Graph neural networkPrediction rankingStructural dependencyWe explain GNNs via preserving prediction ranking, enhancing fidelity of explanation.We introduce a designed differential ranking loss that guides the optimizing process.We propose a graph transformation schema to explicitly model edge dependencies....
CGMega detects gene modules based on a model-agnostic neural network interpretation approach (Fig.1b), and these gene modules consist of two parts: i) a core subgraph consisting of the most influential pairwise relationships for the prediction of cancer gene, and ii) 15-dimensional importance s...
2.3 Explanation of graph neural networks with a global view 虽然GNNExplainer[53] 所提供的解释能保持局部的可信度,但它不能帮助理解模型在整个群体中的总体情况。目前基于GNN 的模型已经被应用具有数百万个实例的图数据,对于如此庞大的数据集,逐一应用局部解释的成本会非常高昂。另一方面,从全局视角解释模型可以增...
NF-GNN:Network Flow Graph Neural Networks for Malware Detection and Classification. (不是CFG) 本文提出CFGExpaliner,是首个针对基于GNN进行恶意软件分类(注意不是检测)的可解释性工作。CFGExplainer在CFG中提取出得到分类结果的关键子图,并对子图内节点进行重要性排序。作者通过与三个常见的GNN解释方法:GNN...
2.2Explanation via Feature Information 2.3 Multi-instance explanations through graph prototypes 3. Experiments 4. Conclusion 1.Introduction 图神经网络(Graph Neural Network), 作为深度学习领域最热门的方向之一,相关论文在各大顶会层出不穷. 但是,图神经网络的解释性问题没有得到较多的关注.图神经网络的解释性是...
(10) in the Methods section. In this regard, if there is no strong correlation, the only possible explanation would be that the contribution of grain orientation outweighs the contribution of grain size. Figure6dshows the distribution of the R2factor among the 492 microstructure graphs. It can...
XGNN: Towards Model-Level Explanations of Graph Neural Networks. KDD 2020. paper Hao Yuan, Jiliang Tang, Xia Hu, Shuiwang Ji. Contrastive Graph Neural Network Explanation. ICML 2020. paper Lukas Faber, Amin K. Moghaddam, Roger Wattenhofer. Interpreting Graph Neural Networks for NLP With Differen...
内容提示: GNNExplainer: Generating Explanationsfor Graph Neural NetworksRex Ying † Dylan Bourgeois †,‡ Jiaxuan You † Marinka Zitnik † Jure Leskovec †† Department of Computer Science, Stanford University‡ Robust.AI{rexying, dtsbourg, jiaxuan, marinka, jure}@cs.stanford.edu...
ratios=[0.1*iforiinrange(1,11)]acc_auc=refine.evaluate_acc(ratios).mean()racall=refine.evaluate_recall(topk=5)refine.visualize(vis_ratio=0.3)# visualize the explanation To evaluate ReFine-FT and ReFine in the testing datasets, run
Spatial transcriptomics (ST) data provide profiles of gene expression along with information on spatial location to be fed into a graph neural network (GNN). The choice of GNN significantly influences the quality of the generated latent embedding. For a thorough analysis of the data, principal ...