Inductive link prediction boosts data availability and enables cross-community link prediction in ecological networks

Predicting species interactions (links) within ecological networks is crucial for advancing our understanding of ecosystem functioning and responses of communities to environmental changes. Transductive link prediction models are often used but are constrained by sparse, incomplete data and are 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. Moreover, the nature of ecological interactions (mutualistic versus antagonistic) did not strongly influence the predictability of missing links. 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. DOI https://doi.org/10.32942/X2JS75 Subjects Ecology and Evolutionary Biology

link prediction, machine learning, transfer learning, ecological networks Dates Published: 2024-08-02 13:27 Last Updated: 2025-06-04 21:25 Older Versions License CC-BY Attribution-NonCommercial-ShareAlike 4.0 International Additional Metadata Data and Code Availability Statement: The data are available in the repository set up in original publication https://osf.io/my9tv/. The full code and technical descriptions on how to run the pipeline are available on the GitHub repository https://github.com/Ecological-Complexity-Lab/eco_ILP Language: English