Global Concept Explanations for Graphs by Contrastive Learning

• URL: http://arxiv.org/abs/2404.16532v1
• Date: Thu, 25 Apr 2024 11:43:46 GMT
• Title: Global Concept Explanations for Graphs by Contrastive Learning
• Authors: Jonas Teufel, Pascal Friederich,
• Abstract summary: We propose a method to extract global concept explanations from the predictions of graph neural networks. We conduct computational experiments on synthetic and real-world graph property prediction tasks.
• Score: 0.6906005491572401
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Beyond improving trust and validating model fairness, xAI practices also have the potential to recover valuable scientific insights in application domains where little to no prior human intuition exists. To that end, we propose a method to extract global concept explanations from the predictions of graph neural networks to develop a deeper understanding of the tasks underlying structure-property relationships. We identify concept explanations as dense clusters in the self-explaining Megan models subgraph latent space. For each concept, we optimize a representative prototype graph and optionally use GPT-4 to provide hypotheses about why each structure has a certain effect on the prediction. We conduct computational experiments on synthetic and real-world graph property prediction tasks. For the synthetic tasks we find that our method correctly reproduces the structural rules by which they were created. For real-world molecular property regression and classification tasks, we find that our method rediscovers established rules of thumb. More specifically, our results for molecular mutagenicity prediction indicate more fine-grained resolution of structural details than existing explainability methods, consistent with previous results from chemistry literature. Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.

Related papers

• Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning [49.095065258759895]
  We develop a novel global explanation model RLHEX for molecular property prediction. It aligns the counterfactual explanations with human-defined principles, making the explanations more interpretable and easy for experts to evaluate. The global explanations produced by RLHEX cover 4.12% more input graphs and reduce the distance between the counterfactual explanation set and the input set by 0.47% on average across three molecular datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:16:40Z)
• Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
  Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models. We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model. We substantiate our theoretical claims with synthetic data experiments.
  arXiv  Detail & Related papers  (2024-06-01T18:01:03Z)
• Factorized Explainer for Graph Neural Networks [7.382632811417645]
  Graph Neural Networks (GNNs) have received increasing attention due to their ability to learn from graph-structured data. Post-hoc instance-level explanation methods have been proposed to understand GNN predictions. We introduce a novel factorized explanation model with theoretical performance guarantees.
  arXiv  Detail & Related papers  (2023-12-09T15:29:45Z)
• Explainable Representations for Relation Prediction in Knowledge Graphs [0.0]
  We propose SEEK, a novel approach for explainable representations to support relation prediction in knowledge graphs. It is based on identifying relevant shared semantic aspects between entities and learning representations for each subgraph. We evaluate SEEK on two real-world relation prediction tasks: protein-protein interaction prediction and gene-disease association prediction.
  arXiv  Detail & Related papers  (2023-06-22T06:18:40Z)
• On the Joint Interaction of Models, Data, and Features [82.60073661644435]
  We introduce a new tool, the interaction tensor, for empirically analyzing the interaction between data and model through features. Based on these observations, we propose a conceptual framework for feature learning. Under this framework, the expected accuracy for a single hypothesis and agreement for a pair of hypotheses can both be derived in closed-form.
  arXiv  Detail & Related papers  (2023-06-07T21:35:26Z)
• ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction [1.6114012813668934]
  Prototypical Graph Regression Self-explainable Trees (ProGReST) model combines prototype learning, soft decision trees, and Graph Neural Networks. In ProGReST, the rationale is obtained along with prediction due to the model's built-in interpretability.
  arXiv  Detail & Related papers  (2022-10-07T10:21:24Z)
• Graph neural networks for the prediction of molecular structure-property relationships [59.11160990637615]
  Graph neural networks (GNNs) are a novel machine learning method that directly work on the molecular graph. GNNs allow to learn properties in an end-to-end fashion, thereby avoiding the need for informative descriptors. We describe the fundamentals of GNNs and demonstrate the application of GNNs via two examples for molecular property prediction.
  arXiv  Detail & Related papers  (2022-07-25T11:30:44Z)
• Graph Rationalization with Environment-based Augmentations [17.733488328772943]
  Rationale identification has improved the generalizability and interpretability of neural networks on vision and language data. Existing graph pooling and/or distribution intervention methods suffer from lack of examples to learn to identify optimal graph rationales. We introduce a new augmentation operation called environment replacement that automatically creates virtual data examples to improve rationale identification.
  arXiv  Detail & Related papers  (2022-06-06T20:23:30Z)
• Convolutional Motif Kernel Networks [1.104960878651584]
  We show that our model is able to robustly learn on small datasets and reaches state-of-the-art performance on relevant healthcare prediction tasks. Our proposed method can be utilized on DNA and protein sequences.
  arXiv  Detail & Related papers  (2021-11-03T15:06:09Z)
• 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)
• 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.