skip to main content


Title: A Hierarchical Graph Learning Model for Brain Network Regression Analysis
Brain networks have attracted increasing attention due to the potential to better characterize brain dynamics and abnormalities in neurological and psychiatric conditions. Recent years have witnessed enormous successes in deep learning. Many AI algorithms, especially graph learning methods, have been proposed to analyze brain networks. An important issue for existing graph learning methods is that those models are not typically easy to interpret. In this study, we proposed an interpretable graph learning model for brain network regression analysis. We applied this new framework on the subjects from Human Connectome Project (HCP) for predicting multiple Adult Self-Report (ASR) scores. We also use one of the ASR scores as the example to demonstrate how to identify sex differences in the regression process using our model. In comparison with other state-of-the-art methods, our results clearly demonstrate the superiority of our new model in effectiveness, fairness, and transparency.  more » « less
Award ID(s):
2045848 1837956
NSF-PAR ID:
10339872
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Frontiers in Neuroscience
Volume:
16
ISSN:
1662-453X
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Network embedding has been an effective tool to analyze heterogeneous networks (HNs) by representing nodes in a low-dimensional space. Although many recent methods have been proposed for representation learning of HNs, there is still much room for improvement. Random walks based methods are currently popular methods to learn network embedding; however, they are random and limited by the length of sampled walks, and have difculty capturing network structural information. Some recent researches proposed using meta paths to express the sample relationship in HNs. Another popular graph learning model, the graph convolutional network (GCN) is known to be capable of better exploitation of network topology, but the current design of GCN is intended for homogenous networks. This paper proposes a novel combination of meta-graph and graph convolution, the meta-graph based graph convolutional networks (MGCN). To fully capture the complex long semantic information, MGCN utilizes different meta-graphs in HNs. As different meta-graphs express different semantic relationships, MGCN learns the weights of different meta-graphs to make up for the loss of semantics when applying GCN. In addition, we improve the current convolution design by adding node self-signicance. To validate our model in learning feature representation, we present comprehensive experiments on four real-world datasets and two representation tasks: classication and link prediction. WMGCN's representations can improve accuracy scores by up to around 10% in comparison to other popular representation learning models. What's more, WMGCN'feature learning outperforms other popular baselines. The experimental results clearly show our model is superior over other state-of-the-art representation learning algorithms. 
    more » « less
  2. Brain-computer interface (BCI) actively translates the brain signals into executable actions by establishing direct communication between the human brain and external devices. Recording brain activity through electroencephalography (EEG) is generally contaminated with both physiological and nonphysiological artifacts, which significantly hinders the BCI performance. Artifact subspace reconstruction (ASR) is a well-known statistical technique that automatically removes artifact components by determining the rejection threshold based on the initial reference EEG segment in multichannel EEG recordings. In real-world applications, the fixed threshold may limit the efficacy of the artifact correction, especially when the quality of the reference data is poor. This study proposes an adaptive online ASR technique by integrating the Hebbian/anti-Hebbian neural networks into the ASR algorithm, namely, principle subspace projection ASR (PSP-ASR) and principal subspace whitening ASR (PSW-ASR) that segmentwise self-organize the artifact subspace by updating the synaptic weights according to the Hebbian and anti-Hebbian learning rules. The effectiveness of the proposed algorithm is compared to the conventional ASR approaches on benchmark EEG dataset and three BCI frameworks, including steady-state visual evoked potential (SSVEP), rapid serial visual presentation (RSVP), and motor imagery (MI) by evaluating the root-mean-square error (RMSE), the signal-to-noise ratio (SNR), the Pearson correlation, and classification accuracy. The results demonstrated that the PSW-ASR algorithm effectively removed the EEG artifacts and retained the activity-specific brain signals compared to the PSP-ASR, standard ASR (Init-ASR), and moving-window ASR (MW-ASR) methods, thereby enhancing the SSVEP, RSVP, and MI BCI performances. Finally, our empirical results from the PSW-ASR algorithm suggested the choice of an aggressive cutoff range of c = 1-10 for activity-specific BCI applications and a moderate range of for the benchmark dataset and general BCI applications. 
    more » « less
  3. Machine learning (ML) methods, such as artificial neural networks (ANN), k-nearest neighbors (kNN), random forests (RF), support vector machines (SVM), and boosted decision trees (DTs), may offer stronger predictive performance than more traditional, parametric methods, such as linear regression, multiple linear regression, and logistic regression (LR), for specific mapping and modeling tasks. However, this increased performance is often accompanied by increased model complexity and decreased interpretability, resulting in critiques of their “black box” nature, which highlights the need for algorithms that can offer both strong predictive performance and interpretability. This is especially true when the global model and predictions for specific data points need to be explainable in order for the model to be of use. Explainable boosting machines (EBM), an augmentation and refinement of generalize additive models (GAMs), has been proposed as an empirical modeling method that offers both interpretable results and strong predictive performance. The trained model can be graphically summarized as a set of functions relating each predictor variable to the dependent variable along with heat maps representing interactions between selected pairs of predictor variables. In this study, we assess EBMs for predicting the likelihood or probability of slope failure occurrence based on digital terrain characteristics in four separate Major Land Resource Areas (MLRAs) in the state of West Virginia, USA and compare the results to those obtained with LR, kNN, RF, and SVM. EBM provided predictive accuracies comparable to RF and SVM and better than LR and kNN. The generated functions and visualizations for each predictor variable and included interactions between pairs of predictor variables, estimation of variable importance based on average mean absolute scores, and provided scores for each predictor variable for new predictions add interpretability, but additional work is needed to quantify how these outputs may be impacted by variable correlation, inclusion of interaction terms, and large feature spaces. Further exploration of EBM is merited for geohazard mapping and modeling in particular and spatial predictive mapping and modeling in general, especially when the value or use of the resulting predictions would be greatly enhanced by improved interpretability globally and availability of prediction explanations at each cell or aggregating unit within the mapped or modeled extent. 
    more » « less
  4. Abstract

