Graph neural networks (GNNs) have drawn more and more attention from material scientists and demonstrated a strong capacity to establish connections between the structure and properties. However, with only unrelaxed structures provided as input, few GNN models can predict the thermodynamic properties of relaxed configurations with an acceptable level of error. In this work, we develop a multi-task (MT) architecture based on DimeNet + + and mixture density networks to improve the performance of

more »

... uch task. Taking CO adsorption on Cu-based single-atom alloy catalysts as an example, our method can reliably predict CO adsorption energy with a mean absolute error of 0.087 eV from the initial CO adsorption structures without costly first-principles calculations. Further, compared to other state-of-the-art GNN methods, our model exhibits improved generalization ability when predicting catalytic performance of out-of-domain configurations, built with either unseen substrate surfaces or doping species. The proposed MT GNN strategy can facilitate the catalyst discovery and optimization process.