Overharvesting in human patch foraging reflects rational structure learning and adaptive planning.

Patch foraging presents a sequential decision-making problem widely studied across organisms-stay with a current option or leave it in search of a better alternative? Behavioral ecology has identified an optimal strategy for these decisions, but, across species, foragers systematically deviate from it, staying too long with an option or "overharvesting" relative to this optimum. Despite the ubiquity of this behavior, the mechanism underlying it remains unclear and an object of extensive investigation. Here, we address this gap by approaching foraging as both a decision-making and learning problem. Specifically, we propose a model in which foragers 1) rationally infer the structure of their environment and 2) use their uncertainty over the inferred structure representation to adaptively discount future rewards. We find that overharvesting can emerge from this rational statistical inference and uncertainty adaptation process. In a patch-leaving task, we show that human participants adapt their foraging to the richness and dynamics of the environment in ways consistent with our model. These findings suggest that definitions of optimal foraging could be extended by considering how foragers reduce and adapt to uncertainty over representations of their environment.

GSL-DTI: Graph structure learning network for Drug-Target interaction prediction.

MOTIVATION: Drug-target interaction prediction is an important area of research to predict whether there is an interaction between a drug molecule and its target protein. It plays a critical role in drug discovery and development by facilitating the identification of potential drug candidates and expediting the overall process. Given the time-consuming, expensive, and high-risk nature of traditional drug discovery methods, the prediction of drug-target interactions has become an indispensable tool. Using machine learning and deep learning to tackle this class of problems has become a mainstream approach, and graph-based models have recently received much attention in this field. However, many current graph-based Drug-Target Interaction (DTI) prediction methods rely on manually defined rules to construct the Drug-Protein Pair (DPP) network during the DPP representation learning process. However, these methods fail to capture the true underlying relationships between drug molecules and target proteins. RESULTS: We propose GSL-DTI, an automatic graph structure learning model used for predicting drug-target interactions (DTIs). Initially, we integrate large-scale heterogeneous networks using a graph convolution network based on meta-paths, effectively learning the representations of drugs and target proteins. Subsequently, we construct drug-protein pairs based on these representations. In contrast to previous studies that construct DPP networks based on manual rules, our method introduces an automatic graph structure learning approach. This approach utilizes a filter gate on the affinity scores of DPPs and relies on the classification loss of downstream tasks to guide the learning of the underlying DPP network structure. Based on the learned DPP network, we transform the prediction of drug-target interactions into a node classification problem. The comprehensive experiments conducted on three public datasets have shown the superiority of GSL-DTI in the tasks of DTI prediction. Additionally, GSL-DTI provides a fresh perspective for advancing research in graph structure learning for DTI prediction.

SGK-Net: A Novel Navigation Scene Graph Generation Network.

Scene graphs can enhance the understanding capability of intelligent ships in navigation scenes. However, the complex entity relationships and the presence of significant noise in contextual information within navigation scenes pose challenges for navigation scene graph generation (NSGG). To address these issues, this paper proposes a novel NSGG network named SGK-Net. This network comprises three innovative modules. The Semantic-Guided Multimodal Fusion (SGMF) module utilizes prior information on relationship semantics to fuse multimodal information and construct relationship features, thereby elucidating the relationships between entities and reducing semantic ambiguity caused by complex relationships. The Graph Structure Learning-based Structure Evolution (GSLSE) module, based on graph structure learning, reduces redundancy in relationship features and optimizes the computational complexity in subsequent contextual message passing. The Key Entity Message Passing (KEMP) module takes full advantage of contextual information to refine relationship features, thereby reducing noise interference from non-key nodes. Furthermore, this paper constructs the first Ship Navigation Scene Graph Simulation dataset, named SNSG-Sim, which provides a foundational dataset for the research on ship navigation SGG. Experimental results on the SNSG-sim dataset demonstrate that our method achieves an improvement of 8.31% (R@50) in the PredCls task and 7.94% (R@50) in the SGCls task compared to the baseline method, validating the effectiveness of our method in navigation scene graph generation.

Learning Causes of Functional Dynamic Targets: Screening and Local Methods.

