Search

Improving operational safety and efficiency of variable speed limit (VSL) systems are the two core control objectives at work zone areas. In response to such need, this study presents a proactive VSL control model for freeway work zone operations. The proposed model uses an embedded macroscopic traffic flow model to predict the traffic state evolutions over the projected time horizon and to determine the optimal speed limits. In addition, Kalman filter is adopted to correct the prediction inaccuracy in a timely manner. To improve the safety of operations, this study proposes a new control objective function to smooth speed transition along the target freeway sketch by minimizing the difference between actual speeds and ideal speeds. Also, the smoothness of speed transition can help prevent the formation of shockwave and consequently enhance system's operational efficiency. The authors' numerical experiment with a calibrated Verkehr In Städten-SIMulationsmodell (VISSIM) simulator reveals that the proposed VSL system can significantly reduce the speed variance among different freeway subsegments. The evaluation of several measures of effectiveness (MOEs) also shows the promising results of the VSL system on the improvement of freeway operational efficiency. [ABSTRACT FROM AUTHOR]

This study presents two models for proactive variable speed limit (VSL) control on a recurrently congested freeway segment. The proposed model uses embedded traffic flow relations to predict the evolution of congestion patterns over the projected time horizon, and then computes the time-varying optimal speed limit to smooth traffic flows. To contend with the uncertainties associated with drivers' responses to VSL control, this study has also proposed an advanced model that further adopts Kalman Filter to enhance the traffic state estimation. Both models have been investigated with two control objectives-travel time minimization and speed variance minimization. Our extensive simulation analysis with a VISSIM simulator, calibrated with field data from our previous VSL field demonstration, has revealed the benefits of the proposed VSL control models. Also, the experimental results indicated that the proposed advanced models with both control objectives can significantly reduce the travel time over the recurrent bottleneck locations. With respect to several selected measure of effectiveness (MOEs), such as average number of stops and average travel time, the research results confirm that the control models with the objective of minimizing speed variance can offer the promising properties for field implementation. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Online businesses and websites have recently become the main target of fake reviews, where fake reviews are intentionally composed to manipulate the business ratings positively or negatively. Most of existing works to detect fake reviews are supervised methods, whose performance highly depends on the amount, quality, and variety of the labeled data, which are often non-trivial to obtain in practice. In this paper, we propose a semi-supervised label sparsity-tolerant framework, LENS, for fake review detection by mining spatial knowledge and learning distributions of embedded topics. LENS builds on two key observations. (1) Spatial knowledge revealed in spatial entities and their co-occurring latent topic distributions may indicate the review authenticity. (2) Distributions of the embedded topics (the contextual distribution) may exhibit important patterns to differentiate between real and fake reviews. Specifically, LENS first extracts embeddings for spatial named entities using a knowledge base trained from Wikipedia webpages. Second, LENS represents each input token as a distribution over the learned latent topics in the embedded topic space. To bypass the differentiation difficulty, LENS builds on two discriminators in the actor-critic architecture using reinforcement learning. Extensive experiments using the real-world spatial and non-spatial datasets show that LENS consistently outperformed the state-of-the-art semi-supervised fake review detection methods on few labels at all different labeling rates for real and fake reviews, respectively, in a label-starving setting. [ABSTRACT FROM AUTHOR]

