XGNN: Towards Model-Level Explanations of Graph Neural Networks
- URL: http://arxiv.org/abs/2006.02587v1
- Date: Wed, 3 Jun 2020 23:52:43 GMT
- Title: XGNN: Towards Model-Level Explanations of Graph Neural Networks
- Authors: Hao Yuan, Jiliang Tang, Xia Hu, Shuiwang Ji
- Abstract summary: Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information.
GNNs are mostly treated as black-boxes and lack human intelligible explanations.
We propose a novel approach, known as XGNN, to interpret GNNs at the model-level.
- Score: 113.51160387804484
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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
human intelligible explanations. Thus, they cannot be fully trusted and used in
certain application domains if GNN models cannot be explained. In this work, we
propose a novel approach, known as XGNN, to interpret GNNs at the model-level.
Our approach can provide high-level insights and generic understanding of how
GNNs work. In particular, we propose to explain GNNs by training a graph
generator so that the generated graph patterns maximize a certain prediction of
the model.We formulate the graph generation as a reinforcement learning task,
where for each step, the graph generator predicts how to add an edge into the
current graph. The graph generator is trained via a policy gradient method
based on information from the trained GNNs. In addition, we incorporate several
graph rules to encourage the generated graphs to be valid. Experimental results
on both synthetic and real-world datasets show that our proposed methods help
understand and verify the trained GNNs. Furthermore, our experimental results
indicate that the generated graphs can provide guidance on how to improve the
trained GNNs.
Related papers
- Stealing Training Graphs from Graph Neural Networks [54.52392250297907]
Graph Neural Networks (GNNs) have shown promising results in modeling graphs in various tasks.
As neural networks can memorize the training samples, the model parameters of GNNs have a high risk of leaking private training data.
We investigate a novel problem of stealing graphs from trained GNNs.
arXiv Detail & Related papers (2024-11-17T23:15:36Z) - Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks [13.655670509818144]
We propose a novel Graph structure Prompt Learning method (GPL) to enhance the training of Graph networks (GNNs)
GPL employs task-independent graph structure losses to encourage GNNs to learn intrinsic graph characteristics while simultaneously solving downstream tasks.
In experiments on eleven real-world datasets, after being trained by neural prediction, GNNs significantly outperform their original performance on node classification, graph classification, and edge tasks.
arXiv Detail & Related papers (2024-07-16T03:59:18Z) - 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) - Training Graph Neural Networks on Growing Stochastic Graphs [114.75710379125412]
Graph Neural Networks (GNNs) rely on graph convolutions to exploit meaningful patterns in networked data.
We propose to learn GNNs on very large graphs by leveraging the limit object of a sequence of growing graphs, the graphon.
arXiv Detail & Related papers (2022-10-27T16:00:45Z) - Geodesic Graph Neural Network for Efficient Graph Representation
Learning [34.047527874184134]
We propose an efficient GNN framework called Geodesic GNN (GDGNN)
It injects conditional relationships between nodes into the model without labeling.
Conditioned on the geodesic representations, GDGNN is able to generate node, link, and graph representations that carry much richer structural information than plain GNNs.
arXiv Detail & Related papers (2022-10-06T02:02:35Z) - GNNInterpreter: A Probabilistic Generative Model-Level Explanation for
Graph Neural Networks [25.94529851210956]
We propose a model-agnostic model-level explanation method for different Graph Neural Networks (GNNs) that follow the message passing scheme, GNNInterpreter.
GNNInterpreter learns a probabilistic generative graph distribution that produces the most discriminative graph pattern the GNN tries to detect.
Compared to existing works, GNNInterpreter is more flexible and computationally efficient in generating explanation graphs with different types of node and edge features.
arXiv Detail & Related papers (2022-09-15T07:45:35Z) - MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs.
We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
arXiv Detail & Related papers (2022-08-21T15:12:08Z) - Distribution Preserving Graph Representation Learning [11.340722297341788]
Graph neural network (GNN) is effective to model graphs for distributed representations of nodes and an entire graph.
We propose Distribution Preserving GNN (DP-GNN) - a GNN framework that can improve the generalizability of expressive GNN models.
We evaluate the proposed DP-GNN framework on multiple benchmark datasets for graph classification tasks.
arXiv Detail & Related papers (2022-02-27T19:16:26Z) - GPT-GNN: Generative Pre-Training of Graph Neural Networks [93.35945182085948]
Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data.
We present the GPT-GNN framework to initialize GNNs by generative pre-training.
We show that GPT-GNN significantly outperforms state-of-the-art GNN models without pre-training by up to 9.1% across various downstream tasks.
arXiv Detail & Related papers (2020-06-27T20:12:33Z)
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.