Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Veni, Vidi, Vici: Solving the Myriad of Challenges before Knowledge Graph Learning

Jeffrey Sardina, Luca Costabello, Christophe Guéret

TL;DR

This paper identifies four core deficiencies hindering effective human-KG interaction: lack of expert knowledge integration, instability to extreme topological variation, neglect of uncertainty and relevance, and lack of explainability. It argues that addressing these issues in isolation constrains progress and proposes a holistic Veni, Vidi, Vici framework to unify problem representations, analysis, and solution design. The framework emphasizes placing problems in a common conceptual space, analyzing why they were separated, and generating integrated, testable solutions that empower both humans and KG-learning systems. With potential applicability beyond KG learning, the approach advocates a shift from divide-and-conquer to holistic co-empowerment in AI systems dealing with complex, multi-faceted knowledge graphs.

Abstract

Knowledge Graphs (KGs) have become increasingly common for representing large-scale linked data. However, their immense size has required graph learning systems to assist humans in analysis, interpretation, and pattern detection. While there have been promising results for researcher- and clinician- empowerment through a variety of KG learning systems, we identify four key deficiencies in state-of-the-art graph learning that simultaneously limit KG learning performance and diminish the ability of humans to interface optimally with these learning systems. These deficiencies are: 1) lack of expert knowledge integration, 2) instability to node degree extremity in the KG, 3) lack of consideration for uncertainty and relevance while learning, and 4) lack of explainability. Furthermore, we characterise state-of-the-art attempts to solve each of these problems and note that each attempt has largely been isolated from attempts to solve the other problems. Through a formalisation of these problems and a review of the literature that addresses them, we adopt the position that not only are deficiencies in these four key areas holding back human-KG empowerment, but that the divide-and-conquer approach to solving these problems as individual units rather than a whole is a significant barrier to the interface between humans and KG learning systems. We propose that it is only through integrated, holistic solutions to the limitations of KG learning systems that human and KG learning co-empowerment will be efficiently affected. We finally present our "Veni, Vidi, Vici" framework that sets a roadmap for effectively and efficiently shifting to a holistic co-empowerment model in both the KG learning and the broader machine learning domain.

Veni, Vidi, Vici: Solving the Myriad of Challenges before Knowledge Graph Learning

TL;DR

This paper identifies four core deficiencies hindering effective human-KG interaction: lack of expert knowledge integration, instability to extreme topological variation, neglect of uncertainty and relevance, and lack of explainability. It argues that addressing these issues in isolation constrains progress and proposes a holistic Veni, Vidi, Vici framework to unify problem representations, analysis, and solution design. The framework emphasizes placing problems in a common conceptual space, analyzing why they were separated, and generating integrated, testable solutions that empower both humans and KG-learning systems. With potential applicability beyond KG learning, the approach advocates a shift from divide-and-conquer to holistic co-empowerment in AI systems dealing with complex, multi-faceted knowledge graphs.

Abstract

Knowledge Graphs (KGs) have become increasingly common for representing large-scale linked data. However, their immense size has required graph learning systems to assist humans in analysis, interpretation, and pattern detection. While there have been promising results for researcher- and clinician- empowerment through a variety of KG learning systems, we identify four key deficiencies in state-of-the-art graph learning that simultaneously limit KG learning performance and diminish the ability of humans to interface optimally with these learning systems. These deficiencies are: 1) lack of expert knowledge integration, 2) instability to node degree extremity in the KG, 3) lack of consideration for uncertainty and relevance while learning, and 4) lack of explainability. Furthermore, we characterise state-of-the-art attempts to solve each of these problems and note that each attempt has largely been isolated from attempts to solve the other problems. Through a formalisation of these problems and a review of the literature that addresses them, we adopt the position that not only are deficiencies in these four key areas holding back human-KG empowerment, but that the divide-and-conquer approach to solving these problems as individual units rather than a whole is a significant barrier to the interface between humans and KG learning systems. We propose that it is only through integrated, holistic solutions to the limitations of KG learning systems that human and KG learning co-empowerment will be efficiently affected. We finally present our "Veni, Vidi, Vici" framework that sets a roadmap for effectively and efficiently shifting to a holistic co-empowerment model in both the KG learning and the broader machine learning domain.
Paper Structure (15 sections, 5 figures)

This paper contains 15 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Expert Knowledge Integration
  3. Expert Knowledge Methods
  4. Handling Extreme Topological Variation
  5. Connectivity-Tolerant Methods
  6. Focusing Learning
  7. Focused Learning Methods
  8. Explainability
  9. Explainability Systems
  10. Veni, Vidi, Vici: Towards a Common Conceptual Space
  11. Phase 1: Veni
  12. Phase 2: Vidi
  13. Phase 3: Vici
  14. Bringing it all Together
  15. Conclusion

Figures (5)

  • Figure 1: Two graphs with identical topology but distinct information.
  • Figure 2: Two graphs with distinct topology but identical information.
  • Figure 3: Graph representing cases where we may care about uncertainty and relevance of various triples.
  • Figure 4: A triple predicted to be true (light green) and false (dark red). Explanation aims to distinguish for what reasons one is labelled as true and the other as false.
  • Figure 5: An overview of the "Veni, Vidi, Vici" framework.