We present the findings of an experimental study whereby we correlate the changes in the morphology of the photoplethysmography (PPG) signal to healthy aging. Under this pretext, we estimate the biological age of a person as well as the age group he/she belongs to, using the PPG data that we collect via a non-invasive low-cost MAX30102 PPG sensor. Specifically, we collect raw infrared PPG data from the finger-tip of 179 apparently healthy subjects, aged 3-65 years. In addition, we record the following metadata of each subject: age, gender, height, weight, family history of cardiac disease, smoking history, vitals (heart rate and SpO2). We pre-process the raw PPG data to remove noise, artifacts, and baseline wander. We then construct 60 features based upon the first four PPG derivatives, the so-called VPG, APG, JPG, and SPG signals, and the demographic features. We then do correlation-based feature-ranking (which retains 26 most important features), followed by Gaussian noise-based data augmentation (which results in 15-fold increase in the size of our dataset). Finally, we feed the feature set to three machine learning classifiers (logistic regression, decision tree, random forest), and two shallow neural networks: a feedforward neural network (FFNN) and a convolutional neural network (CNN). For the age group classification, the shallow FFNN performs the best with 98% accuracy for binary classification (3-15 years vs. 15+ years), and 97% accuracy for three-class classification (3-12 years, 13-30 years, 30+ years). For biological age prediction, the shallow FFNN again performs the best with a mean absolute error (MAE) of 1.64.
Metalearning and multitask learning are two frameworks for solving a group of related learning tasks more efficiently than we could hope to solve each of the individual tasks on their own. In multitask learning, we are given a fixed set of related learning tasks and need to output one accurate model per task, whereas in metalearning we are given tasks that are drawn i.i.d. from a metadistribution and need to output some common information that can be easily specialized to new tasks from the metadistribution. We consider a binary classification setting where tasks are related by a shared representation, that is, every task $P$ can be solved by a classifier of the form $f_{P} \circ h$ where $h \in H$ is a map from features to a representation space that is shared across tasks, and $f_{P} \in F$ is a task-specific classifier from the representation space to labels. The main question we ask is how much data do we need to metalearn a good representation? Here, the amount of data is measured in terms of the number of tasks $t$ that we need to see and the number of samples $n$ per task. We focus on the regime where $n$ is extremely small. Our main result shows that, in a distribution-free setting where the feature vectors are in $\mathbb{R}^d$, the representation is a linear map from $\mathbb{R}^d \to \mathbb{R}^k$, and the task-specific classifiers are halfspaces in $\mathbb{R}^k$, we can metalearn a representation with error $\varepsilon$ using $n = k+2$ samples per task, and $d \cdot (1/\varepsilon)^{O(k)}$ tasks. Learning with so few samples per task is remarkable because metalearning would be impossible with $k+1$ samples per task, and because we cannot even hope to learn an accurate task-specific classifier with $k+2$ samples per task. Our work also yields a characterization of distribution-free multitask learning and reductions between meta and multitask learning.
We address binary classification using neural ordinary differential equations from the perspective of simultaneous control of $N$ data points. We consider a single-neuron architecture with parameters fixed as piecewise constant functions of time. In this setting, the model complexity can be quantified by the number of control switches. Previous work has shown that classification can be achieved using a point-by-point strategy that requires $O(N)$ switches. We propose a new control method that classifies any arbitrary dataset by sequentially steering clusters of $d$ points, thereby reducing the complexity to $O(N/d)$ switches. The optimality of this result, particularly in high dimensions, is supported by some numerical experiments. Our complexity bound is sufficient but often conservative because same-class points tend to appear in larger clusters, simplifying classification. This motivates studying the probability distribution of the number of switches required. We introduce a simple control method that imposes a collinearity constraint on the parameters, and analyze a worst-case scenario where both classes have the same size and all points are i.i.d. Our results highlight the benefits of high-dimensional spaces, showing that classification using constant controls becomes more probable as $d$ increases.
