Interpretability of Graph Neural Networks to Assess Effects of Global Change Drivers on Ecological Networks
Not on the map. Why?
Abstract (arXiv)
Pollinators play a crucial role for plant reproduction, either in natural ecosystem or in human-modified landscape. Global change drivers,including climate change or land use modifications, can alter the plant-pollinator interactions. To assess the potential influence of global change drivers on pollination, large-scale interactions, climate and land use data are required. While recent machine learning methods, such as graph neural networks (GNNs), allow the analysis of such datasets, interpreting their results can be challenging. We explore existing methods for interpreting GNNs in order to highlight the effects of various environmental covariates on pollination network connectivity. An extensive simulation study is performed to confirm whether these methods can detect the interactive effect between a covariate and a genus of plant on connectivity, and whether the application of debiasing techniques influences the estimation of these effects. An application on the Spipoll dataset, with and without accounting for sampling effects, highlights the potential impact of land use on network connectivity and shows that accounting for sampling effects partially alters the estimation of these effects.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 68 references that are in the map. First posted on arXiv 19 Mar 2025.
Builds on
28 of 68 references.
References · 28
- 2017Graph Attention Networkscited by 8,923
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2016Variational Graph Auto-Encoderscited by 1,382
- 2017SmoothGrad: removing noise by adding noisecited by 1,109
- 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
- 2020Parameterized Explainer for Graph Neural Networkcited by 426
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
- 2016Top-down Neural Attention by Excitation Backpropcited by 321
- 2020A Survey on Neural Network Interpretabilitycited by 291
- 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
16 more
- 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
- 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
- 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
- 2019Explainability Techniques for Graph Convolutional Networkscited by 161
- 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
- 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
- 2020On Interpretability of Artificial Neural Networks: A Surveycited by 88
- 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
- 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
- 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
- 2017A statistical interpretation of spectral embedding: the generalised random dot product graphcited by 55
- 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
- 2022Global Counterfactual Explainer for Graph Neural Networkscited by 30
- 2023Distill n' Explain: explaining graph neural networks using simple surrogatescited by 18
- 2023Evaluating Link Prediction Explanations for Graph Neural Networkscited by 2
- 2024Bipartite Graph Variational Auto-Encoder with Fair Latent Representation to Account for Sampling Bias in Ecological Networkscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.