Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification
February 02, 2020 Β· Declared Dead Β· π International Cross-Domain Conference on Machine Learning and Knowledge Extraction
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Xiaoxiao Li, Joao Saude
arXiv ID
2002.00514
Category
cs.SI: Social & Info Networks
Cross-listed
cs.AI,
cs.LG
Citations
20
Venue
International Cross-Domain Conference on Machine Learning and Knowledge Extraction
Last Checked
4 months ago
Abstract
Real data collected from different applications that have additional topological structures and connection information are amenable to be represented as a weighted graph. Considering the node labeling problem, Graph Neural Networks (GNNs) is a powerful tool, which can mimic experts' decision on node labeling. GNNs combine node features, connection patterns, and graph structure by using a neural network to embed node information and pass it through edges in the graph. We want to identify the patterns in the input data used by the GNN model to make a decision and examine if the model works as we desire. However, due to the complex data representation and non-linear transformations, explaining decisions made by GNNs is challenging. In this work, we propose new graph features' explanation methods to identify the informative components and important node features. Besides, we propose a pipeline to identify the key factors used for node classification. We use four datasets (two synthetic and two real) to validate our methods. Our results demonstrate that our explanation approach can mimic data patterns used for node classification by human interpretation and disentangle different features in the graphs. Furthermore, our explanation methods can be used for understanding data, debugging GNN models, and examine model decisions.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Social & Info Networks
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Fake News Detection on Social Media: A Data Mining Perspective
R.I.P.
π»
Ghosted
Natural Scales in Geographical Patterns
R.I.P.
π»
Ghosted
Representation Learning on Graphs: Methods and Applications
R.I.P.
π»
Ghosted
The COVID-19 Social Media Infodemic
R.I.P.
π»
Ghosted
OSMnx: New Methods for Acquiring, Constructing, Analyzing, and Visualizing Complex Street Networks
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted