Explainable Knowledge Graph Embedding: Inference Reconciliation for Knowledge Inferences Supporting Robot Actions

Learned knowledge graph representations supporting robots contain a wealth of domain knowledge that drives robot behavior. However, there does not exist an inference reconciliation framework that expresses how a knowledge graph representation affects a robot's sequential decision making. We use a pedagogical approach to explain the inferences of a learned, black-box knowledge graph representation, a knowledge graph embedding. Our interpretable model uses a decision tree classifier to locally approximate the predictions of the black-box model and provides natural language explanations interpretable by non-experts. Results from our algorithmic evaluation affirm our model design choices, and the results of our user studies with non-experts support the need for the proposed inference reconciliation framework. Critically, results from our simulated robot evaluation indicate that our explanations enable non-experts to correct erratic robot behaviors due to nonsensical beliefs within the black-box.

Authors

• Angel Andres Daruna
• Devleena Das
• Sonia Chernova

Keywords

• Natural languages
• Closed box
• Predictive models
• Approximation algorithms
• Prediction algorithms
• Classification algorithms
• Behavioral sciences
• Active Support
• Knowledge Inference
• Knowledge Graph Embedding
• Decision Tree
• Natural Language
• Nonsense
• User Study
• Model Interpretation
• Robot Behavior
• Differences In Preferences
• Latent Model
• Latent Space
• First Search
• Head And Tail
• User Preferences
• Latent Features
• Interpretation Of Features
• Accurate Correction
• Task Planning
• Improve Success Rates
• Relative Path
• Breadth-first Search
• Explainable Artificial Intelligence
• Causal Questions
• Execution Environment
• Robot Interaction
• Non-expert Users
• Inference Performance
• Task Execution