Graph Counterfactual Explainable AI via Latent Space Traversal

• URL: http://arxiv.org/abs/2501.08850v1
• Date: Wed, 15 Jan 2025 15:04:10 GMT
• Title: Graph Counterfactual Explainable AI via Latent Space Traversal
• Authors: Andreas Abildtrup Hansen, Paraskevas Pegios, Anna Calissano, Aasa Feragen,
• Abstract summary: Counterfactual explanations aim to explain predictions by finding the ''nearest'' in-distribution alternative input. We propose a method to generate counterfactual explanations for any differentiable black-box graph classifier. We empirically validate the approach on three graph datasets, showing that our model is consistently high-performing and more robust than the baselines.
• Score: 4.337339380445765
• License:
• Abstract: Explaining the predictions of a deep neural network is a nontrivial task, yet high-quality explanations for predictions are often a prerequisite for practitioners to trust these models. Counterfactual explanations aim to explain predictions by finding the ''nearest'' in-distribution alternative input whose prediction changes in a pre-specified way. However, it remains an open question how to define this nearest alternative input, whose solution depends on both the domain (e.g. images, graphs, tabular data, etc.) and the specific application considered. For graphs, this problem is complicated i) by their discrete nature, as opposed to the continuous nature of state-of-the-art graph classifiers; and ii) by the node permutation group acting on the graphs. We propose a method to generate counterfactual explanations for any differentiable black-box graph classifier, utilizing a case-specific permutation equivariant graph variational autoencoder. We generate counterfactual explanations in a continuous fashion by traversing the latent space of the autoencoder across the classification boundary of the classifier, allowing for seamless integration of discrete graph structure and continuous graph attributes. We empirically validate the approach on three graph datasets, showing that our model is consistently high-performing and more robust than the baselines.

Related papers

• Fine-grained Graph Rationalization [51.293401030058085]
  We propose fine-grained graph rationalization (FIG) for graph machine learning. Our idea is driven by the self-attention mechanism, which provides rich interactions between input nodes. Our experiments involve 7 real-world datasets, and the proposed FIG shows significant performance advantages compared to 13 baseline methods.
  arXiv  Detail & Related papers  (2023-12-13T02:56:26Z)
• Discrete Graph Auto-Encoder [52.50288418639075]
  We introduce a new framework named Discrete Graph Auto-Encoder (DGAE) We first use a permutation-equivariant auto-encoder to convert graphs into sets of discrete latent node representations. In the second step, we sort the sets of discrete latent representations and learn their distribution with a specifically designed auto-regressive model.
  arXiv  Detail & Related papers  (2023-06-13T12:40:39Z)
• CLEAR: Generative Counterfactual Explanations on Graphs [60.30009215290265]
  We study the problem of counterfactual explanation generation on graphs. A few studies have explored counterfactual explanations on graphs, but many challenges of this problem are still not well-addressed. We propose a novel framework CLEAR which aims to generate counterfactual explanations on graphs for graph-level prediction models.
  arXiv  Detail & Related papers  (2022-10-16T04:35:32Z)
• Node Copying: A Random Graph Model for Effective Graph Sampling [35.957719744856696]
  We introduce the node copying model for constructing a distribution over graphs. We show the usefulness of the copying model in three tasks. We employ our proposed model to mitigate the effect of adversarial attacks on the graph topology.
  arXiv  Detail & Related papers  (2022-08-04T04:04:49Z)
• Reinforced Causal Explainer for Graph Neural Networks [112.57265240212001]
  Explainability is crucial for probing graph neural networks (GNNs) We propose a reinforcement learning agent, Reinforced Causal Explainer (RC-Explainer) RC-Explainer generates faithful and concise explanations, and has a better power to unseen graphs.
  arXiv  Detail & Related papers  (2022-04-23T09:13:25Z)
• Neighborhood Random Walk Graph Sampling for Regularized Bayesian Graph Convolutional Neural Networks [0.6236890292833384]
  In this paper, we propose a novel algorithm called Bayesian Graph Convolutional Network using Neighborhood Random Walk Sampling (BGCN-NRWS) BGCN-NRWS uses a Markov Chain Monte Carlo (MCMC) based graph sampling algorithm utilizing graph structure, reduces overfitting by using a variational inference layer, and yields consistently competitive classification results compared to the state-of-the-art in semi-supervised node classification.
  arXiv  Detail & Related papers  (2021-12-14T20:58:27Z)
• Explaining GNN over Evolving Graphs using Information Flow [12.33508497537769]
  Graph neural networks (GNN) are the current state-of-the-art for these applications, and yet remain obscure to humans. We propose an axiomatic attribution method to uniquely decompose the change in a prediction to paths on computation graphs. We formulate a novel convex optimization problem to optimally select the paths that explain the prediction evolution.
  arXiv  Detail & Related papers  (2021-11-19T04:29:38Z)
• Node Classification Meets Link Prediction on Knowledge Graphs [16.37145148171519]
  We study the problems of transductive node classification over incomplete graphs and link prediction over graphs with node features. Our model performs very strongly when compared to the respective state-of-the-art models for node classification and link prediction.
  arXiv  Detail & Related papers  (2021-06-14T10:52:52Z)
• ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning [65.15423587105472]
  We present a new generative and structured commonsense-reasoning task (and an associated dataset) of explanation graph generation for stance prediction. Specifically, given a belief and an argument, a model has to predict whether the argument supports or counters the belief and also generate a commonsense-augmented graph that serves as non-trivial, complete, and unambiguous explanation for the predicted stance. A significant 83% of our graphs contain external commonsense nodes with diverse structures and reasoning depths.
  arXiv  Detail & Related papers  (2021-04-15T17:51:36Z)
• Line Graph Neural Networks for Link Prediction [71.00689542259052]
  We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. In this formalism, a link prediction problem is converted to a graph classification task. We propose to seek a radically different and novel path by making use of the line graphs in graph theory. In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
  arXiv  Detail & Related papers  (2020-10-20T05:54:31Z)

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.