Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

On GNN explanability with activation patterns

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 patterns in the hidden layers to understand how the GNNs perceive the world. The problem is not to discover activation patterns that are individually highly discriminating for an output of the model. Instead, the challenge is to provide a small set of patterns that cover all input graphs. To this end, we introduce the subjective activation pattern domain. We define an effective and principled algorithm to enumerate patterns of activations in each hidden layer. The proposed approach for quantifying the interest of these patterns is rooted in information theory and is able to account for background knowledge on the input graph data. The activation patterns can then be redescribed thanks to pattern languages involving interpretable features. We show that the activation patterns 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 patterns 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03367714
Contributor : Céline Robardet Connect in order to contact the contributor
Submitted on : Wednesday, October 6, 2021 - 12:55:19 PM
Last modification on : Saturday, October 9, 2021 - 4:12:33 AM

File

hal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03367714, version 1

Citation

Luca Veyrin-Forrer, Ataollah Kamal, Stefan Duffner, Marc Plantevit, Céline Robardet. On GNN explanability with activation patterns. 2021. ⟨hal-03367714⟩

Share

Metrics

Record views

51

Files downloads

107