to guide biopsy and decide the next line of treatment at progression. The radioimmunoconjugate was able to detect known sites of malignancy, suggesting that these tumor lesions were HER2-positive. The optimal imaging time point was 5-8 d after administration, and no toxicities were observed. Dosimetry estimates from OLINDA showed that the organs receiving the highest doses (mean ± SD) were kidney (1.8 ± 0.5 mGy/MBq), liver (1.7 ± 0.3 mGy/MBq), and heart wall (1.2 ± 0.1 mGy/MBq). The average effective dose for 89Zr-ss-pertuzumab was 0.54 ± 0.03 mSv/MBq, which was comparable to both stochastically lysine-labeled 89Zr-DFO-pertuzumab and 89Zr-DFO-trastuzumab. One patient underwent PET/CT with both 89Zr-ss-pertuzumab and 89Zr-DFO-pertuzumab 1 mo apart, with 89Zr-ss-pertuzumab demonstrating improved lesion detection and higher tracer avidity. Conclusion: This study demonstrated the safety, dosimetry, and potential clinical applications of 89Zr-ss-pertuzumab PET/CT. 89Zr-ss-pertuzumab may detect more lesions than 89Zr-DFO-pertuzumab. Potential clinical applications include real-time evaluation of HER2 status to guide biopsy and assist in treatment decisions.

Predicting the Impact of Data Poisoning Attacks in Blockchain-Enabled Supply Chain Networks

As computer networks become increasingly important in various domains, the need for secure and reliable networks becomes more pressing, particularly in the context of blockchain-enabled supply chain networks. One way to ensure network security is by using intrusion detection systems (IDSs), which are specialised devices that detect anomalies and attacks in the network. However, these systems are vulnerable to data poisoning attacks, such as label and distance-based flipping, which can undermine their effectiveness within blockchain-enabled supply chain networks. In this research paper, we investigate the effect of these attacks on a network intrusion detection system using several machine learning models, including logistic regression, random forest, SVC, and XGB Classifier, and evaluate each model via their F1 Score, confusion matrix, and accuracy. We run each model three times: once without any attack, once with random label flipping with a randomness of 20%, and once with distance-based label flipping attacks with a distance threshold of 0.5. Additionally, this research tests an eight-layer neural network using accuracy metrics and a classification report library. The primary goal of this research is to provide insights into the effect of data poisoning attacks on machine learning models within the context of blockchain-enabled supply chain networks. By doing so, we aim to contribute to developing more robust intrusion detection systems tailored to the specific challenges of securing blockchain-based supply chain networks.

Precise learning curves and higher-order scaling limits for dot-product kernel regression *

As modern machine learning models continue to advance the computational frontier, it has become increasingly important to develop precise estimates for expected performance improvements under different model and data scaling regimes. Currently, theoretical understanding of the learning curves (LCs) that characterize how the prediction error depends on the number of samples is restricted to either large-sample asymptotics () or, for certain simple data distributions, to the high-dimensional asymptotics in which the number of samples scales linearly with the dimension (). There is a wide gulf between these two regimes, including all higher-order scaling relations , which are the subject of the present paper. We focus on the problem of kernel ridge regression for dot-product kernels and present precise formulas for the mean of the test error, bias and variance, for data drawn uniformly from the sphere with isotropic random labels in the rth-order asymptotic scaling regime with held constant. We observe a peak in the LC whenever for any integer r, leading to multiple sample-wise descent and non-trivial behavior at multiple scales. We include a colab (available at: https://tinyurl.com/2nzym7ym) notebook that reproduces the essential results of the paper.

An effective relation-first detection model for relational triple extraction

Relational triple extraction is a crucial task in the field of information extraction, which attempts to identify all triples from natural language text. Existing methods primarily focus on addressing the issue of overlapping triples. However, the majority of studies need to perform the same operation on all predefined relations when solving this problem, which will lead to relation redundancy. In addition, most methods have the problem of error propagation. During training, they use the ground truth labels as a priori knowledge to predict at different stages, while during inference, they must use the labels predicted in the previous stage to predict in the following stages. To address these problems, we propose an effective relation-first detection model for relational triple extraction (ERFD-RTE). The proposed model first detects the potential relations in the sentence and then performs entity recognition for each specific relation, which aims to solve the overlapping triples issue and avoid additional calculations for redundant relations. We design a random label error strategy for the error propagation problem in the training phase, which balances the difference between training and inference. Experiment results demonstrate that ERFD-RTE is superior to other baselines by improving the F1 score to 92.7% (+0.7%) on NYT-P and NYT-E, 92.9% (+0.3%) on WebNLG-P, 89.3% (+0.9%) on WebNLG-E and 83.71% (+1.5%) on ADE. Additional analysis shows that ERFD-RTE can effectively extract overlapping triples.

Application of Data Particle Geometrical Divide Algorithms in the Process of Radar Signal Recognition.

