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.
Code (1)
Tasks
Decision MakingGraph EmbeddingKnowledge Graph EmbeddingSequential Decision MakingSimilar Papers 제목 키워드 기반
On the Relationship Between KR Approaches for Explainable Planning
In this paper, we build upon notions from knowledge representation and reasoning (KR) to expand a preliminary logic-based framework that characterizes the model reconciliation problem for explainable planning. We also pr…
Scalable and Explainable Enterprise Knowledge Discovery Using Graph-Centric Hybrid Retrieval
Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis. Conventional retrieval methods based on keyword search or static embeddings often f…
Semantic SimilarityEXTRACT: Explainable Transparent Control of Bias in Embeddings
Knowledge Graphs are a widely used method to represent relations between entities in various AI applications, and Graph Embedding has rapidly become a standard technique to represent Knowledge Graphs in such a way as to …
Graph EmbeddingKnowledge Graph EmbeddingsKnowledge GraphsExplainable Link Prediction for Emerging Entities in Knowledge Graphs
Despite their large-scale coverage, cross-domain knowledge graphs invariably suffer from inherent incompleteness and sparsity. Link prediction can alleviate this by inferring a target entity, given a source entity and a …
Knowledge GraphsLink PredictionPredictionRepresentation LearningKnowledge Graph Embeddings and Explainable AI
Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces. In this chapter, we introduce the reader to the concept of knowl…
Knowledge Graph Embeddings