XInsight: Revealing Model Insights for GNNs with Flow-based Explanations

• URL: http://arxiv.org/abs/2306.04791v1
• Date: Wed, 7 Jun 2023 21:25:32 GMT
• Title: XInsight: Revealing Model Insights for GNNs with Flow-based Explanations
• Authors: Eli Laird, Ayesh Madushanka, Elfi Kraka, Corey Clark
• Abstract summary: Many high-stakes applications, such as drug discovery, require human-intelligible explanations from the models. We propose an explainability algorithm for GNNs called XInsight that generates a distribution of model explanations using GFlowNets. We show the utility of XInsight's explanations by analyzing the generated compounds using QSAR modeling.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Progress in graph neural networks has grown rapidly in recent years, with many new developments in drug discovery, medical diagnosis, and recommender systems. While this progress is significant, many networks are `black boxes' with little understanding of the `what' exactly the network is learning. Many high-stakes applications, such as drug discovery, require human-intelligible explanations from the models so that users can recognize errors and discover new knowledge. Therefore, the development of explainable AI algorithms is essential for us to reap the benefits of AI. We propose an explainability algorithm for GNNs called eXplainable Insight (XInsight) that generates a distribution of model explanations using GFlowNets. Since GFlowNets generate objects with probabilities proportional to a reward, XInsight can generate a diverse set of explanations, compared to previous methods that only learn the maximum reward sample. We demonstrate XInsight by generating explanations for GNNs trained on two graph classification tasks: classifying mutagenic compounds with the MUTAG dataset and classifying acyclic graphs with a synthetic dataset that we have open-sourced. We show the utility of XInsight's explanations by analyzing the generated compounds using QSAR modeling, and we find that XInsight generates compounds that cluster by lipophilicity, a known correlate of mutagenicity. Our results show that XInsight generates a distribution of explanations that uncovers the underlying relationships demonstrated by the model. They also highlight the importance of generating a diverse set of explanations, as it enables us to discover hidden relationships in the model and provides valuable guidance for further analysis.

Related papers

• Self-Supervised Graph Neural Networks for Enhanced Feature Extraction in Heterogeneous Information Networks [16.12856816023414]
  This paper explores the applications and challenges of graph neural networks (GNNs) in processing complex graph data brought about by the rapid development of the Internet. By introducing a self-supervisory mechanism, it is expected to improve the adaptability of existing models to the diversity and complexity of graph data.
  arXiv  Detail & Related papers  (2024-10-23T07:14:37Z)
• 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)
• A Detailed Study of Interpretability of Deep Neural Network based Top Taggers [3.8541104292281805]
  Recent developments in explainable AI (XAI) allow researchers to explore the inner workings of deep neural networks (DNNs) We explore interpretability of models designed to identify jets coming from top quark decay in high energy proton-proton collisions at the Large Hadron Collider (LHC) Our studies uncover some major pitfalls of existing XAI methods and illustrate how they can be overcome to obtain consistent and meaningful interpretation of these models.
  arXiv  Detail & Related papers  (2022-10-09T23:02:42Z)
• An Empirical Study of Retrieval-enhanced Graph Neural Networks [48.99347386689936]
  Graph Neural Networks (GNNs) are effective tools for graph representation learning. We propose a retrieval-enhanced scheme called GRAPHRETRIEVAL, which is agnostic to the choice of graph neural network models. We conduct comprehensive experiments over 13 datasets, and we observe that GRAPHRETRIEVAL is able to reach substantial improvements over existing GNNs.
  arXiv  Detail & Related papers  (2022-06-01T09:59:09Z)
• OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks [42.539085765796976]
  This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for graph neural networks (GNNs) We construct a distinct generative model and design an objective function that encourages the generative model to produce causal, compact, and faithful explanations. We show that OrphicX can effectively identify the causal semantics for generating causal explanations, significantly outperforming its alternatives.
  arXiv  Detail & Related papers  (2022-03-29T03:08:33Z)
• Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification [59.06717774425588]
  We propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field. It contains explicit pairwise factors to model output-output relations and uses a GNN backbone to model input-output relations. We conduct experiments on various datasets, which shows that our model can effectively improve the performance for semi-supervised node classification on graphs.
  arXiv  Detail & Related papers  (2021-07-27T19:47:53Z)
• Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction [2.8544822698499255]
  Graph neural networks (GNNs) remain of limited acceptance in drug discovery due to their lack of interpretability. In this work, we build three levels of benchmark datasets to quantitatively assess the interpretability of the state-of-the-art GNN models. We implement recent XAI methods in combination with different GNN algorithms to highlight the benefits, limitations, and future opportunities for drug discovery.
  arXiv  Detail & Related papers  (2021-07-01T04:49:29Z)
• Leveraging Sparse Linear Layers for Debuggable Deep Networks [86.94586860037049]
  We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. The resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.
  arXiv  Detail & Related papers  (2021-05-11T08:15:25Z)
• GraphSVX: Shapley Value Explanations for Graph Neural Networks [81.83769974301995]
  Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data. In this paper, we propose a unified framework satisfied by most existing GNN explainers. We introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs.
  arXiv  Detail & Related papers  (2021-04-18T10:40:37Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)

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.