Data journeys: Explaining AI workflows through abstraction
Enrico Daga,P. Groth +1 more
TL;DR: In this article , the authors 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.
read more
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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Describing and Organizing Semantic Web and Machine Learning Systems in the SWeMLS-KG
TL;DR: In this article , the authors leverage the results of a large-scale systematic mapping study collecting information about 470 SWeMLS papers and formalize these into one resource containing: (i) SWEMLS-KG, a knowledge graph including machine-actionable metadata of the papers in terms of the SWEMLS ontology.
Describing and Organizing Semantic Web and Machine Learning Systems in the SWeMLS-KG
Fajar J. Ekaputra,Majlinda Llugiqi,Marta Sabou,Andreas Ekelhart,Heiko Paulheim,Anna Breit,Artem Revenko,Laura Waltersdorfer,Kheir Eddine Farfar,Sören Auer +9 more
- 27 Mar 2023
TL;DR: In this paper , the authors performed a systematic study and analyzed nearly 500 papers published in the last decade in this area, where they focused on evaluating architectural, and application-specific features.
2
The role of ontologies and knowledge in Explainable AI
Roberto Confalonieri,Oliver Kutz,Diego Calvanese,J. Alonso-Moral,Shang-Ming Zhou +4 more
- 14 Mar 2024
TL;DR: The accepted papers explored the use of ontologies, knowledge graphs, and knowledge representation and reasoning techniques in advancing Explainable AI.
Citizen Experiences in Cultural Heritage Archives: a Data Journey
Enrico Daga
TL;DR: This study explores the integration of citizen experiences in cultural heritage archives, leveraging digital technologies to facilitate engagement, capture diverse viewpoints, and address challenges in data management, ownership, and rights.
Data journeys in popular science: Producing climate change and COVID-19 data visualizations at Scientific American
Kathleen Gregory,Laura Koesten,Regina Schuster,Torsten Möller,Sarah Davies +4 more
TL;DR: This work examines how data visualizations about climate change and COVID-19 are produced in popular science magazines, using Scientific American, an established English-language popular science magazine, as a case study, and applies the analytical concept of " data journeys" in a mixed methods study.
References
•Proceedings Article
A unified approach to interpreting model predictions
Scott M. Lundberg,Su-In Lee +1 more
- 04 Dec 2017
TL;DR: In this article, a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), is presented, which assigns each feature an importance value for a particular prediction.
•Posted Content
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.
Alejandro Barredo Arrieta,Natalia Díaz-Rodríguez,Javier Del Ser,Javier Del Ser,Adrien Bennetot,Adrien Bennetot,Siham Tabik,Alberto Barbado,Salvador García,Sergio Gil-Lopez,Daniel Molina,Richard Benjamins,Raja Chatila,Francisco Herrera +13 more
TL;DR: Previous efforts to define explainability in Machine Learning are summarized, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought, and a taxonomy of recent contributions related to the explainability of different Machine Learning models are proposed.
5.4K
Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI
Alejandro Barredo Arrieta,Natalia Díaz-Rodríguez,Javier Del Ser,Javier Del Ser,Adrien Bennetot,Adrien Bennetot,Siham Tabik,Alberto Barbado,Salvador García,Sergio Gil-Lopez,Daniel Molina,Richard Benjamins,Raja Chatila,Francisco Herrera +13 more
TL;DR: In this paper, a taxonomy of recent contributions related to explainability of different machine learning models, including those aimed at explaining Deep Learning methods, is presented, and a second dedicated taxonomy is built and examined in detail.
4.7K
IPython: A System for Interactive Scientific Computing
Fernando Perez,Brian E. Granger +1 more
- 01 May 2007
TL;DR: The IPython project as mentioned in this paper provides an enhanced interactive environment that includes, among other features, support for data visualization and facilities for distributed and parallel computation for interactive work and a comprehensive library on top of which more sophisticated systems can be built.
4.5K
The Mythos of Model Interpretability: In machine learning, the concept of interpretability is both important and slippery.
TL;DR: In this article, the authors ask whether or not a supervised machine learning model will work in deployment, and what else can it tell you about the world, besides its predictive capabilities.