This paper addresses the challenge of identifying causes for functional dynamic targets, which are functions of various variables over time. We develop screening and local learning methods to learn the direct causes of the target, as well as all indirect causes up to a given distance. We first discuss the modeling of the functional dynamic target. Then, we propose a screening method to select the variables that are significantly correlated with the target. On this basis, we introduce an algorithm that combines screening and structural learning techniques to uncover the causal structure among the target and its causes. To tackle the distance effect, where long causal paths weaken correlation, we propose a local method to discover the direct causes of the target in these significant variables and further sequentially find all indirect causes up to a given distance. We show theoretically that our proposed methods can learn the causes correctly under some regular assumptions. Experiments based on synthetic data also show that the proposed methods perform well in learning the causes of the target.

Causal Structure Learning with Conditional and Unique Information Groups-Decomposition Inequalities.

The causal structure of a system imposes constraints on the joint probability distribution of variables that can be generated by the system. Archetypal constraints consist of conditional independencies between variables. However, particularly in the presence of hidden variables, many causal structures are compatible with the same set of independencies inferred from the marginal distributions of observed variables. Additional constraints allow further testing for the compatibility of data with specific causal structures. An existing family of causally informative inequalities compares the information about a set of target variables contained in a collection of variables, with a sum of the information contained in different groups defined as subsets of that collection. While procedures to identify the form of these groups-decomposition inequalities have been previously derived, we substantially enlarge the applicability of the framework. We derive groups-decomposition inequalities subject to weaker independence conditions, with weaker requirements in the configuration of the groups, and additionally allowing for conditioning sets. Furthermore, we show how constraints with higher inferential power may be derived with collections that include hidden variables, and then converted into testable constraints using data processing inequalities. For this purpose, we apply the standard data processing inequality of conditional mutual information and derive an analogous property for a measure of conditional unique information recently introduced to separate redundant, synergistic, and unique contributions to the information that a set of variables has about a target.

Updating Contextual Sensory Expectations for Adaptive Behavior.

The brain has the extraordinary capacity to construct predictive models of the environment by internalizing statistical regularities in the sensory inputs. The resulting sensory expectations shape how we perceive and react to the world; at the neural level, this relates to decreased neural responses to expected than unexpected stimuli ("expectation suppression"). Crucially, expectations may need revision as context changes. However, existing research has often neglected this issue. Further, it is unclear whether contextual revisions apply selectively to expectations relevant to the task at hand, hence serving adaptive behavior. The present fMRI study examined how contextual visual expectations spread throughout the cortical hierarchy as we update our beliefs. We created a volatile environment: two alternating contexts contained different sequences of object images, thereby producing context-dependent expectations that needed revision when the context changed. Human participants of both sexes attended a training session before scanning to learn the contextual sequences. The fMRI experiment then tested for the emergence of contextual expectation suppression in two separate tasks, respectively, with task-relevant and task-irrelevant expectations. Effects of contextual expectation emerged progressively across the cortical hierarchy as participants attuned themselves to the context: expectation suppression appeared first in the insula, inferior frontal gyrus, and posterior parietal cortex, followed by the ventral visual stream, up to early visual cortex. This applied selectively to task-relevant expectations. Together, the present results suggest that an insular and frontoparietal executive control network may guide the flexible deployment of contextual sensory expectations for adaptive behavior in our complex and dynamic world.SIGNIFICANCE STATEMENT The world is structured by statistical regularities, which we use to predict the future. This is often accompanied by suppressed neural responses to expected compared with unexpected events ("expectation suppression"). Crucially, the world is also highly volatile and context-dependent: expected events may become unexpected when the context changes, thus raising the crucial need for belief updating. However, this issue has generally been neglected. By setting up a volatile environment, we show that expectation suppression emerges first in executive control regions, followed by relevant sensory areas, only when observers use their expectations to optimize behavior. This provides surprising yet clear evidence on how the brain controls the updating of sensory expectations for adaptive behavior in our ever-changing world.

Constructing Causal Life-Course Models: Comparative Study of Data-Driven and Theory-Driven Approaches.

