Journal Article

Graph embedding and transfer learning can help predict potential species interaction networks despite data limitations

Caron, Dominique, Farrell, Maxwell J., Mercier, Benjamin, Barros, Ceres, Strydom, Tanya, Runghen, Rogini, Dalla Riva, Giulio V., Bouskila, Salomé, Banville, Francis, Fortin, Marie‐Josée, Pollock, Laura J., Poisot, Timothée

2023

Overview

Metawebs (networks of potential interactions within a species pool) are a powerful ion to understand how large‐scale species interaction networks are structured. Because metawebs are typically expressed at large spatial and taxonomic scales, assembling them is a tedious and costly process; predictive methods can help circumvent the limitations in data deficiencies, by providing a first approximation of metawebs. One way to improve our ability to predict metawebs is to maximize available information by using graph embeddings, as opposed to an exhaustive list of species interactions. Graph embedding is an emerging field in machine learning that holds great potential for ecological problems. Here, we outline how the challenges associated with inferring metawebs line‐up with the advantages of graph embeddings; followed by a discussion as to how the choice of the species pool has consequences on the reconstructed network, specifically as to the role of human‐made (or arbitrarily assigned) boundaries and how these may influence ecological hypotheses.

• Publisher: John Wiley & Sons, Inc,Wiley
• Subject: Biodiversity / Ecological effects / ecological networks / Embedding / Machine learning / network embedding / network macroecology / Networks / Probability / Spatial data / Species / Transfer learning