Inductive link prediction facilitates the discovery of missing links and enables cross-community inference in ecological networks

Barry Biton, Rami Puzis, Shai Pilosof 

Predicting species interactions (links) within ecological networks is crucial for advancing our understanding of ecosystem functioning and responses of communities to environmental changes. Traditional link prediction models are often constrained by sparse, incomplete data and are typically limited to single networks. We address these issues using an inductive link prediction (ILP) approach. We evaluated the model performance on 538 networks across four community types: plant-seed disperser, plant-pollinator, host-parasite, and plant-herbivore. By pooling data across communities and applying transfer learning, our model predicts interactions within and between ecological networks. The ILP model achieved higher precision and F1 scores than transductive models. However, cross-community prediction efficacy varies, with plant-seed disperser and host-parasite networks performing better than plant-pollinator and plant-herbivore networks as training and test sets. Finally, leveraging ILP’s generalizability, we developed a pre-trained model that ecologists can readily use to make instant predictions for their networks. This study highlights ILP’s potential to improve the prediction of ecological interactions, enabling generalization across diverse ecological contexts and bridging critical data gaps.