A total of 133 Salmonella isolates recovered from retail meats purchased in the United States and the People's Republic of China were assayed for antimicrobial susceptibility, the presence of integrons and antimicrobial resistance genes, and horizontal transfer of characterized antimicrobial resistance determinants via conjugation. Seventy-three (82%) of these Salmonella isolates were resistant to at least one antimicrobial agent. Resistance to the following antibiotics was common among the United States isolates: tetracycline (68% of the isolates were resistant), streptomycin (61%), sulfamethoxazole (42%), and ampicillin (29%). Eight Salmonella isolates (6%) were resistant to ceftriaxone. Fourteen isolates (11%) from the People's Republic of China were resistant to nalidixic acid and displayed decreased susceptibility to ciprofloxacin. A total of 19 different antimicrobial resistance genes were identified in 30 multidrug-resistant Salmonella isolates. The bla[sub CMY-2] gene, encoding a class A AmpC β-lactamase, was detected in all 10 Salmonella isolates resistant to extended-spectrum β-lactams. Resistance to ampicillin was most often associated with a TEM-1 family β-lactamase gene. Six aminoglycoside resistance genes, aadA1, aadA2, aacC2, Kn, aph(3)-Ila, and aac(3)-IVa, were commonly present in the Salmonella isolates. Sixteen (54%) of 30 Salmonella isolates tested had integrons ranging in size from 0.75 to 2.7 kb. Conjugation studies demonstrated that there was plasmid-mediated transfer of genes encoding CMY-2 and TEM-1-like β-lactamases. These data indicate that Salmonella isolates recovered from retail raw meats are commonly resistant to multiple antimicrobials, including those used for treating salmonellosis, such as ceftriaxone. Genes conferring antimicrobial resistance in Salmonella are often carried on integrons and plasmids and could be transmitted through conjugation. These mobile DNA elements have likely played an important role in transmission and dissemination of antimicrobial resistance determinants among Salmonella strains. [ABSTRACT FROM AUTHOR]

Current neuroimaging studies frequently use complex machine learning models to classify human fMRI data, distinguishing healthy and disordered brains, often to validate new methods or enhance prediction accuracy. Yet, where prediction accuracy is a concern, our results suggest that precision in prediction does not always require such sophistication. When a classifier as simple as logistic regression is applied to feature-engineered fMRI data, it can match or even outperform more sophisticated recent models. Classification of the raw time series fMRI data generally benefits from complex parameter-rich models. However, this complexity often pushes them into the class of black-box models. Yet, we found that a relatively simple model can consistently outperform much more complex classifiers in both accuracy and speed. This model applies the same multi-layer perceptron repeatedly across time and averages the results. Thus, the complexity and black-box nature of the parameter rich models, often perceived as a necessary trade-off for higher performance, do not invariably yield superior results on fMRI. Given the success of straightforward approaches, we challenge the merit of research that concentrates solely on complex model development driven by classification. Instead, we advocate for increased focus on designing models that prioritize the explainability of fMRI data or pursue applicable objectives beyond mere classification accuracy, unless they significantly outperform logistic regression or our proposed model. To validate our claim, we explore possible reasons for the superior performance of our straightforward model by examining the innate characteristics of fMRI time series data. Our findings suggest that the sequential information hidden in the temporal order may be far less important for the accurate fMRI classification than the stand-alone pieces of information scattered across the frames of the time series., Competing Interests: Declaration of competing interest The authors declare no conflicts of interest or competing interests., (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)

The MRI-derived brain network serves as a pivotal instrument in elucidating both the structural and functional aspects of the brain, encompassing the ramifications of diseases and developmental processes. However, prevailing methodologies, often focusing on synchronous BOLD signals from functional MRI (fMRI), may not capture directional influences among brain regions and rarely tackle temporal functional dynamics. In this study, we first construct the brain-effective network via the dynamic causal model. Subsequently, we introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE). This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic inter-play between structural and effective networks via an ordinary differential equation (ODE) model, which characterizes spatial-temporal brain dynamics. Our framework is validated on several clinical phenotype prediction tasks using two independent publicly available datasets (HCP and OASIS). The experimental results clearly demonstrate the advantages of our model compared to several state-of-the-art methods.

Computational drug repositioning, through predicting drug-disease associations (DDA), offers significant potential for discovering new drug indications. Current methods incorporate graph neural networks (GNN) on drug-disease heterogeneous networks to predict DDAs, achieving notable performances compared to traditional machine learning and matrix factorization approaches. However, these methods depend heavily on network topology, hampered by incomplete and noisy network data, and overlook the wealth of biomedical knowledge available. Correspondingly, large language models (LLMs) excel in graph search and relational reasoning, which can possibly enhance the integration of comprehensive biomedical knowledge into drug and disease profiles. In this study, we first investigate the contribution of LLM-inferred knowledge representation in drug repositioning and DDA prediction. A zero-shot prompting template was designed for LLM to extract high-quality knowledge descriptions for drug and disease entities, followed by embedding generation from language models to transform the discrete text to continual numerical representation. Then, we proposed LLM-DDA with three different model architectures (LLM-DDA Node Feat , LLM-DDA Dual GNN , LLM-DDA GNN-AE ) to investigate the best fusion mode for LLM-based embeddings. Extensive experiments on four DDA benchmarks show that, LLM-DDA GNN-AE achieved the optimal performance compared to 11 baselines with the overall relative improvement in AUPR of 23.22%, F1-Score of 17.20%, and precision of 25.35%. Meanwhile, selected case studies of involving Prednisone and Allergic Rhinitis highlighted the model's capability to identify reliable DDAs and knowledge descriptions, supported by existing literature. This study showcases the utility of LLMs in drug repositioning with its generality and applicability in other biomedical relation prediction tasks., (© 2024. International Association of Scientists in the Interdisciplinary Areas.)

