Memorization is an essential functionality that enables today's machine learning algorithms
to provide a high quality of learning and reasoning for each prediction. Memorization gives …

Recent years have seen a surge in research on dynamic graph representation learning,
which aims to model temporal graphs that are dynamic and evolving constantly over time …

Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded
devices for real-time on-device Machine Learning (ML). While many acknowledge the …

Knowledge graphs are an expressive and widely used data structure due to their ability to
integrate data from different domains in a sensible and machine-readable way. Thus, they …

Relational representation learning has lately received an increase in interest due to its
flexibility in modeling a variety of systems like interacting particles, materials and industrial …

Many of today's most interesting questions involve understanding and interpreting complex
relationships within graph-based structures. For instance, in materials science, predicting …

The rapid evolution of distributed networks and the increasing complexity of modern
software systems have created significant challenges for traditional software testing …

The growing complexity of distributed network systems has brought forth the need for
advanced software testing strategies to ensure reliability and high performance. Traditional …

In the realm of software quality assurance, traditional testing methods often struggle to meet
the demands of modern distributed systems, which are characterized by dynamic …

The rapid advancement of autonomous systems has led to an increased demand for efficient
resource allocation strategies that can adapt to dynamic environments. This paper explores …