Life-course epidemiology relies on specifying complex (causal) models that describe how variables interplay over time. Traditionally, such models have been constructed by perusing existing theory and previous studies. By comparing data-driven and theory-driven models, we investigated whether data-driven causal discovery algorithms can help in this process. We focused on a longitudinal data set on a cohort of Danish men (the Metropolit Study, 1953-2017). The theory-driven models were constructed by 2 subject-field experts. The data-driven models were constructed by use of the temporal Peter-Clark (TPC) algorithm. The TPC algorithm utilizes the temporal information embedded in life-course data. We found that the data-driven models recovered some, but not all, causal relationships included in the theory-driven expert models. The data-driven method was especially good at identifying direct causal relationships that the experts had high confidence in. Moreover, in a post hoc assessment, we found that most of the direct causal relationships proposed by the data-driven model but not included in the theory-driven model were plausible. Thus, the data-driven model may propose additional meaningful causal hypotheses that are new or have been overlooked by the experts. In conclusion, data-driven methods can aid causal model construction in life-course epidemiology, and combining both data-driven and theory-driven methods can lead to even stronger models.

Information enhanced model selection for Gaussian graphical model with application to metabolomic data.

In light of the low signal-to-noise nature of many large biological data sets, we propose a novel method to learn the structure of association networks using Gaussian graphical models combined with prior knowledge. Our strategy includes two parts. In the first part, we propose a model selection criterion called structural Bayesian information criterion, in which the prior structure is modeled and incorporated into Bayesian information criterion. It is shown that the popular extended Bayesian information criterion is a special case of structural Bayesian information criterion. In the second part, we propose a two-step algorithm to construct the candidate model pool. The algorithm is data-driven and the prior structure is embedded into the candidate model automatically. Theoretical investigation shows that under some mild conditions structural Bayesian information criterion is a consistent model selection criterion for high-dimensional Gaussian graphical model. Simulation studies validate the superiority of the proposed algorithm over the existing ones and show the robustness to the model misspecification. Application to relative concentration data from infant feces collected from subjects enrolled in a large molecular epidemiological cohort study validates that metabolic pathway involvement is a statistically significant factor for the conditional dependence between metabolites. Furthermore, new relationships among metabolites are discovered which can not be identified by the conventional methods of pathway analysis. Some of them have been widely recognized in biological literature.

Individualized causal discovery with latent trajectory embedded Bayesian networks.

Bayesian networks have been widely used to generate causal hypotheses from multivariate data. Despite their popularity, the vast majority of existing causal discovery approaches make the strong assumption of a (partially) homogeneous sampling scheme. However, such assumption can be seriously violated, causing significant biases when the underlying population is inherently heterogeneous. To this end, we propose a novel causal Bayesian network model, termed BN-LTE, that embeds heterogeneous samples onto a low-dimensional manifold and builds Bayesian networks conditional on the embedding. This new framework allows for more precise network inference by improving the estimation resolution from the population level to the observation level. Moreover, while causal Bayesian networks are in general not identifiable with purely observational, cross-sectional data due to Markov equivalence, with the blessing of causal effect heterogeneity, we prove that the proposed BN-LTE is uniquely identifiable under relatively mild assumptions. Through extensive experiments, we demonstrate the superior performance of BN-LTE in causal structure learning as well as inferring observation-specific gene regulatory networks from observational data.

Functional Bayesian networks for discovering causality from multivariate functional data.

Multivariate functional data arise in a wide range of applications. One fundamental task is to understand the causal relationships among these functional objects of interest. In this paper, we develop a novel Bayesian network (BN) model for multivariate functional data where conditional independencies and causal structure are encoded by a directed acyclic graph. Specifically, we allow the functional objects to deviate from Gaussian processes, which is the key to unique causal structure identification even when the functions are measured with noises. A fully Bayesian framework is designed to infer the functional BN model with natural uncertainty quantification through posterior summaries. Simulation studies and real data examples demonstrate the practical utility of the proposed model.

Computational evidence for hierarchically structured reinforcement learning in humans.