Recent advancements in neuroimaging techniques have sparked a growing interest in understanding the complex interactions between anatomical regions of interest (ROIs), forming into brain networks that play a crucial role in various clinical tasks, such as neural pattern discovery and disorder diagnosis. In recent years, graph neural networks (GNNs) have emerged as powerful tools for analyzing network data. However, due to the complexity of data acquisition and regulatory restrictions, brain network studies remain limited in scale and are often confined to local institutions. These limitations greatly challenge GNN models to capture useful neural circuitry patterns and deliver robust downstream performance. As a distributed machine learning paradigm, federated learning (FL) provides a promising solution in addressing resource limitation and privacy concerns, by enabling collaborative learning across local institutions (i.e., clients) without data sharing. While the data heterogeneity issues have been extensively studied in recent FL literature, cross-institutional brain network analysis presents unique data heterogeneity challenges, that is, the inconsistent ROI parcellation systems and varying predictive neural circuitry patterns across local neuroimaging studies. To this end, we propose FedBrain, a GNN-based personalized FL framework that takes into account the unique properties of brain network data. Specifically, we present a federated atlas mapping mechanism to overcome the feature and structure heterogeneity of brain networks arising from different ROI atlas systems, and a clustering approach guided by clinical prior knowledge to address varying predictive neural circuitry patterns regarding different patient groups, neuroimaging modalities and clinical outcomes. Compared to existing FL strategies, our approach demonstrates superior and more consistent performance, showcasing its strong potential and generalizability in cross-institutional connectome-based brain imaging analysis. The implementation is available here.

Functional brain networks represent dynamic and complex interactions among anatomical regions of interest (ROIs), providing crucial clinical insights for neural pattern discovery and disorder diagnosis. In recent years, graph neural networks (GNNs) have proven immense success and effectiveness in analyzing structured network data. However, due to the high complexity of data acquisition, resulting in limited training resources of neuroimaging data, GNNs, like all deep learning models, suffer from overfitting. Moreover, their capability to capture useful neural patterns for downstream prediction is also adversely affected. To address such challenge, this study proposes BrainSTEAM, an integrated framework featuring a spatio-temporal module that consists of an EdgeConv GNN model, an autoencoder network, and a Mixup strategy. In particular, the spatio-temporal module aims to dynamically segment the time series signals of the ROI features for each subject into chunked sequences. We leverage each sequence to construct correlation networks, thereby increasing the training data. Additionally, we employ the EdgeConv GNN to capture ROI connectivity structures, an autoencoder for data denoising, and mixup for enhancing model training through linear data augmentation. We evaluate our framework on two real-world neuroimaging datasets, ABIDE for Autism prediction and HCP for gender prediction. Extensive experiments demonstrate the superiority and robustness of BrainSTEAM when compared to a variety of existing models, showcasing the strong potential of our proposed mechanisms in generalizing to other studies for connectome-based fMRI analysis.

