CaLMol: Disentangled Causal Graph LLM for Molecular Relational Learning
We propose CaLMol, capable of exploiting causal molecular relationships to predict interactions for new drugs.
Sep 28, 2024
Causal-Aware Graph Neural Architecture Search under Distribution Shifts
We propose to handle the distribution shifts in the graph architecture search process by discovering and exploiting the causal relationship between graphs and architectures to search for the optimal architectures that can generalize under distribution shifts.
May 26, 2024