Humans have the fascinating ability to achieve goals in a complex and constantly changing world, still surpassing modern machine-learning algorithms in terms of flexibility and learning speed. It is generally accepted that a crucial factor for this ability is the use of abstract, hierarchical representations, which employ structure in the environment to guide learning and decision making. Nevertheless, how we create and use these hierarchical representations is poorly understood. This study presents evidence that human behavior can be characterized as hierarchical reinforcement learning (RL). We designed an experiment to test specific predictions of hierarchical RL using a series of subtasks in the realm of context-based learning and observed several behavioral markers of hierarchical RL, such as asymmetric switch costs between changes in higher-level versus lower-level features, faster learning in higher-valued compared to lower-valued contexts, and preference for higher-valued compared to lower-valued contexts. We replicated these results across three independent samples. We simulated three models-a classic RL, a hierarchical RL, and a hierarchical Bayesian model-and compared their behavior to human results. While the flat RL model captured some aspects of participants' sensitivity to outcome values, and the hierarchical Bayesian model captured some markers of transfer, only hierarchical RL accounted for all patterns observed in human behavior. This work shows that hierarchical RL, a biologically inspired and computationally simple algorithm, can capture human behavior in complex, hierarchical environments and opens the avenue for future research in this field.

Causal Analysis of Physiological Sleep Data Using Granger Causality and Score-Based Structure Learning.

Understanding how the human body works during sleep and how this varies in the population is a task with significant implications for medicine. Polysomnographic studies, or sleep studies, are a common diagnostic method that produces a significant quantity of time-series sensor data. This study seeks to learn the causal structure from data from polysomnographic studies carried out on 600 adult volunteers in the United States. Two methods are used to learn the causal structure of these data: the well-established Granger causality and "DYNOTEARS", a modern approach that uses continuous optimisation to learn dynamic Bayesian networks (DBNs). The results from the two methods are then compared. Both methods produce graphs that have a number of similarities, including the mutual causation between electrooculogram (EOG) and electroencephelogram (EEG) signals and between sleeping position and SpO2 (blood oxygen level). However, DYNOTEARS, unlike Granger causality, frequently finds a causal link to sleeping position from the other variables. Following the creation of these causal graphs, the relationship between the discovered causal structure and the characteristics of the participants is explored. It is found that there is an association between the waist size of a participant and whether a causal link is found between the electrocardiogram (ECG) measurement and the EOG and EEG measurements. It is concluded that a person's body shape appears to impact the relationship between their heart and brain during sleep and that Granger causality and DYNOTEARS can produce differing results on real-world data.

Multiple imputation and test-wise deletion for causal discovery with incomplete cohort data.

Causal discovery algorithms estimate causal graphs from observational data. This can provide a valuable complement to analyses focusing on the causal relation between individual treatment-outcome pairs. Constraint-based causal discovery algorithms rely on conditional independence testing when building the graph. Until recently, these algorithms have been unable to handle missing values. In this article, we investigate two alternative solutions: test-wise deletion and multiple imputation. We establish necessary and sufficient conditions for the recoverability of causal structures under test-wise deletion, and argue that multiple imputation is more challenging in the context of causal discovery than for estimation. We conduct an extensive comparison by simulating from benchmark causal graphs: as one might expect, we find that test-wise deletion and multiple imputation both clearly outperform list-wise deletion and single imputation. Crucially, our results further suggest that multiple imputation is especially useful in settings with a small number of either Gaussian or discrete variables, but when the dataset contains a mix of both neither method is uniformly best. The methods we compare include random forest imputation and a hybrid procedure combining test-wise deletion and multiple imputation. An application to data from the IDEFICS cohort study on diet- and lifestyle-related diseases in European children serves as an illustrating example.

Learning stable and predictive structures in kinetic systems.

Learning kinetic systems from data is one of the core challenges in many fields. Identifying stable models is essential for the generalization capabilities of data-driven inference. We introduce a computationally efficient framework, called CausalKinetiX, that identifies structure from discrete time, noisy observations, generated from heterogeneous experiments. The algorithm assumes the existence of an underlying, invariant kinetic model, a key criterion for reproducible research. Results on both simulated and real-world examples suggest that learning the structure of kinetic systems benefits from a causal perspective. The identified variables and models allow for a concise description of the dynamics across multiple experimental settings and can be used for prediction in unseen experiments. We observe significant improvements compared to well-established approaches focusing solely on predictive performance, especially for out-of-sample generalization.