Pre-training on graph neural networks (GNNs) aims to learn transferable knowledge for downstream tasks with unlabeled data, and it has recently become an active research area. The success of graph pre-training models is often attributed to the massive amount of input data. In this paper, however, we identify the curse of big data phenomenon in graph pre-training: more training data do not necessarily lead to better downstream performance. Motivated by this observation, we propose a better-with-less framework for graph pre-training: fewer, but carefully chosen data are fed into a GNN model to enhance pre-training. The proposed pre-training pipeline is called the data-active graph pre-training (APT) framework, and is composed of a graph selector and a pre-training model. The graph selector chooses the most representative and instructive data points based on the inherent properties of graphs as well as predictive uncertainty . The proposed predictive uncertainty, as feedback from the pre-training model, measures the confidence level of the model in the data. When fed with the chosen data, on the other hand, the pre-training model grasps an initial understanding of the new, unseen data, and at the same time attempts to remember the knowledge learned from previous data. Therefore, the integration and interaction between these two components form a unified framework (APT), in which graph pre-training is performed in a progressive and iterative way. Experiment results show that the proposed APT is able to obtain an efficient pre-training model with fewer training data and better downstream performance.

Graphs are widely used to model interconnected entities and improve downstream predictions in various real-world applications. However, real-world graphs nowadays are often associated with complex attributes on multiple types of nodes and even links that are hard to model uniformly, while the widely used graph neural networks (GNNs) often require sufficient training toward specific downstream predictions to achieve strong performance. In this work, we take a fundamentally different approach than GNNs, to simultaneously achieve deep joint modeling of complex attributes and flexible structures of real-world graphs and obtain unsupervised generic graph representations that are not limited to specific downstream predictions. Our framework, built on a natural integration of language models (LMs) and random walks (RWs), is straightforward, powerful and data-efficient. Specifically, we first perform attributed RWs on the graph and design an automated program to compose roughly meaningful textual sequences directly from the attributed RWs; then we fine-tune an LM using the RW-based textual sequences and extract embedding vectors from the LM, which encapsulates both attribute semantics and graph structures. In our experiments, we evaluate the learned node embeddings towards different downstream prediction tasks on multiple real-world attributed graph datasets and observe significant improvements over a comprehensive set of state-of-the-art unsupervised node embedding methods. We believe this work opens a door for more sophisticated technical designs and empirical evaluations toward the leverage of LMs for the modeling of real-world graphs.

Images contain rich relational knowledge that can help machines understand the world. Existing methods on visual knowledge extraction often rely on the pre-defined format (e.g., sub-verb-obj tuples) or vocabulary (e.g., relation types), restricting the expressiveness of the extracted knowledge. In this work, we take a first exploration to a new paradigm of open visual knowledge extraction. To achieve this, we present OpenVik which consists of an open relational region detector to detect regions potentially containing relational knowledge and a visual knowledge generator that generates format-free knowledge by prompting the large multimodality model with the detected region of interest. We also explore two data enhancement techniques for diversifying the generated format-free visual knowledge. Extensive knowledge quality evaluations highlight the correctness and uniqueness of the extracted open visual knowledge by OpenVik. Moreover, integrating our extracted knowledge across various visual reasoning applications shows consistent improvements, indicating the real-world applicability of OpenVik.

Personalized diagnosis prediction based on electronic health records (EHR) of patients is a promising yet challenging task for AI in healthcare. Existing studies typically ignore the heterogeneity of diseases across different patients. For example, diabetes can have different complications across different patients (e.g., hyperlipidemia and circulatory disorder), which requires personalized diagnoses and treatments. Specifically, existing models fail to consider 1) varying severity of the same diseases for different patients, 2) complex interactions among syndromic diseases, and 3) dynamic progression of chronic diseases. In this work, we propose to perform personalized diagnosis prediction based on EHR data via capturing disease severity, interaction, and progression. In particular, we enable personalized disease representations via severity-driven embeddings at the disease level. Then, at the visit level, we propose to capture higher-order interactions among diseases that can collectively affect patients' health status via hypergraph-based aggregation; at the patient level, we devise a personalized generative model based on neural ordinary differential equations to capture the continuous-time disease progressions underlying discrete and incomplete visits. Extensive experiments on two real-world EHR datasets show significant performance gains brought by our approach, yielding average improvements of 10.70% for diagnosis prediction over state-of-the-art competitors.

