4 papers
Oracle-Budgeted Molecular Optimization with Short-Term Graph Memory
Jiannan Yang, Veronika Thost, Xiang Ling +1
The paper proposes a short-term graph memory module that uses an online graph neural surrogate to pre‑screen candidate molecules, allowing a fixed oracle budget to be spent on high…
Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
Kimia Hamidieh, Veronika Thost, Walter Gerych +2
Large language models (LLMs) often produce confident yet incorrect responses, and uncertainty quantification is one potential solution to more robust usage. Recent works routinely…
Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design
Jiannan Yang, Veronika Thost, Tengfei Ma
Self-supervised learning (SSL) plays a central role in molecular representation learning. Yet, many recent innovations in masking-based pretraining are introduced as heuristics and…
Understanding and Tackling Over-Dilution in Graph Neural Networks
Junhyun Lee, Veronika Thost, Bumsoo Kim +2
Message Passing Neural Networks (MPNNs) hold a key position in machine learning on graphs, but they struggle with unintended behaviors, such as over-smoothing and over-squashing, d…