.png){kind=icon}
返回
Explaining Deep Graph Networks via Input Perturbation
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3165618.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep graph networks (DGNs) are a family of machine learning models for structured data which are finding heavy application in life sciences (drug repurposing, molecular property predictions) and on social network data (recommendation systems). The privacy and safety-critical nature of such domains motivates the need for developing effective explainability methods for this family of models. So far, progress in this field has been challenged by the combinatorial nature and complexity of graph structures. In this respect, we present a novel local explanation framework specifically tailored to graph data and DGNs. Our approach leverages reinforcement learning to generate meaningful local perturbations of the input graph, whose prediction we seek an interpretation for. These perturbed data points are obtained by optimizing a multiobjective score taking into account similarities both at a structural level as well as at the level of the deep model outputs. By this means, we are able to populate a set of informative neighboring samples for the query graph, which is then used to fit an interpretable model for the predictive behavior of the deep network locally to the query graph prediction. We show the effectiveness of the proposed explainer by a qualitative analysis on two chemistry datasets, TOX21 and Estimated SOLubility (ESOL) and by quantitative results on a benchmark dataset for explanations, CYCLIQ.
Keyword:
Predictive models
Data models
Task analysis
Analytical models
Perturbation methods
Convolution
Training
Deep graph networks (DGNs)
deep reinforcement learning
explainable artificial intelligence (XAI)
graph
interpretability
期刊
IF:
8.9
论文数:
7.5K
被引数:
7.2W
机构
引用论文
Reconstructing spatially extended brain sources via enforcing multiple transform sparseness.png)
NeuroImage
NeuroImageIF0
PREAI
分享收藏Intercellular Adhesion Molecule 1 (ICAM-1) Gene Variant is Associated with Coronary Artery Calcification Independent of Soluble ICAM-1 Levels细胞间粘附分子1 (ICAM-1) 基因变异与冠状动脉钙化相关，与可溶性ICAM-1水平无关
PREAI
分享收藏
分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Cell-free Protein Synthesis in an Autoinduction System for NMR Studies of Protein–Protein Interactions用于NMR研究蛋白质-蛋白质相互作用的自动诱导系统中的无细胞蛋白质合成
PREAI
分享收藏
查看更多内容