Biological networks are commonly used in biomedical and healthcare domains to effectively model the structure of complex biological systems with interactions linking biological entities. However, due to their characteristics of high dimensionality and low sample size, directly applying deep learning models on biological networks usually faces severe overfitting. In this work, we propose R-Mixup, a Mixup-based data augmentation technique that suits the symmetric positive definite (SPD) property of adjacency matrices from biological networks with optimized training efficiency. The interpolation process in R-Mixup leverages the log-Euclidean distance metrics from the Riemannian manifold, effectively addressing the swelling effect and arbitrarily incorrect label issues of vanilla Mixup. We demonstrate the effectiveness of R-Mixup with five real-world biological network datasets on both regression and classification tasks. Besides, we derive a commonly ignored necessary condition for identifying the SPD matrices of biological networks and empirically study its influence on the model performance. The code implementation can be found in Appendix E.

Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain. In the graph mining domain, a similar analogy can be drawn for pre-training graph models on large graphs in the hope of benefiting downstream graph applications, which has also been explored by several recent studies. However, no existing study has ever investigated the pre-training of text plus graph models on large heterogeneous graphs with abundant textual information (a.k.a. large graph corpora) and then fine-tuning the model on different related downstream applications with different graph schemas. To address this problem, we propose a framework of graph-aware language model pre-training (GaLM) on a large graph corpus, which incorporates large language models and graph neural networks, and a variety of fine-tuning methods on downstream applications. We conduct extensive experiments on Amazon's real internal datasets and large public datasets. Comprehensive empirical results and in-depth analysis demonstrate the effectiveness of our proposed methods along with lessons learned.

In recent years, graph pre-training has gained significant attention, focusing on acquiring transferable knowledge from unlabeled graph data to improve downstream performance. Despite these recent endeavors, the problem of negative transfer remains a major concern when utilizing graph pre-trained models to downstream tasks. Previous studies made great efforts on the issue of what to pre-train and how to pre-train by designing a variety of graph pre-training and fine-tuning strategies. However, there are cases where even the most advanced "pre-train and fine-tune" paradigms fail to yield distinct benefits. This paper introduces a generic framework W2PGNN to answer the crucial question of when to pre-train ( i.e ., in what situations could we take advantage of graph pre-training) before performing effortful pre-training or fine-tuning. We start from a new perspective to explore the complex generative mechanisms from the pre-training data to downstream data. In particular, W2PGNN first fits the pre-training data into graphon bases, each element of graphon basis ( i.e ., a graphon) identifies a fundamental transferable pattern shared by a collection of pre-training graphs. All convex combinations of graphon bases give rise to a generator space, from which graphs generated form the solution space for those downstream data that can benefit from pre-training. In this manner, the feasibility of pre-training can be quantified as the generation probability of the downstream data from any generator in the generator space. W2PGNN offers three broad applications: providing the application scope of graph pre-trained models, quantifying the feasibility of pre-training, and assistance in selecting pre-training data to enhance downstream performance. We provide a theoretically sound solution for the first application and extensive empirical justifications for the latter two applications.

The complex systems in the real-world are commonly associated with multiple types of objects and relations, and heterogeneous graphs are ubiquitous data structures that can inherently represent multi-modal interactions between objects. Generating high-quality heterogeneous graphs allows us to understand the implicit distribution of heterogeneous graphs and provides benchmarks for downstream heterogeneous representation learning tasks. Existing works are limited to either merely generating the graph topology with neglecting local semantic information or only generating the graph without preserving the higher-order structural information and the global heterogeneous distribution in generated graphs. To this end, we formulate a general, end-to-end framework - HGEN for generating novel heterogeneous graphs with a newly proposed heterogeneous walk generator. On top of HGEN, we further develop a network motif generator to better characterize the higher-order structural distribution. A novel heterogeneous graph assembler is further developed to adaptively assemble novel heterogeneous graphs from the generated heterogeneous walks and motifs in a stratified manner. The extended model is proven to preserve the local semantic and heterogeneous global distribution of observed graphs with the theoretical guarantee. Lastly, comprehensive experiments on both synthetic and real-world practical datasets demonstrate the power and efficiency of the proposed method.

