4 papers
Follow the MEP: Scalable Neural Representations for Minimum-Energy Path Discovery in Molecular Systems
Magnus Petersen, Gemma Roig, Roberto Covino
Characterizing conformational transitions in physical systems remains a fundamental challenge, as traditional sampling methods struggle with the high-dimensional nature of molecula…
On Explaining Knowledge Distillation: Measuring and Visualising the Knowledge Transfer Process
Gereziher Adhane, Mohammad Mahdi Dehshibi, Dennis Vetter +2
Knowledge distillation (KD) remains challenging due to the opaque nature of the knowledge transfer process from a Teacher to a Student, making it difficult to address certain issue…
Classification of freshwater snails of the genus Radomaniola with multimodal triplet networks
Dennis Vetter, Muhammad Ahsan, Diana Delicado +3
In this paper, we present our first proposal of a machine learning system for the classification of freshwater snails of the genus Radomaniola. We elaborate on the specific challen…
Fairness Through Controlled (Un)Awareness in Node Embeddings
Dennis Vetter, Jasper Forth, Gemma Roig +1
Graph representation learning is central for the application of machine learning (ML) models to complex graphs, such as social networks. Ensuring `fair' representations is essentia…