Unsupervised Path Representation Learning with Curriculum Negative Sampling

Path representations are critical in a variety of transportation applications, such as estimating path ranking in path recommendation systems and estimating path travel time in navigation systems. Existing studies often learn task-specific path representations in a supervised manner, which require a large amount of labeled training data and generalize poorly to other tasks. We propose an unsupervised learning framework Path InfoMax (PIM) to learn generic path representations that work for different downstream tasks. We first propose a curriculum negative sampling method, for each input path, to generate a small amount of negative paths, by following the principles of curriculum learning. Next, PIM employs mutual information maximization to learn path representations from both a global and a local view. In the global view, PIM distinguishes the representations of the input paths from those of the negative paths. In the local view, PIM distinguishes the input path representations from the representations of the nodes that appear only in the negative paths. This enables the learned path representations encode both global and local information at different scales. Extensive experiments on two downstream tasks, ranking score estimation and travel time estimation, using two road network datasets suggest that PIM significantly outperforms other unsupervised methods and is also able to be used as a pre-training method to enhance supervised path representation learning.

The paradox of second-order homophily in networks

Homophily—the tendency of nodes to connect to others of the same type—is a central issue in the study of networks. Here we take a local view of homophily, defining notions of first-order homophily of a node (its individual tendency to link to similar others) and second-order homophily of a node (the aggregate first-order homophily of its neighbors). Through this view, we find a surprising result for homophily values that applies with only minimal assumptions on the graph topology. It can be phrased most simply as “in a graph of red and blue nodes, red friends of red nodes are on average more homophilous than red friends of blue nodes”. This gap in averages defies simple intuitive explanations, applies to globally heterophilous and homophilous networks and is reminiscent of but structually distinct from the Friendship Paradox. The existence of this gap suggests intrinsic biases in homophily measurements between groups, and hence is relevant to empirical studies of homophily in networks.

Adjudicating Between Local and Global Architectures of Predictive Processing in the Subcortical Auditory Pathway

Predictive processing, a leading theoretical framework for sensory processing, suggests that the brain constantly generates predictions on the sensory world and that perception emerges from the comparison between these predictions and the actual sensory input. This requires two distinct neural elements: generative units, which encode the model of the sensory world; and prediction error units, which compare these predictions against the sensory input. Although predictive processing is generally portrayed as a theory of cerebral cortex function, animal and human studies over the last decade have robustly shown the ubiquitous presence of prediction error responses in several nuclei of the auditory, somatosensory, and visual subcortical pathways. In the auditory modality, prediction error is typically elicited using so-called oddball paradigms, where sequences of repeated pure tones with the same pitch are at unpredictable intervals substituted by a tone of deviant frequency. Repeated sounds become predictable promptly and elicit decreasing prediction error; deviant tones break these predictions and elicit large prediction errors. The simplicity of the rules inducing predictability make oddball paradigms agnostic about the origin of the predictions. Here, we introduce two possible models of the organizational topology of the predictive processing auditory network: (1) the global view, that assumes that predictions on the sensory input are generated at high-order levels of the cerebral cortex and transmitted in a cascade of generative models to the subcortical sensory pathways; and (2) the local view, that assumes that independent local models, computed using local information, are used to perform predictions at each processing stage. In the global view information encoding is optimized globally but biases sensory representations along the entire brain according to the subjective views of the observer. The local view results in a diminished coding efficiency, but guarantees in return a robust encoding of the features of sensory input at each processing stage. Although most experimental results to-date are ambiguous in this respect, recent evidence favors the global model.

Development of Problem-Based Learning (PBL)

This chapter starts with a basic definition of PBL that leads a review of a history of PBL. The review involves both a global view and a local view in China. It then describes how learning activity happens in PBL and introduces main characteristics of PBL. This motivates a theoretical reflection on why PBL works well in preparing qualified young generation for dealing with challenges of complexity in future professional practice. This chapter will close its discussion on why and how PBL should be considered as a good strategy in Chinese universities.

“Xilala is only treated with a good hand”: a study on the treatment of malnutrition in Mozambique

In Mozambique old and new evils of body and spirit intertwine, thus allowing particular contours to modern life. Traditional diseases are reconfigured along the lines of a new thinking, and what Western medicine calls malnutrition is defined as xilala by the local traditional thinking. This study aimed to understand the point of view of both caregivers (mothers and grandmothers) of children participating in a Nutritional Rehabilitation Program and ethnomedicine experts, who find themselves entangled in a complex set of relationships through which different forms to comprehend body, health, and disease circulate. The supplement, as an object, has a life of its own and takes on new meanings when it leaves the hospital. When its use happens at home, it acquires a particularity: it becomes food. Thus, it ceases to be something inert and impersonal, which is a feature of standard medicine of the health institution. The local view centered on ethnomedicine is based on the certainty that a situation affecting a child cannot have a healing outcome if not by traditional medicine. Biomedical rationality erected from the confluence of the biological and technical sciences with their scientific postulates does not constitute the authorized discourse in this context.

Towards Adaptive Discrete Event Control Based on PRD, PSS and Automatic Planner

Industry 4.0 technologies integrate devices and data, bring exibility, eciency and decision making, derived from decentralization. In a post pandemic society it is mandatory to reduce human presence in production and distribution of goods. This work implements some of Industry 4.0 characteristics by combining manufacturing elements such as Cyber Physical System (CPS) with passive entities that directly aect decisions in the same automatic planning domain. Theproposal is illustrated by emulating a Block World problem, where it will be used a set of blocks with Radio Frequency Identication (RFID) each one containing its self goals, represented by predicates, an approach called PRD (Predicate inside RFID Database). A robot can identify objects by helding a RFID reader integrated with a Physical State Space (PSS). Since the robot controller has a local view of the process it is unable to compute the plan for the whole systemby itself, so the planning process must be a Cloud service. Local planning must also be taken into consideration, solving any network issues. Thus, a generic solution has to be adapted to t physical execution and domain constraints. Such solution detects changes in the physical environment and redo its plan, generating an adaptive discrete event controller.