Scientific document classification is a critical task for a wide range of applications, but the cost of collecting human-labeled data can be prohibitive. We study scientific document classification using label names only. In scientific domains, label names often include domain-specific concepts that may not appear in the document corpus, making it difficult to match labels and documents precisely. To tackle this issue, we propose WanDeR, which leverages dense retrieval to perform matching in the embedding space to capture the semantics of label names. We further design the label name expansion module to enrich its representations. Lastly, a self-training step is used to refine the predictions. The experiments on three datasets show that WanDeR outperforms the best baseline by 11.9%. Our code will be published at https://github.com/ritaranx/wander.

Medical decision-making processes can be enhanced by comprehensive biomedical knowledge bases, which require fusing knowledge graphs constructed from different sources via a uniform index system. The index system often organizes biomedical terms in a hierarchy to provide the aligned entities with fine-grained granularity. To address the challenge of scarce supervision in the biomedical knowledge fusion (BKF) task, researchers have proposed various unsupervised methods. However, these methods heavily rely on ad-hoc lexical and structural matching algorithms, which fail to capture the rich semantics conveyed by biomedical entities and terms. Recently, neural embedding models have proved effective in semantic-rich tasks, but they rely on sufficient labeled data to be adequately trained. To bridge the gap between the scarce-labeled BKF and neural embedding models, we propose HiPrompt, a supervision-efficient knowledge fusion framework that elicits the few-shot reasoning ability of large language models through hierarchy-oriented prompts. Empirical results on the collected KG-Hi-BKF benchmark datasets demonstrate the effectiveness of HiPrompt.

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one drawback of self-training is that it is vulnerable to the label noise from incorrect pseudo labels. Inspired by the fact that samples with similar labels tend to share similar representations, we develop a neighborhood-based sample selection approach to tackle the issue of noisy pseudo labels. We further stabilize self-training via aggregating the predictions from different rounds during sample selection. Experiments on eight tasks show that our proposed method outperforms the strongest self-training baseline with 1.83% and 2.51% performance gain for text and graph datasets on average. Our further analysis demonstrates that our proposed data selection strategy reduces the noise of pseudo labels by 36.8% and saves 57.3% of the time when compared with the best baseline. Our code and appendices will be uploaded to https://github.com/ritaranx/NeST.

Electronic health records (EHR) data contain rich information about patients' health conditions including diagnosis, procedures, medications and etc., which have been widely used to facilitate digital medicine. Despite its importance, it is often non-trivial to learn useful representations for patients' visits that support downstream clinical predictions, as each visit contains massive and diverse medical codes. As a result, the complex interactions among medical codes are often not captured, which leads to substandard predictions. To better model these complex relations, we leverage hypergraphs, which go beyond pairwise relations to jointly learn the representations for visits and medical codes. We also propose to use the self-attention mechanism to automatically identify the most relevant medical codes for each visit based on the downstream clinical predictions with better generalization power. Experiments on two EHR datasets show that our proposed method not only yields superior performance, but also provides reasonable insights towards the target tasks., (©2023 AMIA - All rights reserved.)

The utilization of web search activity for pandemic forecasting has significant implications for managing disease spread and informing policy decisions. However, web search records tend to be noisy and influenced by geographical location, making it difficult to develop large-scale models. While regularized linear models have been effective in predicting the spread of respiratory illnesses like COVID-19, they are limited to specific locations. The lack of incorporation of neighboring areas' data and the inability to transfer models to new locations with limited data has impeded further progress. To address these limitations, this study proposes a novel self-supervised message-passing neural network (SMPNN) framework for modeling local and cross-location dynamics in pandemic forecasting. The SMPNN framework utilizes an MPNN module to learn cross-location dependencies through self-supervised learning and improve local predictions with graph-generated features. The framework is designed as an end-to-end solution and is compared with state-of-the-art statistical and deep learning models using COVID-19 data from England and the US. The results of the study demonstrate that the SMPNN model outperforms other models by achieving up to a 6.9% improvement in prediction accuracy and lower prediction errors during the early stages of disease outbreaks. This approach represents a significant advancement in disease surveillance and forecasting, providing a novel methodology, datasets, and insights that combine web search data and spatial information. The proposed SMPNN framework offers a promising avenue for modeling the spread of pandemics, leveraging both local and cross-location information, and has the potential to inform public health policy decisions.

