Skip to main navigation Skip to search Skip to main content

Data journeys: Explaining AI workflows through abstraction

Research output: Contribution to journal › Article › peer-review

Abstract

Artificial intelligence systems are not simply built on a single dataset or trained model. Instead, they are made by complex data science workflows involving multiple datasets, models, preparation scripts, and algorithms. Given this complexity, in order to understand these AI systems, we need to provide explanations of their functioning at higher levels of abstraction. To tackle this problem, we focus on the extraction and representation of data journeys from these workflows. A data journey is a multi-layered semantic representation of data processing activity linked to data science code and assets. We propose an ontology to capture the essential elements of a data journey and an approach to extract such data journeys. Using a corpus of Python notebooks from Kaggle, we show that we are able to capture high-level semantic data flow that is more compact than using the code structure itself. Furthermore, we show that introducing an intermediate knowledge graph representation outperforms models that rely only on the code itself. Finally, we report on a user survey to reflect on the challenges and opportunities presented by computational data journeys for explainable AI.

Original languageEnglish
Pages (from-to)1057-1083
Number of pages27
JournalSemantic Web
Volume15
Issue number4 The Role of Ontologies and Knowledge in Explainable AI
DOIs
StatePublished - Oct 4 2024
Externally publishedYes

Keywords

  • Data science analysis
  • XAI
  • data provenance
  • explainability
  • transparency
  • workflows

Fingerprint

Dive into the research topics of 'Data journeys: Explaining AI workflows through abstraction'. Together they form a unique fingerprint.

Cite this