# The Robustness of Structural Features in Species Interaction Networks

arXiv: https://arxiv.org/abs/2502.16778 · HTML: https://mlsanity.com/paper/2502.16778/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 128 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Builds on (most cited first, 3 of 3)

- [Community detection in networks: A user guide](https://mlsanity.com/paper/1608.00163/) (2016)
- [Temporal Link Prediction Using Graph Embedding Dynamics](https://mlsanity.com/paper/2401.07516/) (2024)
- [Machine Learning on Dynamic Graphs: A Survey on Applications](https://mlsanity.com/paper/2401.08147/) (2024)

## Built on by (most cited first, 2 of 2)

- [A Review and Analysis of a Parallel Approach for Decision Tree Learning from Large Data Streams](https://mlsanity.com/paper/2505.11780/) (2025)
- [A Low-Cost Machine Learning Approach for Timber Diameter Estimation](https://mlsanity.com/paper/2507.17219/) (2025)

## Abstract (arXiv)

Species interaction networks are a powerful tool for describing ecological communities; they typically contain nodes representing species, and edges representing interactions between those species. For the purposes of drawing abstract inferences about groups of similar networks, ecologists often use graph topology metrics to summarize structural features. However, gathering the data that underlies these networks is challenging, which can lead to some interactions being missed. Thus, it is important to understand how much different structural metrics are affected by missing data. To address this question, we analyzed a database of 148 real-world bipartite networks representing four different types of species interactions (pollination, host-parasite, plant-ant, and seed-dispersal). For each network, we measured six different topological properties: number of connected components, variance in node betweenness, variance in node PageRank, largest Eigenvalue, the number of non-zero Eigenvalues, and community detection as determined by four different algorithms. We then tested how these properties change as additional edges -- representing data that may have been missed -- are added to the networks. We found substantial variation in how robust different properties were to the missing data. For example, the Clauset-Newman-Moore and Louvain community detection algorithms showed much more gradual change as edges were added than the label propagation and Girvan-Newman algorithms did, suggesting that the former are more robust. Robustness also varied for some metrics based on interaction type. These results provide a foundation for selecting network properties to use when analyzing messy ecological network data.