On GNN explanability with activation rules

• URL: http://arxiv.org/abs/2406.11594v1
• Date: Mon, 17 Jun 2024 14:42:59 GMT
• Title: On GNN explanability with activation rules
• Authors: Luca Veyrin-Forrer, Ataollah Kamal, Stefan Duffner, Marc Plantevit, Céline Robardet,
• Abstract summary: We propose to mine activation rules in the hidden layers to understand how the GNNs perceive the world. We define an effective and principled algorithm to enumerate activations rules in each hidden layer. We show that the activation rules provide insights on the characteristics used by the GNN to classify the graphs.
• Score: 4.448117354676033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: GNNs are powerful models based on node representation learning that perform particularly well in many machine learning problems related to graphs. The major obstacle to the deployment of GNNs is mostly a problem of societal acceptability and trustworthiness, properties which require making explicit the internal functioning of such models. Here, we propose to mine activation rules in the hidden layers to understand how the GNNs perceive the world. The problem is not to discover activation rules that are individually highly discriminating for an output of the model. Instead, the challenge is to provide a small set of rules that cover all input graphs. To this end, we introduce the subjective activation pattern domain. We define an effective and principled algorithm to enumerate activations rules in each hidden layer. The proposed approach for quantifying the interest of these rules is rooted in information theory and is able to account for background knowledge on the input graph data. The activation rules can then be redescribed thanks to pattern languages involving interpretable features. We show that the activation rules provide insights on the characteristics used by the GNN to classify the graphs. Especially, this allows to identify the hidden features built by the GNN through its different layers. Also, these rules can subsequently be used for explaining GNN decisions. Experiments on both synthetic and real-life datasets show highly competitive performance, with up to 200% improvement in fidelity on explaining graph classification over the SOTA methods.

Related papers

• Global Graph Counterfactual Explanation: A Subgraph Mapping Approach [54.42907350881448]
  Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. Counterfactual explanation aims to find minimum perturbations on input graphs that change the GNN predictions. We propose GlobalGCE, a novel global-level graph counterfactual explanation method.
  arXiv  Detail & Related papers  (2024-10-25T21:39:05Z)
• Relational Graph Convolutional Networks Do Not Learn Sound Rules [13.66949379381985]
  Graph neural networks (GNNs) are frequently used to predict missing facts in knowledge graphs (KGs) Recent work has aimed to explain their predictions using Datalog, a widely used logic-based formalism. We consider one of the most popular GNN architectures for KGs, R-GCN, and we provide two methods to extract rules that explain its predictions and are sound.
  arXiv  Detail & Related papers  (2024-08-14T15:46:42Z)
• How Graph Neural Networks Learn: Lessons from Training Dynamics [80.41778059014393]
  We study the training dynamics in function space of graph neural networks (GNNs) We find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function. This finding offers new interpretable insights into when and why the learned GNN functions generalize.
  arXiv  Detail & Related papers  (2023-10-08T10:19:56Z)
• 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)
• Understanding Expressivity of GNN in Rule Learning [36.04983130825589]
  Rule learning is critical to improving knowledge graph (KG) reasoning. GNNs with tail entity scoring are unified into a common framework. We propose a novel labeling strategy to learn more rules in KG reasoning.
  arXiv  Detail & Related papers  (2023-03-22T04:49:00Z)
• Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure [17.912507269030577]
  Graph Neural Networks (GNNs) are popular models for graph learning problems. We show that GNNs can fully exploit the graph structure by themselves. In effect, GNNs can use both the hidden and explicit node features for downstream tasks.
  arXiv  Detail & Related papers  (2023-01-26T06:28:41Z)
• 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)
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning [63.97983530843762]
  Graph Neural Networks (GNNs) have achieved great success in graph representation learning. GNNs generate identical representations for graph substructures that may in fact be very different. More powerful GNNs, proposed recently by mimicking higher-order tests, are inefficient as they cannot sparsity of underlying graph structure. We propose Distance Depiction (DE) as a new class of graph representation learning.
  arXiv  Detail & Related papers  (2020-08-31T23:15:40Z)
• 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)
• XGNN: Towards Model-Level Explanations of Graph Neural Networks [113.51160387804484]
  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.
  arXiv  Detail & Related papers  (2020-06-03T23:52:43Z)

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.