Silicon Valley Community Foundation

This poster presents a practical model for transatlantic collaboration in computer science education through a blended mobility program between Karlsruhe University of Education (Germany) and Northeastern Illinois University (USA). The program funded by the European Union (Erasmus+) combines virtual and physical mobility phases, enabling students to participate in collaborative courses such as Physical Computing and Cybersecurity without interrupting their home semester. We share insights from the program's first implementation cycle, including student feedback and preliminary data on learning outcomes. This model demonstrates how EU-US cooperation can effectively support practical, hands-on computer science courses in a blended learning environment. Our work highlights challenges and best practices for designing sustainable, international blended mobility programs in computer science teacher education, offering valuable implications for institutions seeking to foster global collaboration in computer science education.

Mutation testing was proposed to identify weaknesses in test suites by repeatedly generating artificially faulty versions of the software (i.e., mutants) and determining if the test suite is sufficient to detect them (i.e., kill them). When the tests are insufficient, each surviving mutant provides an opportunity to improve the test suite. We conducted a study and found that many such surviving mutants (up to 84% for the subjects of our study) are detectable by simply augmenting existing tests with additional assertions, or assertion amplification. Moreover, we find that many of these mutants are detectable by multiple existing tests, giving developers options for how to detect them. To help with these challenges, we created a technique that performs memory-state analysis to identify candidate assertions that developers can use to detect the surviving mutants. Additionally, we build upon prior research that identifies “crossfiring” opportunities - tests that coincidentally kill multiple mutants. To this end, we developed a theoretical model that describes the varying granularities that crossfiring can occur in the existing test suite, which provide opportunities and options for how to kill surviving mutants. We operationalize this model to an accompanying technique that optimizes the assertion amplification of the existing tests to crossfire multiple mutants with fewer added assertions, optionally concentrated within fewer tests. Our experiments show that we can kill all surviving mutants that are detectable with existing test data with only 1.1% of the identified assertion candidates, and increasing by a factor of 6x, on average, the number of killed mutants from amplified tests, over tests that do not crossfire.

INTRODUCTION: Patients with chronic constipation exhibit symptoms and motility abnormalities that occur in combinations, but the nature of these combinations has not been characterized. METHODS: We calculated prevalences of combinations of symptoms (abdominal pain, infrequent defecation, incomplete evacuation, straining), abnormal motility test results (prolonged colonic transit time, low anal basal pressure, low anal squeeze pressure, poor rectal sensation, absent balloon expulsion), or both using data from 75 females and 91 males with chronic constipation. We calculated the Cluster Factor as observed prevalence of a combination of symptoms, abnormal test results or both divided by the prevalence of the combination due to chance. We calculated the conditional probabilities of combinations of symptoms, abnormal motility test results or both given the prevalence of other members of the same combination. RESULTS: Combinations of symptoms alone or abnormal motility test results alone in both males and females, and for combinations of symptoms plus abnormal motility test results in females, failed to cluster together beyond that attributable to chance alone. Males, however, showed significant clustering. Significant conditional probabilities with symptoms, and with symptoms plus abnormal motility test results was higher in males than females. Significant conditional probabilities with abnormal motility test results were not different between males and females. CONCLUSIONS: Gender-related differences in prevalences of combinations of symptoms and abnormal motility test results, of significant Cluster Factors, and of conditional probabilities indicate that chronic constipation in males reflects a fundamentally different disorder from that in females.

To evaluate the predictors of postpartum depression and to examine the effects of maternal racial identity on postpartum depression among women with low incomes in the United States. We conducted a secondary data analysis using baseline data from the Baby's First Years study, including postpartum women living below the federal poverty line who were recruited from four diverse communities in the United States. Postpartum depression symptoms were assessed using the Center for Epidemiologic Studies Depression Scale (CES-D). Logistic regressions were performed to identify associations between pre-identified postpartum depression risk factors and postpartum depression among participants, followed by predictive margins analyses to elaborate on probability of postpartum depression across different racial identity groups in the sample. The sample included 1,051 postpartum women. Almost one-half of participants identified as Black (45.9%), followed by White (20.7%), American Indian (1.8%), and Asian (1.3%). Prevalence of postpartum depression in the sample was 24%. Financial insecurity and alcohol use were positively associated with postpartum depression, whereas level of education and reported physical health were negatively associated with postpartum depression. Mothers who identified as Black had an 8.3% higher probability of postpartum depression than that of White mothers in the sample. Nurses working with populations with low income should assess social determinants of health to provide holistic mental health care. Women with low incomes should be referred to resources which account for their financial burden. Racial disparities exist in perinatal care, and birth and postpartum mental health outcomes. It is crucial to address the systemic racism faced by Black mothers experiencing postpartum depression.