The process of recognising and classifying radar signals and their radiation sources is currently a key element of operational activities in the electromagnetic environment. Systems of this type, called ELINT class systems, are passive solutions that detect, process, and analyse radio-electronic signals, providing distinctive information on the identified emission source in the final stage of data processing. The data processing in the mentioned types of systems is a very sophisticated issue and is based on advanced machine learning algorithms, artificial neural networks, fractal analysis, intra-pulse analysis, unintentional out-of-band emission analysis, and hybrids of these methods. Currently, there is no optimal method that would allow for the unambiguous identification of particular copies of the same type of radar emission source. This article constitutes an attempt to analyse radar signals generated by six radars of the same type under comparable measurement conditions for all six cases. The concept of the SEI module for the ELINT system was proposed in this paper. The main aim was to perform an advanced analysis, the purpose of which was to identify particular copies of those radars. Pioneering in this research is the application of the author's algorithm for the data particle geometrical divide, which at the moment has no reference in international publication reports. The research revealed that applying the data particle geometrical divide algorithms to the SEI process concerning six copies of the same radar type allows for almost three times better accuracy than a random labelling strategy within approximately one second.

Data Reconstruction Attack with Label Guessing for Federated Learning

<p>In light of recent advancements in deep and machine learning, federated learning has been proposed as a means to prevent privacy invasion. However, a reconstruction attack that exploits gradients to leak learning data has recently been developed. With increasing research into federated learning and the importance of data usage, it is crucial to prepare for such attacks. Specifically, when face data are used in federated learning, the damage caused by privacy infringement can be significant. Therefore, attack studies are necessary to develop effective defense strategies against these attacks. In this study, we propose a new attack method that uses labels to achieve faster and more accurate reconstruction performance than previous reconstruction attacks. We demonstrate the effectiveness of our proposed method on the Yale Face Database B, MNIST, and CIFAR-10 datasets, as well as under non-IID conditions, similar to real federated learning. The results show that our proposed method outperforms random labeling in terms of reconstruction performance in all evaluations for MNIST and CIFAR-10 datasets in round 1.</p> <p> </p>

Local Inhomogeneous Weighted Summary Statistics for Marked Point Processes

We introduce a family of local inhomogeneous mark-weighted summary statistics, of order two and higher, for general marked point processes. Depending on how the involved weight function is specified, these summary statistics capture different kinds of local dependence structures. We first derive some basic properties and show how these new statistical tools can be used to construct most existing summary statistics for (marked) point processes. We then propose a local test of random labeling. This procedure allows us to identify points, and consequently regions, where the random labeling assumption does not hold, for example, when the (functional) marks are spatially dependent. Through a simulation study we show that the test is able to detect local deviations from random labeling. We also provide an application to an earthquake point pattern with functional marks given by seismic waveforms.

Asymptotic normality for the size of graph tries built from M-ary tree labelings

Graph tries are a new and interesting data structure proposed by Jacquet in 2014. They generalize the classical trie data structure which has found many applications in computer science and is one of the most popular data structure on words. For his generalization, Jacquet considered the size (or space requirement) and derived an asymptotic expansion for the mean and the variance when graph tries are built from n independently chosen random labelings of a rooted M-ary tree. Moreover, he conjectured a central limit theorem for the (suitably normalized) size as the number of labelings tends to infinity. In this paper, we verify this conjecture with the method of moments.

Double robust semi-supervised inference for the mean: selection bias under MAR labeling with decaying overlap

Abstract Semi-supervised (SS) inference has received much attention in recent years. Apart from a moderate-sized labeled data, $\mathcal L$, the SS setting is characterized by an additional, much larger sized, unlabeled data, $\mathcal U$. The setting of $|\mathcal U\ |\gg |\mathcal L\ |$, makes SS inference unique and different from the standard missing data problems, owing to natural violation of the so-called ‘positivity’ or ‘overlap’ assumption. However, most of the SS literature implicitly assumes $\mathcal L$ and $\mathcal U$ to be equally distributed, i.e., no selection bias in the labeling. Inferential challenges in missing at random type labeling allowing for selection bias, are inevitably exacerbated by the decaying nature of the propensity score (PS). We address this gap for a prototype problem, the estimation of the response’s mean. We propose a double robust SS mean estimator and give a complete characterization of its asymptotic properties. The proposed estimator is consistent as long as either the outcome or the PS model is correctly specified. When both models are correctly specified, we provide inference results with a non-standard consistency rate that depends on the smaller size $|\mathcal L\ |$. The results are also extended to causal inference with imbalanced treatment groups. Further, we provide several novel choices of models and estimators of the decaying PS, including a novel offset logistic model and a stratified labeling model. We present their properties under both high- and low-dimensional settings. These may be of independent interest. Lastly, we present extensive simulations and also a real data application.