Related papers: The CAPIRE Curriculum Graph: Structural Feature En…
We introduce structural causal bottleneck models (SCBMs), a novel class of structural causal models. At the core of SCBMs lies the assumption that causal effects between high-dimensional variables only depend on low-dimensional summary…
Attribute-missing graph clustering has emerged as a significant unsupervised task, where only attribute vectors of partial nodes are available and the graph structure is intact. The related models generally follow the two-step paradigm of…
In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…
Problem: The involvement of external stakeholders in capstone projects and project courses is desirable due to its potential positive effects on the students. Capstone projects particularly profit from the inclusion of an industrial partner…
The transition from secondary to higher education represents a critical point in academic trajectories, particularly in programmes with a strong emphasis on basic sciences. Across different higher education systems, introductory Mathematics…
In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs). Our main contribution is twofold: first, we present a rigorous graph-theoretic framework describing the connecting architectures of…
A wide range of graph learning tasks, such as structure discovery, temporal graph analysis, and combinatorial optimization, focus on inferring graph structures from data, rather than making predictions on given graphs. However, the…
Artificial intelligence and semantic technologies are evolving and have been applied in various research areas, including the education domain. Higher Education institutions strive to improve students' academic performance. Early…
Linking learning resources to a structured competency framework is key to enabling competency-based search and curriculum analytics in Learning Management Systems (LMS). However, manual tagging is labor-intensive, and fully automatic…
Structural modularity is a pervasive feature of biological neural networks, which have been linked to several functional and computational advantages. Yet, the use of modular architectures in artificial neural networks has been relatively…
Machine learning pipelines for classification tasks often train a universal model to achieve accuracy across a broad range of classes. However, a typical user encounters only a limited selection of classes regularly. This disparity provides…
Educational Process Mining (EPM) is a data analysis technique that is used to improve educational processes. It is based on Process Mining (PM), which involves gathering records (logs) of events to discover process models and analyze the…
Graph Neural Networks (GNNs) have achieved great success in representing data with dependencies by recursively propagating and aggregating messages along the edges. However, edges in real-world graphs often have varying degrees of…
The design of neural architectures for structured objects is typically guided by experimental insights rather than a formal process. In this work, we appeal to kernels over combinatorial structures, such as sequences and graphs, to derive…
Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental…
Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform…
Educational Knowledge Graphs (EduKGs) organize various learning entities and their relationships to support structured and adaptive learning. Prerequisite relationships (PRs) are critical in EduKGs for defining the logical order in which…
Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely hand-designed and computationally inefficient. We study if we…
FB15k-237 mitigates the data leakage issue by excluding inverse and symmetric relationship triples, however, this has led to substantial performance degradation and slow improvement progress. Traditional approaches demonstrate limited…
Using university capstone courses to teach agile software development methodologies has become commonplace, as agile methods have gained support in professional software development. This usually means students are introduced to and work…