Training physics-informed neural networks (PINNs) for forward problems often suffers from severe convergence issues, hindering the propagation of information from regions where the desired solution is well-defined. Haitsiukevich and Ilin (2023) proposed an ensemble approach that extends the active training domain of each PINN based on i) ensemble consensus and ii) vicinity to (pseudo-)labeled points, thus ensuring that the information from the initial condition successfully propagates to the interior of the computational domain.In this work, we suggest replacing the ensemble by a Bayesian PINN, and consensus by an evaluation of the PINN’s posterior variance. Our experiments show that this mathematically principled approach outperforms the ensemble on a set of benchmark problems and is competitive with PINN ensembles trained with combinations of Adam and LBFGS.

Retrieval over knowledge graphs is typically performed using specialized, complex query languages such as SPARQL.We propose a novel system, Ontology and Semantic Exploration Toolkit (OnSET), that allows novice users to quickly build queries with visual user guidance provided by topic modeling and semantic search throughout the application.OnSET enables users without prior knowledge of the ontology or networked knowledge to start exploring topics of interest over knowledge graphs, including the retrieval and detailed exploration of prototypical sub-graphs and their instances.Existing systems either focus on direct graph exploration or do not foster further exploration of the result set.We, however, provide a node-based editor that can extend these missing properties of existing systems to support search over large ontologies with subgraph instances.Furthermore, OnSET combines efficient and open platforms to deploy the system on commodity hardware.

In recent decades, computer science (CS) has undergone remarkable growth and diversification. Creating attractive, social, or hands-on games has already been identified as a possible approach to get teenagers and young adults interested in CS. However, overcoming the global gap between the interest and participation of men and women in CS is still a worldwide problem. To address this challenge, we present a multiplayer game that is used in a workshop setting to motivate girls to program through a 3D game environment. The paper aims to expand the educational landscape within computer science education by offering a motivating and engaging platform for young women to explore programming quests in a collaborative environment. The study involved 235 girls and 50 coaches for the workshop evaluation and a subset of 20 participants for an in-game analysis. In this paper, we explore the engagement in programming and assess the cognitive workload while playing and solving programming quests within the game, as well as the learning experience and the outcome. The results show that the positive outcomes of the workshop underscore the effectiveness of a game-based collaborative learning approach to get girls interested in computer science activities. The variety of solutions found for the different tasks demonstrates the creativity and problem-solving skills of the participants and underlines the effectiveness of the workshop in promoting critical thinking and computational skills.

Federated learning allows training machine learning (ML) models without central consolidation of the raw data. Variants of such federated learning systems enable privacy-preserving ML, and address data ownership and/or sharing constraints. However, existing work mostly adopt data-parallel parameter-server architectures for mini-batch training, require manual construction of federated runtime plans, and largely ignore the broad variety of data preparation, ML algorithms, and model debugging. Over the last years, we extended Apache SystemDS by an additional federated runtime backend for federated linear-algebra programs, federated parameter servers, and federated data preparation. In this paper, we share the system-level compiler and runtime integration, new features such as multi-tenant federated learning, selected federated primitives, multi-key homomorphic encryption, and our monitoring infrastructure. Our demonstrator showcases how composite ML pipelines can be compiled into federated runtime plans with low overhead.

Data science workflows are largely exploratory, dealing with under-specified objectives, open-ended problems, and unknown business value. Therefore, little investment is made in systematic acquisition, integration, and pre-processing of data. This lack of infrastructure results in redundant manual effort and computation. Furthermore, central data consolidation is not always technically or economically desirable or even feasible (e.g., due to privacy, and/or data ownership). The ExDRa system aims to provide system infrastructure for this exploratory data science process on federated and heterogeneous, raw data sources. Technical focus areas include (1) ad-hoc and federated data integration on raw data, (2) data organization and reuse of intermediates, and (3) optimization of the data science lifecycle, under awareness of partially accessible data. In this paper, we describe use cases, the overall system architecture, selected features of SystemDS' new federated backend (for federated linear algebra programs, federated parameter servers, and federated data preparation), as well as promising initial results. Beyond existing work on federated learning, ExDRa focuses on enterprise federated ML and related data pre-processing challenges. In this context, federated ML has the potential to create a more fine-grained spectrum of data ownership and thus, even new markets.