Argumentative Ensembling for Robust Recourse under Model Multiplicity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Junqi, Rago, Antonio, Leofante, Francesco, Toni, Francesca
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911021565739008
author Jiang, Junqi
Rago, Antonio
Leofante, Francesco
Toni, Francesca
author_facet Jiang, Junqi
Rago, Antonio
Leofante, Francesco
Toni, Francesca
contents In machine learning, it is common to obtain multiple equally performing models for the same prediction task, e.g., when training neural networks with different random seeds. Model multiplicity (MM) is the situation which arises when these competing models differ in their predictions for the same input, for which ensembling is often employed to determine an aggregation of the outputs. Providing recourse recommendations via counterfactual explanations (CEs) under MM thus becomes complex, since the CE may not be valid across all models, i.e., the CEs are not robust under MM. In this work, we formalise the problem of providing recourse under MM, which we name recourse-aware ensembling (RAE). We propose the idea that under MM, CEs for each individual model should be considered alongside their predictions so that the aggregated prediction and recourse are decided in tandem. Centred around this intuition, we introduce six desirable properties for solutions to this problem. For solving RAE, we propose a novel argumentative ensembling method which guarantees the robustness of CEs under MM. Specifically, our method leverages computational argumentation to explicitly represent the conflicts between models and counterfactuals regarding prediction results and CE validity. It then uses argumentation semantics to resolve the conflicts and obtain the final solution, in a manner which is parametric to the chosen semantics. Our method also allows for the specification of preferences over the models under MM, allowing further customisation of the ensemble. In a comprehensive theoretical analysis, we characterise the behaviour of argumentative ensembling with four different argumentation semantics. We then empirically demonstrate the effectiveness of our approach in satisfying desirable properties with eight instantiations of our method. (Abstract is shortened for arXiv.)
format Preprint
id arxiv_https___arxiv_org_abs_2506_20260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Argumentative Ensembling for Robust Recourse under Model Multiplicity
Jiang, Junqi
Rago, Antonio
Leofante, Francesco
Toni, Francesca
Machine Learning
Artificial Intelligence
Multiagent Systems
In machine learning, it is common to obtain multiple equally performing models for the same prediction task, e.g., when training neural networks with different random seeds. Model multiplicity (MM) is the situation which arises when these competing models differ in their predictions for the same input, for which ensembling is often employed to determine an aggregation of the outputs. Providing recourse recommendations via counterfactual explanations (CEs) under MM thus becomes complex, since the CE may not be valid across all models, i.e., the CEs are not robust under MM. In this work, we formalise the problem of providing recourse under MM, which we name recourse-aware ensembling (RAE). We propose the idea that under MM, CEs for each individual model should be considered alongside their predictions so that the aggregated prediction and recourse are decided in tandem. Centred around this intuition, we introduce six desirable properties for solutions to this problem. For solving RAE, we propose a novel argumentative ensembling method which guarantees the robustness of CEs under MM. Specifically, our method leverages computational argumentation to explicitly represent the conflicts between models and counterfactuals regarding prediction results and CE validity. It then uses argumentation semantics to resolve the conflicts and obtain the final solution, in a manner which is parametric to the chosen semantics. Our method also allows for the specification of preferences over the models under MM, allowing further customisation of the ensemble. In a comprehensive theoretical analysis, we characterise the behaviour of argumentative ensembling with four different argumentation semantics. We then empirically demonstrate the effectiveness of our approach in satisfying desirable properties with eight instantiations of our method. (Abstract is shortened for arXiv.)
title Argumentative Ensembling for Robust Recourse under Model Multiplicity
topic Machine Learning
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2506.20260