Cardiovascular disease (CVD) remains a leading global health burden, with carotid intima-media thickness (cIMT) recognized as a sensitive, non-invasive biomarker for early atherosclerosis and future cardiovascular risk. Although ultrasound imaging is the standard method for measuring cIMT, its accessibility may be limited in large-scale populations with intensive screening demands or in low-resource settings, posing a significant challenge for stroke survivors who have a high need for CVD assessment. While existing cIMT prediction models based solely on tabular data have been proposed to bypass the need for strong reliance on image-derived features, they typically frame the task as a binary classification problem, indicating only the presence or absence of vascular risk, thereby failing to effectively capture its actual severity. In contrast, this work proposes a prognostic learning model to effectively estimate cIMT, enabling precise quantification of atherosclerosis severity without relying on imaging data. By constructing a patient similarity graph relying on demographic and clinical-derived features to (i) bypass the need for revealing the actual clinical measurements, promoting privacy, and (ii) to explicitly account for patient's interdependencies, this work introduces a graph-guided self-supervised learning (Self-SL) framework to learn informative representations for the cIMT prediction task. These learned representations encode key local and global graph information that can readily assist the downstream task requiring only a minimal amount of labeled data. Applied to the UK Biobank cohort, the model outperforms conventional learning models, achieving up to 93.22% average MSE reduction, underscoring graph similarity strength in capturing latent clinical patterns.

The advent of diverse frequency bands in 5G networks has promoted measurement studies focused on 5G signal propagation, aiming to understand its pathloss, coverage, and channel quality characteristics. Nonetheless, conducting a thorough 5G measurement campaign is markedly laborious given the large number of samples that must be collected. To alleviate this burden, the present contribution leverages principled active learning (AL) methods to prudently select only a few, yet most informative locations to collect samples. The core idea is to rely on a Gaussian Process (GP) model to efficiently extrapolate measurements throughout the coverage area. Specifically, an ensemble (E) of GP models is adopted that not only provides a rich learning function space, but also quantifies uncertainty, and can offer accurate predictions. Building on this EGP model, a suite of acquisition functions (AFs) are advocated to query new locations on-the-fly. To account for realistic scenaria, the proposed AFs are augmented with a novel distance-based AL rule that selects informative samples, while penalizing queries at long distances. Numerical tests on 5G data generated by the Sionna simulator and on real urban and suburban datasets, showcase the merits of the novel EGP-AL approaches.

Cardiovascular disease (CVD) poses a significant global health challenge, and accurate inference methods are vital for early detection and intervention. However, the quality of prediction relies heavily on the availability of labeled data, which are often limited in medical applications. To cope with the challenge of limited labeled data, we are the first to propose an active learning (AL) approach that leverages a weighted ensemble of Gaussian processes to effectively infer CVD by strategically selecting the few most informative data points to label. Through experiments conducted on the SMARTool dataset, we demonstrate the effectiveness of the advocated approach, achieving superior performance in CVD inference compared to baseline methods. Our findings highlight the potential impact of the proposed AL framework in CVD diagnosis and treatment clinical cases, particularly in scenarios where labeled data are scarce, due to data confidentiality concerns or high sampling costs.

Graph-based inference arises in a gamut of network science-related applications, including smart transportation, climate forecasting, and neuroscience. Given observations over a subset of the nodes due to sampling costs or privacy considerations, extrapolation of time-varying signals over the unobserved nodes can be realized by leveraging their spatio-temporal correlations across the graph. Building on a recently proposed Gaussian process (GP) auto-regressive model to capture spatio-temporal dynamics across slots, the present work further pursues an adaptive framework by ensembling a candidate set of such dynamical models, each representing a unique dynamic pattern of the sought process. With nodal observation arriving on-the-fly, the proposed method simultaneously estimates the missing nodal values and selects the fitted dynamical model via data-adaptive weights. Tests with real data showcase the merits of the proposed method.

Optimizing a black-box function that is expensive to evaluate emerges in a gamut of machine learning and artificial intelligence applications including drug discovery, policy optimization in robotics, and hyperparameter tuning of learning models to list a few. Bayesian optimization (BO) provides a principled framework to find the global optimum of such functions using a limited number of function evaluations. BO relies on a statistical surrogate model to actively select new query points, that is typically captured by a Gaussian process (GP). Unlike most existing approaches that hinge on a single GP surrogate model with a pre-selected kernel function that may confine the expressiveness of the sought function especially under the limited evaluation budget, the present work puts forth a weighted ensemble of GPs as a surrogate model. Building on the advocated Gaussian mixture (GM) posterior, the EGP framework adapts to the most fitted surrogate model as data arrive on-the-fly, offering a richer function space. For the acquisition of next evaluation points, the EGP-based posterior is coupled with an adaptive expected improvement (EI) criterion to balance exploration and exploitation of the search space. Numerical tests on a set of benchmark synthetic functions and two robotic tasks, demonstrate the impressive benefits of the proposed approach.

Assessing set-membership and evaluating distances to the related set boundary are problems of widespread interest, and can often be computationally challenging. Seeking efficient learning models for such tasks, this paper deals with voltage stability margin prediction for power systems. Supervised training of such models is conventionally hard due to high-dimensional feature space, and a cumbersome label-generation process. Nevertheless, one may find related easy auxiliary tasks, such as voltage stability verification, that can aid in training for the hard task. This paper develops a novel approach for such settings by leveraging transfer learning. A Gaussian process-based learning model is efficiently trained using learning- and physics-based auxiliary tasks. Numerical tests demonstrate markedly improved performance that is harnessed alongside the benefit of uncertainty quantification to suit the needs of the considered application.

Bayesian optimization (BO) has well-documented merits for optimizing black-box functions with an expensive evaluation cost. Such functions emerge in applications as diverse as hyperparameter tuning, drug discovery, and robotics. BO hinges on a Bayesian surrogate model to sequentially select query points so as to balance exploration with exploitation of the search space. Most existing works rely on a single Gaussian process (GP) based surrogate model, where the kernel function form is typically preselected using domain knowledge. To bypass such a design process, this paper leverages an ensemble (E) of GPs to adaptively select the surrogate model fit on-the-fly, yielding a GP mixture posterior with enhanced expressiveness for the sought function. Acquisition of the next evaluation input using this EGP-based function posterior is then enabled by Thompson sampling (TS) that requires no additional design parameters. To endow function sampling with scalability, random feature-based kernel approximation is leveraged per GP model. The novel EGP-TS readily accommodates parallel operation. To further establish convergence of the proposed EGP-TS to the global optimum, analysis is conducted based on the notion of Bayesian regret for both sequential and parallel settings. Tests on synthetic functions and real-world applications showcase the merits of the proposed method.

Graph-guided semi-supervised learning (SSL) is a major task emerging in a gamut of network science applications. However, most SSL approaches rely on deterministic similarity metrics for prediction, thus providing only point estimates of the sought function. To allow for uncertainty quantification, which is of utmost importance in safety-critical applications, this work tackles the SSL task in a Gaussian process (GP) based Bayesian framework to propagate the distribution of nonparametric function estimates. Specifically, an incremental learning scenario is considered, where prediction of the desired value of a new node per iteration is followed by processing the corresponding nodal observation. Capitalizing on random features for scalability, an ensemble of GP experts is employed, each associated with a unique kernel from a known dictionary, to choose the fitted kernel combination in a graph- and data-adaptive fashion, thus bypassing the need for offline model training. Experiments with synthetic and real data showcase the merits of the proposed approach.