Functional magnetic resonance imaging (fMRI) has become one of the most common imaging modalities for brain function analysis. Recently, graph neural networks (GNN) have been adopted for fMRI analysis with superior performance. Unfortunately, traditional functional brain networks are mainly constructed based on similarities among region of interests (ROIs), which are noisy and can lead to inferior results for GNN models. To better adapt GNNs for fMRI analysis, we propose DABNet, a D eep D A G learning framework based on B rain Net works for fMRI analysis. DABNet adopts a brain network generator module, which harnesses the DAG learning approach to transform the raw time-series into effective brain connectivities. Experiments on two fMRI datasets demonstrate the efficacy of DABNet. The generated brain networks also highlight the prediction-related brain regions and thus provide interpretations for predictions.

Chronic kidney disease (CKD) is a life-threatening and prevalent disease. CKD patients, especially endstage kidney disease (ESKD) patients on hemodialysis, suffer from kidney failures and are unable to remove excessive fluid, causing fluid overload and multiple morbidities including death. Current solutions for fluid overtake monitoring such as ultrasonography and biomarkers assessment are cumbersome, discontinuous, and can only be performed in the clinic. In this paper, we propose SRDA, a latent graph learning powered fluid overload detection system based on Sensor Relation Dual Autoencoder to detect excessive fluid consumption of EKSD patients based on passively collected bio-behavioral data from smartwatch sensors. Experiments using real-world mobile sensing data indicate that SRDA outperforms the state-of-the-art baselines in both F1 score and recall, and demonstrate the potential of ubiquitous sensing for ESKD fluid intake management.

Electronic Health Record modeling is crucial for digital medicine. However, existing models ignore higher-order interactions among medical codes and their causal relations towards downstream clinical predictions. To address such limitations, we propose a novel framework CACHE, to provide effective and insightful clinical predictions based on hypergraph representation learning and counterfactual and factual reasoning techniques. Experiments on two real EHR datasets show the superior performance of CACHE. Case studies with a domain expert illustrate a preferred capability of CACHE in generating clinically meaningful interpretations towards the correct predictions.

Multimodal brain networks characterize complex connectivities among different brain regions from both structural and functional aspects and provide a new means for mental disease analysis. Recently, Graph Neural Networks (GNNs) have become a de facto model for analyzing graph-structured data. However, how to employ GNNs to extract effective representations from brain networks in multiple modalities remains rarely explored. Moreover, as brain networks provide no initial node features, how to design informative node attributes and leverage edge weights for GNNs to learn is left unsolved. To this end, we develop a novel multiview GNN for multimodal brain networks. In particular, we treat each modality as a view for brain networks and employ contrastive learning for multimodal fusion. Then, we propose a GNN model which takes advantage of the message passing scheme by propagating messages based on degree statistics and brain region connectivities. Extensive experiments on two real-world disease datasets (HIV and Bipolar) demonstrate the effectiveness of our proposed method over state-of-the-art baselines.

Functional magnetic resonance imaging (fMRI) is one of the most common imaging modalities to investigate brain functions. Recent studies in neuroscience stress the great potential of functional brain networks constructed from fMRI data for clinical predictions. Traditional functional brain networks, however, are noisy and unaware of downstream prediction tasks, while also incompatible with the deep graph neural network (GNN) models. In order to fully unleash the power of GNNs in network-based fMRI analysis, we develop FBNETGEN, a task-aware and interpretable fMRI analysis framework via deep brain network generation. In particular, we formulate (1) prominent region of interest (ROI) features extraction, (2) brain networks generation, and (3) clinical predictions with GNNs, in an end-to-end trainable model under the guidance of particular prediction tasks. Along with the process, the key novel component is the graph generator which learns to transform raw time-series features into task-oriented brain networks. Our learnable graphs also provide unique interpretations by highlighting prediction-related brain regions. Comprehensive experiments on two datasets, i.e., the recently released and currently largest publicly available fMRI dataset Adolescent Brain Cognitive Development (ABCD), and the widely-used fMRI dataset PNC, prove the superior effectiveness and interpretability of FBNETGEN. The implementation is available at https://github.com/Wayfear/FBNETGEN.