A Novel Spatio-Temporal Multi-Task Approach for the Prediction of Diabetes-Related Complication: a Cardiopathy Case of Study

The prediction of the risk profile related to the cardiopathy complication is a core research task that could support clinical decision making. However, the design and implementation of a clinical decision support system based on Electronic Health Record (EHR) temporal data comprise of several challenges. Several single task learning approaches consider the prediction of the risk profile related to a specific diabetes complication (i.e., cardiopathy) independent from other complications. Accordingly, the state-of-the-art multi-task learning (MTL) model encapsulates only the temporal relatedness among the EHR data. However, this assumption might be restricted in the clinical scenario where both spatio-temporal constraints should be taken into account. The aim of this study is the proposal of two different MTL procedures, called spatio-temporal lasso (STL-MTL) and spatio-temporal group lasso (STGL-MTL), which encode the spatio-temporal relatedness using a regularization term and a graph-based approach (i.e., encoding the task relatedness using the structure matrix). Experimental results on a real-world EHR dataset demonstrate the robust performance and the interpretability of the proposed approach.

Distributed Primal-Dual Optimization for Online Multi-Task Learning

Conventional online multi-task learning algorithms suffer from two critical limitations: 1) Heavy communication caused by delivering high velocity of sequential data to a central machine; 2) Expensive runtime complexity for building task relatedness. To address these issues, in this paper we consider a setting where multiple tasks are geographically located in different places, where one task can synchronize data with others to leverage knowledge of related tasks. Specifically, we propose an adaptive primal-dual algorithm, which not only captures task-specific noise in adversarial learning but also carries out a projection-free update with runtime efficiency. Moreover, our model is well-suited to decentralized periodic-connected tasks as it allows the energy-starved or bandwidth-constraint tasks to postpone the update. Theoretical results demonstrate the convergence guarantee of our distributed algorithm with an optimal regret. Empirical results confirm that the proposed model is highly effective on various real-world datasets.

Dissociating the freely-moving thought dimension of mind-wandering from the intentionality and task-unrelated thought dimensions

The recently forwarded family-resemblances framework of mind-wandering argues that mind-wandering is a multidimensional construct consisting of a variety of exemplars. On this view, membership in the mind-wandering family is graded along various dimensions that define more or less prototypical instances of mind-wandering. In recent work, three dimensions that have played a prominent role in defining prototypicality within the mind-wandering family include: (a) task-relatedness, (b) intentionality, and (c) thought constraint. One concern, however, is that these dimensions may be redundant with each other. The utility of distinguishing among these different dimensions of mind-wandering rests upon a demonstration that they are dissociable. To shed light on this issue, we indexed the task-relatedness, intentionality, and constraint dimensions of thought during completion of a laboratory task to evaluate how these dimensions relate to each other. We found that 56% of unconstrained thoughts were “on-task” and that 23% of constrained thoughts were “off-task.” Moreover, we found that rates of off-task thought, but not unconstrained thought, varied as a function of expected changes in task demands, confirming that task-relatedness and thought constraint are separable dimensions. Participants also reported 21% of intentional off-task thoughts that were freely moving, and 9% of unintentional off-task thoughts that were not freely moving. Whereas intentional off-task thoughts varied as a function of expected changes in task demands, freely moving thoughts did not. Taken together, the results suggest that these three dimensions of mind-wandering are not redundant with one another.

Multi-Task Clustering with Model Relation Learning

Multi-task clustering improves the clustering performance of each task by transferring knowledge among the related tasks. An important aspect of multi-task clustering is to assess the task relatedness. However, to our knowledge, only two previous works have assessed the task relatedness, but they both have limitations. In this paper, we propose a multi-task clustering with model relation learning (MTCMRL) method, which automatically learns the model parameter relatedness between each pair of tasks. The objective function of MTCMRL consists of two parts: (1) within-task clustering: clustering each task by introducing linear regression model into symmetric nonnegative matrix factorization; (2) cross-task relatedness learning: updating the parameter of the linear regression model in each task by learning the model parameter relatedness between the clusters in each pair of tasks. We present an effective alternating algorithm to solve the non-convex optimization problem. Experimental results show the superiority of the proposed method over traditional single-task clustering methods and existing multi-task clustering methods.