Interpreting Predictive Models through Causality: A Query-Driven Methodology - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Interpreting Predictive Models through Causality: A Query-Driven Methodology

Mahdi Hadj Ali
  • Function : Author
Yann Le Biannic
  • Function : Author
Pierre-Henri Wuillemin

Abstract

Machine learning algorithms have been widely adopted in recent years due to their efficiency and versatility across many fields. However, the complexity of predictive models has led to a lack of interpretability in automatic decision-making. Recent works have improved general interpretability by estimating the contributions of input features to the prediction of a pre-trained model. Despite these advancements, practitioners still seek to gain causal insights into the underlying data-generating mechanisms. To this end, some works have attempted to integrate causal knowledge into interpretability, as non-causal techniques can lead to paradoxical explanations. These efforts have provided answers to various queries, but relying on a single pre-trained model may result in quantification problems. In this paper, we argue that each causal query requires its own reasoning; thus, a single predictive model is not suited for all questions. Instead, we propose a new framework that prioritizes the query of interest and then derives a query-driven methodology accordingly to the structure of the causal model. It results in a tailored predictive model adapted to the query and an adapted interpretability technique. Specifically, it provides a numerical estimate of causal effects, which allows for accurate answers to explanatory questions when the causal structure is known.
Fichier principal
Vignette du fichier
flairs-36-54-3.pdf (1.22 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04110395 , version 1 (05-06-2023)

Identifiers

Cite

Mahdi Hadj Ali, Yann Le Biannic, Pierre-Henri Wuillemin. Interpreting Predictive Models through Causality: A Query-Driven Methodology. The International FLAIRS Conference Proceedings, May 2023, ClearWater, FL, United States. ⟨10.32473/flairs.36.133387⟩. ⟨hal-04110395⟩
31 View
94 Download

Altmetric

Share

Gmail Facebook X LinkedIn More