paper-with-me

홈 › Papers

L2XGNN: Learning to Explain Graph Neural Networks

2022-09-28 · Giuseppe Serra, Mathias Niepert

Graph Neural Networks (GNNs) are a popular class of machine learning models. Inspired by the learning to explain (L2X) paradigm, we propose L2XGNN, a framework for explainable GNNs which provides faithful explanations by design. L2XGNN learns a mechanism for selecting explanatory subgraphs (motifs) which are exclusively used in the GNNs message-passing operations. L2XGNN is able to select, for each input graph, a subgraph with specific properties such as being sparse and connected. Imposing such constraints on the motifs often leads to more interpretable and effective explanations. Experiments on several datasets suggest that L2XGNN achieves the same classification accuracy as baseline methods using the entire input graph while ensuring that only the provided explanations are used to make predictions. Moreover, we show that L2XGNN is able to identify motifs responsible for the graph's properties it is intended to predict.

📄 PDF Abstract BibTeX arXiv:2209.14402

Code (1)

giuseppeserra93/l2xgnn 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Extracting Interpretable Logic Rules from Graph Neural Networks

2025-03-25 · Chuqin Geng, Zhaoyue Wang, Ziyu Zhao, Haolin Ye 외

Graph neural networks (GNNs) operate over both input feature spaces and combinatorial graph structures, making it challenging to understand the rationale behind their predictions. As GNNs gain widespread popularity and d…

Drug DesignDrug Discovery

Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia

2025-09-23 · Niharika Tewari, Nguyen Linh Dan Le, Mujie Liu, Jing Ren 외 arxiv

Dementia is a progressive neurodegenerative disorder with multiple etiologies, including Alzheimer's disease, Parkinson's disease, frontotemporal dementia, and vascular dementia. Its clinical and biological heterogeneity…

XGNN: Towards Model-Level Explanations of Graph Neural Networks

2020-06-03 · Hao Yuan, Jiliang Tang, Xia Hu, Shuiwang Ji

Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information, which have achieved promising performance on many graph tasks. However, GNNs are mostly treated as black-boxes and lack…

Graph Generationvalid

CloudNine: Analyzing Meteorological Observation Impact on Weather Prediction Using Explainable Graph Neural Networks

2024-02-21 · Hyeon-Ju Jeon, Jeon-Ho Kang, In-Hyuk Kwon, O-Joun Lee

The impact of meteorological observations on weather forecasting varies with sensor type, location, time, and other environmental factors. Thus, quantitative analysis of observation impacts is crucial for effective and e…

State EstimationWeather Forecasting

A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics

2022-07-26 · Yiqiao Li, Jianlong Zhou, Sunny Verma, Fang Chen

Graph neural networks (GNNs) have demonstrated a significant boost in prediction performance on graph data. At the same time, the predictions made by these models are often hard to interpret. In that regard, many efforts…