Achieving state-of-the-art results in face verification systems typically hinges on the availability of labeled face training data, a resource that often proves challenging to acquire in substantial quantities. In this research endeavor, we proposed employing Siamese networks for face recognition, eliminating the need for labeled face images. We achieve this by strategically leveraging negative samples alongside nearest neighbor counterparts, thereby establishing positive and negative pairs through an unsupervised methodology. The architectural framework adopts a VGG encoder, trained as a double branch siamese network. Our primary aim is to circumvent the necessity for labeled face image data, thus proposing the generation of training pairs in an entirely unsupervised manner. Positive training data are selected within a dataset based on their highest cosine similarity scores with a designated anchor, while negative training data are culled in a parallel fashion, though drawn from an alternate dataset. During training, the proposed siamese network conducts binary classification via cross-entropy loss. Subsequently, during the testing phase, we directly extract face verification scores from the network's output layer. Experimental results reveal that the proposed unsupervised system delivers a performance on par with a similar but fully supervised baseline.
To combat the potential misuse of Natural Language Generation (NLG) technology, a variety of algorithms have been developed for the detection of AI-generated texts. Traditionally, this task is treated as a binary classification problem. Although supervised learning has demonstrated promising results, acquiring labeled data for detection purposes poses real-world challenges and the risk of overfitting. In an effort to address these issues, we delve into the realm of zero-shot machine-generated text detection. Existing zero-shot detectors, typically designed for specific tasks or topics, often assume uniform testing scenarios, limiting their practicality. In our research, we explore various advanced Large Language Models (LLMs) and their specialized variants, contributing to this field in several ways. In empirical studies, we uncover a significant correlation between topics and detection performance. Secondly, we delve into the influence of topic shifts on zero-shot detectors. These investigations shed light on the adaptability and robustness of these detection methods across diverse topics. The code is available at \url{https://github.com/yfzhang114/robustness-detection}.
Fairness AI aims to detect and alleviate bias across the entire AI development life cycle, encompassing data curation, modeling, evaluation, and deployment-a pivotal aspect of ethical AI implementation. Addressing data bias, particularly concerning sensitive attributes like gender and race, reweighting samples proves efficient for fairness AI. This paper contributes a systematic examination of reweighting samples for traditional machine learning (ML) models, employing five models for binary classification on the Adult Income and COMPUS datasets with various protected attributes. The study evaluates prediction results using five fairness metrics, uncovering the nuanced and model-specific nature of reweighting sample effectiveness in achieving fairness in traditional ML models, as well as revealing the complexity of bias dynamics.
Innovation is a major driver of economic and social development, and information about many kinds of innovation is embedded in semi-structured data from patents and patent applications. Although the impact and novelty of innovations expressed in patent data are difficult to measure through traditional means, ML offers a promising set of techniques for evaluating novelty, summarizing contributions, and embedding semantics. In this paper, we introduce the Harvard USPTO Patent Dataset (HUPD), a large-scale, well-structured, and multi-purpose corpus of English-language patent applications filed to the United States Patent and Trademark Office (USPTO) between 2004 and 2018. With more than 4.5 million patent documents, HUPD is two to three times larger than comparable corpora. Unlike previously proposed patent datasets in NLP, HUPD contains the inventor-submitted versions of patent applications--not the final versions of granted patents--thereby allowing us to study patentability at the time of filing using NLP methods for the first time. It is also novel in its inclusion of rich structured metadata alongside the text of patent filings: By providing each application's metadata along with all of its text fields, the dataset enables researchers to perform new sets of NLP tasks that leverage variation in structured covariates. As a case study on the types of research HUPD makes possible, we introduce a new task to the NLP community--namely, binary classification of patent decisions. We additionally show the structured metadata provided in the dataset enables us to conduct explicit studies of concept shifts for this task. Finally, we demonstrate how HUPD can be used for three additional tasks: multi-class classification of patent subject areas, language modeling, and summarization.
In this article we offer a comprehensive analysis of the Urysohn's classifier in a binary classification context. It utilizes Urysohn's Lemma of Topology to construct separating functions, providing rigorous and adaptable solutions. Numerical experiments demonstrated exceptional performance, with scores ranging from 95% to 100%. Notably, the Urysohn's classifier outperformed CatBoost and KNN in various scenarios. Despite sensitivity to the p-metric parameter, it proved robust and adaptable. The Urysohn's classifier's mathematical rigor and adaptability make it promising for binary classification, with applications in medical diagnosis, fraud detection and cyber security. Future research includes parameter optimization and combining the Urysohn's classifier with other techniques. It offers an elegant and principled approach to classification, ensuring integrity and valuable data insights.
