GNNAnatomy: Systematic Generation and Evaluation of Multi-Level Explanations for Graph Neural Networks
- URL: http://arxiv.org/abs/2406.04548v1
- Date: Thu, 6 Jun 2024 23:09:54 GMT
- Title: GNNAnatomy: Systematic Generation and Evaluation of Multi-Level Explanations for Graph Neural Networks
- Authors: Hsiao-Ying Lu, Yiran Li, Ujwal Pratap Krishna Kaluvakolanu Thyagarajan, Kwan-Liu Ma,
- Abstract summary: Graph Neural Networks (GNNs) have proven highly effective in various machine learning (ML) tasks involving graphs, such as node/graph classification and link prediction.
Explaining the decisions made by GNNs poses challenges because of the aggregated relational information based on graph structure, leading to complex data transformations.
We introduce GNNAnatomy, a model- and dataset-agnostic visual analytics system designed to facilitate the generation and evaluation of multi-level explanations for GNNs.
- Score: 20.05098366613674
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Graph Neural Networks (GNNs) have proven highly effective in various machine learning (ML) tasks involving graphs, such as node/graph classification and link prediction. However, explaining the decisions made by GNNs poses challenges because of the aggregated relational information based on graph structure, leading to complex data transformations. Existing methods for explaining GNNs often face limitations in systematically exploring diverse substructures and evaluating results in the absence of ground truths. To address this gap, we introduce GNNAnatomy, a model- and dataset-agnostic visual analytics system designed to facilitate the generation and evaluation of multi-level explanations for GNNs. In GNNAnatomy, we employ graphlets to elucidate GNN behavior in graph-level classification tasks. By analyzing the associations between GNN classifications and graphlet frequencies, we formulate hypothesized factual and counterfactual explanations. To validate a hypothesized graphlet explanation, we introduce two metrics: (1) the correlation between its frequency and the classification confidence, and (2) the change in classification confidence after removing this substructure from the original graph. To demonstrate the effectiveness of GNNAnatomy, we conduct case studies on both real-world and synthetic graph datasets from various domains. Additionally, we qualitatively compare GNNAnatomy with a state-of-the-art GNN explainer, demonstrating the utility and versatility of our design.
Related papers
- DGNN: Decoupled Graph Neural Networks with Structural Consistency
between Attribute and Graph Embedding Representations [62.04558318166396]
Graph neural networks (GNNs) demonstrate a robust capability for representation learning on graphs with complex structures.
A novel GNNs framework, dubbed Decoupled Graph Neural Networks (DGNN), is introduced to obtain a more comprehensive embedding representation of nodes.
Experimental results conducted on several graph benchmark datasets verify DGNN's superiority in node classification task.
arXiv Detail & Related papers (2024-01-28T06:43:13Z) - DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
We propose DEGREE to provide a faithful explanation for GNN predictions.
By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction.
We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
arXiv Detail & Related papers (2023-05-22T10:29:52Z) - Structural Explanations for Graph Neural Networks using HSIC [21.929646888419914]
Graph neural networks (GNNs) are a type of neural model that tackle graphical tasks in an end-to-end manner.
The complicated dynamics of GNNs make it difficult to understand which parts of the graph features contribute more strongly to the predictions.
In this study, a flexible model agnostic explanation method is proposed to detect significant structures in graphs.
arXiv Detail & Related papers (2023-02-04T09:46:47Z) - 2-hop Neighbor Class Similarity (2NCS): A graph structural metric
indicative of graph neural network performance [4.051099980410583]
Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data across numerous domains.
On heterophilous graphs, in which different-type nodes are likely connected, GNNs perform less consistently.
We introduce 2-hop Neighbor Class Similarity (2NCS), a new quantitative graph structural property that correlates with GNN performance more strongly and consistently than alternative metrics.
arXiv Detail & Related papers (2022-12-26T16:16:51Z) - Discovering the Representation Bottleneck of Graph Neural Networks from
Multi-order Interactions [51.597480162777074]
Graph neural networks (GNNs) rely on the message passing paradigm to propagate node features and build interactions.
Recent works point out that different graph learning tasks require different ranges of interactions between nodes.
We study two common graph construction methods in scientific domains, i.e., emphK-nearest neighbor (KNN) graphs and emphfully-connected (FC) graphs.
arXiv Detail & Related papers (2022-05-15T11:38:14Z) - Graph Neural Networks for Graphs with Heterophily: A Survey [98.45621222357397]
We provide a comprehensive review of graph neural networks (GNNs) for heterophilic graphs.
Specifically, we propose a systematic taxonomy that essentially governs existing heterophilic GNN models.
We discuss the correlation between graph heterophily and various graph research domains, aiming to facilitate the development of more effective GNNs.
arXiv Detail & Related papers (2022-02-14T23:07:47Z) - Edge-Level Explanations for Graph Neural Networks by Extending
Explainability Methods for Convolutional Neural Networks [33.20913249848369]
Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property prediction.
We extend explainability methods for CNNs, such as Local Interpretable Model-Agnostic Explanations (LIME), Gradient-Based Saliency Maps, and Gradient-Weighted Class Activation Mapping (Grad-CAM) to GNNs.
The experimental results indicate that the LIME-based approach is the most efficient explainability method for multiple tasks in the real-world situation, outperforming even the state-of-the
arXiv Detail & Related papers (2021-11-01T06:27:29Z) - Topological Relational Learning on Graphs [2.4692806302088868]
Graph neural networks (GNNs) have emerged as a powerful tool for graph classification and representation learning.
We propose a novel topological relational inference (TRI) which allows for integrating higher-order graph information to GNNs.
We show that the new TRI-GNN outperforms all 14 state-of-the-art baselines on 6 out 7 graphs and exhibit higher robustness to perturbations.
arXiv Detail & Related papers (2021-10-29T04:03:27Z) - A Unified View on Graph Neural Networks as Graph Signal Denoising [49.980783124401555]
Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data.
In this work, we establish mathematically that the aggregation processes in a group of representative GNN models can be regarded as solving a graph denoising problem.
We instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes.
arXiv Detail & Related papers (2020-10-05T04:57:18Z) - Understanding Graph Isomorphism Network for rs-fMRI Functional
Connectivity Analysis [49.05541693243502]
We develop a framework for analyzing fMRI data using the Graph Isomorphism Network (GIN)
One of the important contributions of this paper is the observation that the GIN is a dual representation of convolutional neural network (CNN) in the graph space.
We exploit CNN-based saliency map techniques for the GNN, which we tailor to the proposed GIN with one-hot encoding.
arXiv Detail & Related papers (2020-01-10T23:40:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.