Digital Twin for Training Bayesian Networks for Fault Diagnostics of Manufacturing Systems.

Smart manufacturing systems are being advocated to leverage technological advances that enable them to be more resilient to faults through rapid diagnosis for performance assurance. In this paper, we propose a co-simulation approach for engineering digital twins (DTs) that are used to train Bayesian Networks (BNs) for fault diagnostics at equipment and factory levels. Specifically, the co-simulation model is engineered by using cyber-physical system (CPS) consisting of networked sensors, high-fidelity simulation model of each equipment, and a detailed discrete-event simulation (DES) model of the factory. The proposed DT approach enables injection of faults in the virtual system, thereby alleviating the need for expensive factory-floor experimentation. It should be emphasized that this approach of injecting faults eliminates the need for obtaining balanced data that include faulty and normal factory operations. We propose a Structural Intervention Algorithm (SIA) in this paper to first detect all possible directed edges and then distinguish between a parent and an ancestor node of the BN. We engineered a DT research test-bed in our laboratory consisting of four industrial robots configured into an assembly cell where each robot has an industrial Internet-of-Things sensor that can monitor vibrations in two-axes. A detailed equipment-level simulator of these robots was integrated with a detailed DES model of the robotic assembly cell. The resulting DT was used to carry out interventions to learn a BN model structure for fault diagnostics. Laboratory experiments validated the efficacy of the proposed approach by accurately learning the BN structure, and in the experiments, the accuracy obtained by the proposed approach (measured using Structural Hamming Distance) was found to be significantly better than traditional methods. Furthermore, the BN structure learned was found to be robust to variations in parameters, such as mean time to failure (MTTF).

Bayesian Network Model Averaging Classifiers by Subbagging.

When applied to classification problems, Bayesian networks are often used to infer a class variable when given feature variables. Earlier reports have described that the classification accuracy of Bayesian network structures achieved by maximizing the marginal likelihood (ML) is lower than that achieved by maximizing the conditional log likelihood (CLL) of a class variable given the feature variables. Nevertheless, because ML has asymptotic consistency, the performance of Bayesian network structures achieved by maximizing ML is not necessarily worse than that achieved by maximizing CLL for large data. However, the error of learning structures by maximizing the ML becomes much larger for small sample sizes. That large error degrades the classification accuracy. As a method to resolve this shortcoming, model averaging has been proposed to marginalize the class variable posterior over all structures. However, the posterior standard error of each structure in the model averaging becomes large as the sample size becomes small; it subsequently degrades the classification accuracy. The main idea of this study is to improve the classification accuracy using subbagging, which is modified bagging using random sampling without replacement, to reduce the posterior standard error of each structure in model averaging. Moreover, to guarantee asymptotic consistency, we use the K-best method with the ML score. The experimentally obtained results demonstrate that our proposed method provides more accurate classification than earlier BNC methods and the other state-of-the-art ensemble methods do.

Bayesian Network Structure Learning Method Based on Causal Direction Graph for Protein Signaling Networks.

Constructing the structure of protein signaling networks by Bayesian network technology is a key issue in the field of bioinformatics. The primitive structure learning algorithms of the Bayesian network take no account of the causal relationships between variables, which is unfortunately important in the application of protein signaling networks. In addition, as a combinatorial optimization problem with a large searching space, the computational complexities of the structure learning algorithms are unsurprisingly high. Therefore, in this paper, the causal directions between any two variables are calculated first and stored in a graph matrix as one of the constraints of structure learning. A continuous optimization problem is constructed next by using the fitting losses of the corresponding structure equations as the target, and the directed acyclic prior is used as another constraint at the same time. Finally, a pruning procedure is developed to keep the result of the continuous optimization problem sparse. Experiments show that the proposed method improves the structure of the Bayesian network compared with the existing methods on both the artificial data and the real data, meanwhile, the computational burdens are also reduced significantly.

Generic Structure Extraction with Bi-Level Optimization for Graph Structure Learning.

Currently, most Graph Structure Learning (GSL) methods, as a means of learning graph structure, improve the robustness of GNN merely from a local view by considering the local information related to each edge and indiscriminately applying the mechanism across edges, which may suffer from the local structure heterogeneity of the graph (i.e., the uneven distribution of inter-class connections over nodes). To overcome the drawbacks, we extract the graph structure as a learnable parameter and jointly learn the structure and common parameters of GNN from the global view. Excitingly, the common parameters contain the global information for nodes features mapping, which is also crucial for structure optimization (i.e., optimizing the structure relies on global mapping information). Mathematically, we apply a generic structure extractor to abstract the graph structure and transform GNNs in the form of learning structure and common parameters. Then, we model the learning process as a novel bi-level optimization, i.e., Generic Structure Extraction with Bi-level Optimization for Graph Structure Learning (GSEBO), which optimizes GNN parameters in the upper level to obtain the global mapping information and graph structure is optimized in the lower level with the global information learned from the upper level. We instantiate the proposed GSEBO on classical GNNs and compare it with the state-of-the-art GSL methods. Extensive experiments validate the effectiveness of the proposed GSEBO on four real-world datasets.

Nonparametric Causal Structure Learning in High Dimensions.

The PC and FCI algorithms are popular constraint-based methods for learning the structure of directed acyclic graphs (DAGs) in the absence and presence of latent and selection variables, respectively. These algorithms (and their order-independent variants, PC-stable and FCI-stable) have been shown to be consistent for learning sparse high-dimensional DAGs based on partial correlations. However, inferring conditional independences from partial correlations is valid if the data are jointly Gaussian or generated from a linear structural equation model-an assumption that may be violated in many applications. To broaden the scope of high-dimensional causal structure learning, we propose nonparametric variants of the PC-stable and FCI-stable algorithms that employ the conditional distance covariance (CdCov) to test for conditional independence relationships. As the key theoretical contribution, we prove that the high-dimensional consistency of the PC-stable and FCI-stable algorithms carry over to general distributions over DAGs when we implement CdCov-based nonparametric tests for conditional independence. Numerical studies demonstrate that our proposed algorithms perform nearly as good as the PC-stable and FCI-stable for Gaussian distributions, and offer advantages in non-Gaussian graphical models.

Revaluing the Role of vmPFC in the Acquisition of Pavlovian Threat Conditioning in Humans.

The role of the ventromedial prefrontal cortex (vmPFC) in human pavlovian threat conditioning has been relegated largely to the extinction or reversal of previously acquired stimulus-outcome associations. However, recent neuroimaging evidence questions this view by also showing activity in the vmPFC during threat acquisition. Here we investigate the casual role of vmPFC in the acquisition of pavlovian threat conditioning by assessing skin conductance response (SCR) and declarative memory of stimulus-outcome contingencies during a differential pavlovian threat-conditioning paradigm in eight patients with a bilateral vmPFC lesion, 10 with a lesion outside PFC and 10 healthy participants (each group included both females and males). Results showed that patients with vmPFC lesion failed to produce a conditioned SCR during threat acquisition, despite no evidence of compromised SCR to unconditioned stimulus or compromised declarative memory for stimulus-outcome contingencies. These results suggest that the vmPFC plays a causal role in the acquisition of new learning and not just in the extinction or reversal of previously acquired learning, as previously thought. Given the role of the vmPFC in schema-related processing and latent structure learning, the vmPFC may be required to construct a detailed representation of the task, which is needed to produce a sustained conditioned physiological response in anticipation of the unconditioned stimulus during threat acquisition.SIGNIFICANCE STATEMENT Pavlovian threat conditioning is an adaptive mechanism through which organisms learn to avoid potential threats, thus increasing their chances of survival. Understanding what brain regions contribute to such a process is crucial to understand the mechanisms underlying adaptive as well as maladaptive learning, and has the potential to inform the treatment of anxiety disorders. Importantly, the role of the ventromedial prefrontal cortex (vmPFC) in the acquisition of pavlovian threat conditioning has been relegated largely to the inhibition of previously acquired learning. Here, we show that the vmPFC actually plays a causal role in the acquisition of pavlovian threat conditioning.