Quantum computing revolutionizes the way of solving complex problems and handling vast datasets, which shows great potential to accelerate the machine learning process. However, data leakage in quantum machine learning (QML) may present privacy risks. Although differential privacy (DP), which protects privacy through the injection of artificial noise, is a well-established approach, its application in the QML domain remains under-explored. In this paper, we propose to harness inherent quantum noises to protect data privacy in QML. Especially, considering the Noisy Intermediate-Scale Quantum (NISQ) devices, we leverage the unavoidable shot noise and incoherent noise in quantum computing to preserve the privacy of QML models for binary classification. We mathematically analyze that the gradient of quantum circuit parameters in QML satisfies a Gaussian distribution, and derive the upper and lower bounds on its variance, which can potentially provide the DP guarantee. Through simulations, we show that a target privacy protection level can be achieved by running the quantum circuit a different number of times.
With such a massive growth in the number of images stored, efficient search in a database has become a crucial endeavor managed by image retrieval systems. Image Retrieval with Relevance Feedback (IRRF) involves iterative human interaction during the retrieval process, yielding more meaningful outcomes. This process can be generally cast as a binary classification problem with only {\it few} labeled samples derived from user feedback. The IRRF task frames a unique few-shot learning characteristics including binary classification of imbalanced and asymmetric classes, all in an open-set regime. In this paper, we study this task through the lens of few-shot learning methods. We propose a new scheme based on a hyper-network, that is tailored to the task and facilitates swift adjustment to user feedback. Our approach's efficacy is validated through comprehensive evaluations on multiple benchmarks and two supplementary tasks, supported by theoretical analysis. We demonstrate the advantage of our model over strong baselines on 4 different datasets in IRRF, addressing also retrieval of images with multiple objects. Furthermore, we show that our method can attain SoTA results in few-shot one-class classification and reach comparable results in binary classification task of few-shot open-set recognition.
Objective: Function is increasingly recognized as an important indicator of whole-person health. This study evaluates the ability of publicly available large language models (LLMs) to accurately identify the presence of functioning information from clinical notes. We explore various strategies to improve the performance on this task. Materials and Methods: We collect a balanced binary classification dataset of 1000 sentences from the Mobility NER dataset, which was curated from n2c2 clinical notes. For evaluation, we construct zero-shot and few-shot prompts to query the LLMs whether a given sentence contains mobility functioning information. Two sampling techniques, random sampling and k-nearest neighbor (kNN)-based sampling, are used to select the few-shot examples. Furthermore, we apply a parameter-efficient prompt-based fine-tuning method to the LLMs and evaluate their performance under various training settings. Results: Flan-T5-xxl outperforms all other models in both zero-shot and few-shot settings, achieving a F1 score of 0.865 with a single demonstrative example selected by kNN sampling. In prompt-based fine-tuning experiments, this foundation model also demonstrates superior performance across all low-resource settings, particularly achieving an impressive F1 score of 0.922 using the full training dataset. The smaller model, Flan-T5-xl, requires fine-tuning with only 2.3M additional parameters to achieve comparable performance to the fully fine-tuned Gatortron-base model, both surpassing 0.9 F1 score. Conclusion: Open-source instruction-tuned LLMs demonstrate impressive in-context learning capability in the mobility functioning classification task. The performance of these models can be further improved by continuing fine-tuning on a task-specific dataset.
Cropland maps are a core and critical component of remote-sensing-based agricultural monitoring, providing dense and up-to-date information about agricultural development. Machine learning is an effective tool for large-scale agricultural mapping, but relies on geo-referenced ground-truth data for model training and testing, which can be scarce or time-consuming to obtain. In this study, we explore the usefulness of combining a global cropland dataset and a hand-labeled dataset to train machine learning models for generating a new cropland map for Nigeria in 2020 at 10 m resolution. We provide the models with pixel-wise time series input data from remote sensing sources such as Sentinel-1 and 2, ERA5 climate data, and DEM data, in addition to binary labels indicating cropland presence. We manually labeled 1827 evenly distributed pixels across Nigeria, splitting them into 50\% training, 25\% validation, and 25\% test sets used to fit the models and test our output map. We evaluate and compare the performance of single- and multi-headed Long Short-Term Memory (LSTM) neural network classifiers, a Random Forest classifier, and three existing 10 m resolution global land cover maps (Google's Dynamic World, ESRI's Land Cover, and ESA's WorldCover) on our proposed test set. Given the regional variations in cropland appearance, we additionally experimented with excluding or sub-setting the global crowd-sourced Geowiki cropland dataset, to empirically assess the trade-off between data quantity and data quality in terms of the similarity to the target data distribution of Nigeria. We find that the existing WorldCover map performs the best with an F1-score of 0.825 and accuracy of 0.870 on the test set, followed by a single-headed LSTM model trained with our hand-labeled training samples and the Geowiki data points in Nigeria, with a F1-score of 0.814 and accuracy of 0.842.