    A key problem in social network analysis is to identify nonhuman interactions. State‐of‐the‐art bot‐detection systems like Botometer train machine‐learning models on user‐specific data. Unfortunately, these methods do not work on data sets in which only topological information is available. In this paper, we propose a new, purely topological approach. Our method removes edges that connect nodes exhibiting strong evidence of non‐human activity from publicly available electronic‐social‐network datasets, including, for example, those in the Stanford Network Analysis Project repository (SNAP). Our methodology is inspired by classic work in evolutionary psychology by Dunbar that posits upper bounds on the total strength of the set of social connections in which a single human can be engaged. We model edge strength with Easley and Kleinberg's topological estimate; label nodes as “violators” if the sum of these edge strengths exceeds a Dunbar‐inspired bound; and then remove the violator‐to‐violator edges. We run our algorithm on multiple social networks and show that our Dunbar‐inspired bound appears to hold for social networks, but not for nonsocial networks. Our cleaning process classifies 0.04% of the nodes of the Twitter‐2010 followers graph as violators, and we find that more than 80% of these violator nodes have Botometer scores of 0.5 or greater. Furthermore, after we remove the roughly 15 million violator‐violator edges from the 1.2‐billion‐edge Twitter‐2010 follower graph, 34% of the violator nodes experience a factor‐of‐two decrease in PageRank. PageRank is a key component of many graph algorithms such as node/edge ranking and graph sparsification. Thus, this artificial inflation would bias algorithmic output, and result in some incorrect decisions based on this output.

     
    more » « less
  5. Machine learning (ML) methods for causal inference have gained popularity due to their flexibility to predict the outcome model and the propensity score. In this article, we provide a within-group approach for ML-based causal inference methods in order to robustly estimate average treatment effects in multilevel studies when there is cluster-level unmeasured confounding. We focus on one particular ML-based causal inference method based on the targeted maximum likelihood estimation (TMLE) with an ensemble learner called SuperLearner. Through our simulation studies, we observe that training TMLE within groups of similar clusters helps remove bias from cluster-level unmeasured confounders. Also, using within-group propensity scores estimated from fixed effects logistic regression increases the robustness of the proposed within-group TMLE method. Even if the propensity scores are partially misspecified, the within-group TMLE still produces robust ATE estimates due to double robustness with flexible modeling, unlike parametric-based inverse propensity weighting methods. We demonstrate our proposed methods and conduct sensitivity analyses against the number of groups and individual-level unmeasured confounding to evaluate the effect of taking an eighth-grade algebra course on math achievement in the Early Childhood Longitudinal Study.

     
    more » « less