<p> This paper describes a series of courses in the MS program in Software Management at Carnegie Mellon’s Silicon Valley campus. Students identify product ideas and form 4-5 person teams around their ideas, working through them for two semesters. The class covers everything from ideation of product ideas through financial models for the envisioned company, including identification of the pain points faced by prospective users, the target market, customer validation of the product ideas, creation of a product roadmap, competitive analysis, estimation of engineering effort, strategies for marketing and sales, and financial models. This paper emphasizes those aspects of the courses related to product definition and product strategy.<em><strong> </strong></em></p>

Abstract During the past decade, great significant advancements have been witnessed in the domain of automatic product description generation. As the services provided by e‐commerce platforms become diverse, it is necessary to dynamically adapt the patterns of descriptions generated. The selling point of products is an important type of product description for which the length should be as short as possible while still conveying key information. In addition, this kind of product description should be eye‐catching to the readers. Currently, product selling points are normally written by human experts. Thus, the creation and maintenance of these contents incur high costs. These costs can be significantly reduced if product selling points can be automatically generated by machines. In this paper, we report our experience developing and deploying the intelligent online selling point extraction (IOSPE) system to serve the recommendation system in the JD.com e‐commerce platform. In addition, an interactive tool is released for merchants in JD.COM, which additionally allow them to select and customize the selling points with flexibility. Since July 2020, IOSPE has become a core service for 62 key categories of products (covering more than four million products). So far, it has generated more than 0.1 billion selling points, thereby significantly scaling up the selling point creation operation and saving human labor. These IOSPE‐generated selling points have increased the click‐through rate (CTR) by 1.89% and the average duration the customers spent on the products by more than 2.03% compared to the previous practice, which are significant improvements for such a large‐scale e‐commerce platform.

Level III: Retrospective comparative.

Predicting the next interaction of a short-term interaction session is a challenging task in session-based recommendation. Almost all existing works rely on item transition patterns, and neglect the impact of user historical sessions while modeling user preference, which often leads to non-personalized recommendation. Additionally, existing personalized session-based recommenders capture user preference only based on the sessions of the current user, but ignore the useful item-transition patterns from other user's historical sessions. To address these issues, we propose a novel Heterogeneous Global Graph Neural Networks (HG-GNN) to exploit the item transitions over all sessions in a subtle manner for better inferring user preference from the current and historical sessions. To effectively exploit the item transitions over all sessions from users, we propose a novel heterogeneous global graph that contains item transitions of sessions, user-item interactions and global co-occurrence items. Moreover, to capture user preference from sessions comprehensively, we propose to learn two levels of user representations from the global graph via two graph augmented preference encoders. Specifically, we design a novel heterogeneous graph neural network (HGNN) on the heterogeneous global graph to learn the long-term user preference and item representations with rich semantics. Based on the HGNN, we propose the Current Preference Encoder and the Historical Preference Encoder to capture the different levels of user preference from the current and historical sessions, respectively. To achieve personalized recommendation, we integrate the representations of the user current preference and historical interests to generate the final user preference representation. Extensive experimental results on three real-world datasets show that our model outperforms other state-of-the-art methods.

Graph Neural Networks (GNNs) have demonstrated their powerful capability in learning representations for graph-structured data. Consequently, they have enhanced the performance of many graph-related tasks such as node classification and graph classification. However, it is evident from recent studies that GNNs are vulnerable to adversarial attacks. Their performance can be largely impaired by deliberately adding carefully created unnoticeable perturbations to the graph. Existing attacking methods often produce perturbation by adding/deleting a few edges, which might be noticeable even when the number of modified edges is small. In this paper, we propose a graph rewiring operation to perform the attack. It can affect the graph in a less noticeable way compared to existing operations such as adding/deleting edges. We then utilize deep reinforcement learning to learn the strategy to effectively perform the rewiring operations. Experiments on real-world graphs demonstrate the effectiveness of the proposed framework. To understand the proposed framework, we further analyze how its generated perturbation impacts the target model and the advantages of the rewiring operations. The implementation of the proposed framework is available at https://github.com/alge24/ReWatt.