Support vector machines (SVMs) are well-studied supervised learning models for binary classification. In many applications, large amounts of samples can be cheaply and easily obtained. What is often a costly and error-prone process is to manually label these instances. Semi-supervised support vector machines (S3VMs) extend the well-known SVM classifiers to the semi-supervised approach, aiming at maximizing the margin between samples in the presence of unlabeled data. By leveraging both labeled and unlabeled data, S3VMs attempt to achieve better accuracy and robustness compared to traditional SVMs. Unfortunately, the resulting optimization problem is non-convex and hence difficult to solve exactly. In this paper, we present a new branch-and-cut approach for S3VMs using semidefinite programming (SDP) relaxations. We apply optimality-based bound tightening to bound the feasible set. Box constraints allow us to include valid inequalities, strengthening the lower bound. The resulting SDP relaxation provides bounds significantly stronger than the ones available in the literature. For the upper bound, instead, we define a local search exploiting the solution of the SDP relaxation. Computational results highlight the efficiency of the algorithm, showing its capability to solve instances with a number of data points 10 times larger than the ones solved in the literature.
This paper extends our previous method for COVID-19 diagnosis, proposing an enhanced solution for detecting COVID-19 from computed tomography (CT) images. To decrease model misclassifications, two key steps of image processing were employed. Firstly, the uppermost and lowermost slices were removed, preserving sixty percent of each patient's slices. Secondly, all slices underwent manual cropping to emphasize the lung areas. Subsequently, resized CT scans (224 by 224) were input into an Xception transfer learning model. Leveraging Xception's architecture and pre-trained weights, the modified model achieved binary classification. Promising results on the COV19-CT database showcased higher validation accuracy and macro F1 score at both the slice and patient levels compared to our previous solution and alternatives on the same dataset.
Robustness to distribution shift has become a growing concern for text and image models as they transition from research subjects to deployment in the real world. However, high-quality benchmarks for distribution shift in tabular machine learning tasks are still lacking despite the widespread real-world use of tabular data and differences in the models used for tabular data in comparison to text and images. As a consequence, the robustness of tabular models to distribution shift is poorly understood. To address this issue, we introduce TableShift, a distribution shift benchmark for tabular data. TableShift contains 15 binary classification tasks in total, each with an associated shift, and includes a diverse set of data sources, prediction targets, and distribution shifts. The benchmark covers domains including finance, education, public policy, healthcare, and civic participation, and is accessible using only a few lines of Python code via the TableShift API. We conduct a large-scale study comparing several state-of-the-art tabular data models alongside robust learning and domain generalization methods on the benchmark tasks. Our study demonstrates (1) a linear trend between in-distribution (ID) and out-of-distribution (OOD) accuracy; (2) domain robustness methods can reduce shift gaps but at the cost of reduced ID accuracy; (3) a strong relationship between shift gap (difference between ID and OOD performance) and shifts in the label distribution. The benchmark data, Python package, model implementations, and more information about TableShift are available at https://github.com/mlfoundations/tableshift and https://tableshift.org .
Objective: To develop a high-throughput biomedical relation extraction system that takes advantage of the large language models'(LLMs) reading comprehension ability and biomedical world knowledge in a scalable and evidential manner. Methods: We formulate the relation extraction task as binary classifications for large language models. Specifically, LLMs make the decision based on the external corpus and its world knowledge, giving the reason for the judgment for factual verification. This method is tailored for semi-structured web articles, wherein we designate the main title as the tail entity and explicitly incorporate it into the context, and the potential head entities are matched based on a biomedical thesaurus. Moreover, lengthy contents are sliced into text chunks, embedded, and retrieved with additional embedding models. Results: Using an open-source LLM, we extracted 248659 relation triplets of three distinct relation types from three reputable biomedical websites. To assess the efficacy of the basic pipeline employed for biomedical relation extraction, we curated a benchmark dataset annotated by a medical expert. Evaluation results indicate that the pipeline exhibits performance comparable to that of GPT-4. Case studies further illuminate challenges faced by contemporary LLMs in the context of biomedical relation extraction for semi-structured web articles. Conclusion: The proposed method has demonstrated its effectiveness in leveraging the strengths of LLMs for high-throughput biomedical relation extraction. Its adaptability is evident, as it can be seamlessly extended to diverse semi-structured biomedical websites, facilitating the extraction of various types of biomedical relations with ease.
