Argumentative Ensembling for Robust Recourse under Model Multiplicity

2025-06-25

AI Summary

Under model multiplicity (MM), counterfactual explanations (CEs) suffer from cross-model fragility, yielding inconsistent remedial recommendations across equally performant models. Method: We propose the Remediation-Aware Ensemble (RAE) framework to generate robust, model-agnostic remedial suggestions valid across multiple high-performing models. We formally define the RAE problem and introduce six desiderata for robust remediation. Leveraging computational argumentation theory, we design a joint aggregation mechanism for predictions and counterfactuals, enabling semantic parameterization and model-preference modeling to resolve inter-model prediction conflicts. Contribution/Results: We theoretically characterize RAE’s behavior under four argumentation semantics. Empirical evaluation across eight instantiated methods demonstrates significant improvements in both desiderata satisfaction and cross-model robustness. This work delivers the first systematic, provably sound, and configurable solution for trustworthy decision support under MM.

Technology Category

• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Argumentation
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.)

Problem

• Ensuring robust counterfactual explanations under model multiplicity
• Formalizing recourse-aware ensembling for conflicting model predictions
• Resolving conflicts between models and counterfactuals via argumentation

Innovation

• Argumentative ensembling for robust recourse under multiplicity
• Leveraging computational argumentation to resolve model conflicts
• Parametric semantics for customizable ensemble preferences