Causal machine learning: A survey and open problems
Causal Machine Learning (CausalML) is an umbrella term for machine learning methods
that formalize the data-generation process as a structural causal model (SCM). This …
that formalize the data-generation process as a structural causal model (SCM). This …
Impossibility theorems for feature attribution
Despite a sea of interpretability methods that can produce plausible explanations, the field
has also empirically seen many failure cases of such methods. In light of these results, it …
has also empirically seen many failure cases of such methods. In light of these results, it …
The role of explainable AI in the context of the AI Act
C Panigutti, R Hamon, I Hupont… - Proceedings of the …, 2023 - dl.acm.org
The proposed EU regulation for Artificial Intelligence (AI), the AI Act, has sparked some
debate about the role of explainable AI (XAI) in high-risk AI systems. Some argue that black …
debate about the role of explainable AI (XAI) in high-risk AI systems. Some argue that black …
Explaining link prediction systems based on knowledge graph embeddings
Link Prediction (LP) aims at tackling Knowledge Graph incompleteness by inferring new,
missing facts from the already known ones. The rise of novel Machine Learning techniques …
missing facts from the already known ones. The rise of novel Machine Learning techniques …
Desiderata for representation learning: A causal perspective
Representation learning constructs low-dimensional representations to summarize essential
features of high-dimensional data. This learning problem is often approached by describing …
features of high-dimensional data. This learning problem is often approached by describing …
The inadequacy of Shapley values for explainability
X Huang, J Marques-Silva - arXiv preprint arXiv:2302.08160, 2023 - arxiv.org
This paper develops a rigorous argument for why the use of Shapley values in explainable
AI (XAI) will necessarily yield provably misleading information about the relative importance …
AI (XAI) will necessarily yield provably misleading information about the relative importance …
Causal explanations and XAI
S Beckers - Conference on causal learning and reasoning, 2022 - proceedings.mlr.press
Abstract Although standard Machine Learning models are optimized for making predictions
about observations, more and more they are used for making predictions about the results of …
about observations, more and more they are used for making predictions about the results of …
[HTML][HTML] Conceptual challenges for interpretable machine learning
DS Watson - Synthese, 2022 - Springer
As machine learning has gradually entered into ever more sectors of public and private life,
there has been a growing demand for algorithmic explainability. How can we make the …
there has been a growing demand for algorithmic explainability. How can we make the …
The Utility of “Even if” semifactual explanation to optimise positive outcomes
When users receive either a positive or negative outcome from an automated system,
Explainable AI (XAI) has almost exclusively focused on how to mutate negative outcomes …
Explainable AI (XAI) has almost exclusively focused on how to mutate negative outcomes …
Axiomatic aggregations of abductive explanations
The recent criticisms of the robustness of post hoc model approximation explanation
methods (like LIME and SHAP) have led to the rise of model-precise abductive explanations …
methods (like LIME and SHAP) have led to the rise of model-precise abductive explanations …