The standard theory of optimal stopping is based on the idealised assumption that the underlying process is essentially known. In this paper, we drop this restriction and study data-driven optimal stopping for a general diffusion process, focusing on investigating the statistical performance of the proposed estimator of the optimal stopping barrier. More specifically, we derive non-asymptotic upper bounds on the simple regret, along with uniform and non-asymptotic PAC bounds. Minimax optimality is verified by completing the upper bound results with matching lower bounds on the simple regret. All results are shown both under general conditions on the payoff functions and under more refined assumptions that mimic the margin condition used in binary classification, leading to an improved rate of convergence. Additionally, we investigate how our results on the simple regret transfer to the cumulative regret for a specific exploration-exploitation strategy, both with respect to lower bounds and upper bounds.
This paper proposes the use of causal modeling to detect and mitigate algorithmic bias that is nonlinear in the protected attribute. We provide a general overview of our approach. We use the German Credit data set, which is available for download from the UC Irvine Machine Learning Repository, to develop (1) a prediction model, which is treated as a black box, and (2) a causal model for bias mitigation. In this paper, we focus on age bias and the problem of binary classification. We show that the probability of getting correctly classified as "low risk" is lowest among young people. The probability increases with age nonlinearly. To incorporate the nonlinearity into the causal model, we introduce a higher order polynomial term. Based on the fitted causal model, the de-biased probability estimates are computed, showing improved fairness with little impact on overall classification accuracy. Causal modeling is intuitive and, hence, its use can enhance explicability and promotes trust among different stakeholders of AI.
Support Vector Machine (SVM) stands out as a prominent machine learning technique widely applied in practical pattern recognition tasks. It achieves binary classification by maximizing the "margin", which represents the minimum distance between instances and the decision boundary. Although many efforts have been dedicated to expanding SVM for multi-class case through strategies such as one versus one and one versus the rest, satisfactory solutions remain to be developed. In this paper, we propose a novel method for multi-class SVM that incorporates pairwise class loss considerations and maximizes the minimum margin. Adhering to this concept, we embrace a new formulation that imparts heightened flexibility to multi-class SVM. Furthermore, the correlations between the proposed method and multiple forms of multi-class SVM are analyzed. The proposed regularizer, akin to the concept of "margin", can serve as a seamless enhancement over the softmax in deep learning, providing guidance for network parameter learning. Empirical evaluations demonstrate the effectiveness and superiority of our proposed method over existing multi-classification methods.Code is available at https://github.com/zz-haooo/M3SVM.
While machine learning (ML) includes a valuable array of tools for analyzing biomedical data, significant time and expertise is required to assemble effective, rigorous, and unbiased pipelines. Automated ML (AutoML) tools seek to facilitate ML application by automating a subset of analysis pipeline elements. In this study we develop and validate a Simple, Transparent, End-to-end Automated Machine Learning Pipeline (STREAMLINE) and apply it to investigate the added utility of photography-based phenotypes for predicting obstructive sleep apnea (OSA); a common and underdiagnosed condition associated with a variety of health, economic, and safety consequences. STREAMLINE is designed to tackle biomedical binary classification tasks while adhering to best practices and accommodating complexity, scalability, reproducibility, customization, and model interpretation. Benchmarking analyses validated the efficacy of STREAMLINE across data simulations with increasingly complex patterns of association. Then we applied STREAMLINE to evaluate the utility of demographics (DEM), self-reported comorbidities (DX), symptoms (SYM), and photography-based craniofacial (CF) and intraoral (IO) anatomy measures in predicting any OSA or moderate/severe OSA using 3,111 participants from Sleep Apnea Global Interdisciplinary Consortium (SAGIC). OSA analyses identified a significant increase in ROC-AUC when adding CF to DEM+DX+SYM to predict moderate/severe OSA. A consistent but non-significant increase in PRC-AUC was observed with the addition of each subsequent feature set to predict any OSA, with CF and IO yielding minimal improvements. Application of STREAMLINE to OSA data suggests that CF features provide additional value in predicting moderate/severe OSA, but neither CF nor IO features meaningfully improved the prediction of any OSA beyond established demographics, comorbidity and symptom characteristics.