Argumentative explanations for interactive recommendations

Rago, Antonio; Cocarascu, Oana; Bechlivanidis, Christos; Lagnado, David A.; Toni, Francesca

doi:10.1016/j.artint.2021.103506

Cited by 40 publications

(35 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Formal explanation 6 approaches have been studied in a growing body of research in recent years [169,93,170,94,139,188,14,57,58,168,152,44,92,118,98,119,100,117,83,13,89,12,55,45,81,151,114,185,59,42,9,82,88,121,74]. Concretely, this paper uses the definition of abductive explanation [93] (AXp), which corresponds to a PI-explanation [169] in the case of boolean classifiers.…”

Section: Formal Explainabilitymentioning

confidence: 99%

On Tackling Explanation Redundancy in Decision Trees

Izza,

Ignatiev,

Marques-Silva

2022

Preprint

View full text Add to dashboard Cite

Decision trees (DTs) epitomize the ideal of interpretability of machine learning (ML) models. The interpretability of decision trees motivates explainability approaches by socalled intrinsic interpretability, and it is at the core of recent proposals for applying interpretable ML models in high-risk applications. The belief in DT interpretability is justified by the fact that explanations for DT predictions are generally expected to be succinct. Indeed, in the case of DTs, explanations correspond to DT paths. Since decision trees are ideally shallow, and so paths contain far fewer features than the total number of features, explanations in DTs are expected to be succinct, and hence interpretable. This paper offers both theoretical and experimental arguments demonstrating that, as long as interpretability of decision trees equates with succinctness of explanations, then decision trees ought not be deemed interpretable. The paper introduces logically rigorous path explanations and path explanation redundancy, and proves that there exist functions for which decision trees must exhibit paths with explanation redundancy that is arbitrarily larger than the actual path explanation. The paper also proves that only a very restricted class of functions can be represented with DTs that exhibit no explanation redundancy. In addition, the paper includes experimental results substantiating that path explanation redundancy is observed ubiquitously in decision trees, including those obtained using different tree learning algorithms, but also in a wide range of publicly available decision trees. The paper also proposes polynomial-time algorithms for eliminating path explanation redundancy, which in practice require negligible time to compute. Thus, these algorithms serve to indirectly attain irreducible, and so succinct, explanations for decision trees. Furthermore, the paper includes novel results related with duality and enumeration of explanations, based on using SAT solvers as witness-producing NP-oracles.

show abstract

Section: Formal Explainabilitymentioning

confidence: 99%

On Tackling Explanation Redundancy in Decision Trees

Izza,

Ignatiev,

Marques-Silva

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Although this paper focuses on AXp's, CXp's, their relationship, and associated computational problems, other formal approaches to explainability have been pursued in recent years (Wolf, Galanti, and Hazan 2019;Amgoud 2021;Liu and Lorini 2021). Other lines of research on explainability (Rago et al 2020(Rago et al , 2021 are based on formal logic, but are not model-based, and we opt not to categorize them as formal approaches to XAI. The paper opts to cover approaches to formal explainability which have not only seen rapid growth, but are also supported by a stream of practical results.…”

Section: Related Workmentioning

confidence: 99%

Delivering Trustworthy AI through Formal XAI

Marques-Silva

Ignatiev

2022

AAAI

View full text Add to dashboard Cite

The deployment of systems of artificial intelligence (AI) in high-risk settings warrants the need for trustworthy AI. This crucial requirement is highlighted by recent EU guidelines and regulations, but also by recommendations from OECD and UNESCO, among several other examples. One critical premise of trustworthy AI involves the necessity of finding explanations that offer reliable guarantees of soundness. This paper argues that the best known eXplainable AI (XAI) approaches fail to provide sound explanations, or that alternatively find explanations which can exhibit significant redundancy. The solution to these drawbacks are explanation approaches that offer formal guarantees of rigor. These formal explanations are not only sound but guarantee irredundancy. This paper summarizes the recent developments in the emerging discipline of formal XAI. The paper also outlines existing challenges for formal XAI.

show abstract

“…For instance, an explanation may bring attention to an element of someone's profile that is not specific enough to exclude nonrelevant results. As yet, approaches to enable such interaction with explanations have received limited attention (e.g., [65]).…”

Section: Explainingmentioning

confidence: 99%

On Natural Language User Profiles for Transparent and Scrutable Recommendation

Radlinski,

Balog,

Diaz

et al. 2022

Preprint

View full text Add to dashboard Cite

Natural interaction with recommendation and personalized search systems has received tremendous attention in recent years. We focus on the challenge of supporting people's understanding and control of these systems and explore a fundamentally new way of thinking about representation of knowledge in recommendation and personalization systems. Specifically, we argue that it may be both desirable and possible for algorithms that use natural language representations of users' preferences to be developed. We make the case that this could provide significantly greater transparency, as well as affordances for practical actionable interrogation of, and control over, recommendations. Moreover, we argue that such an approach, if successfully applied, may enable a major step towards systems that rely less on noisy implicit observations while increasing portability of knowledge of one's interests.

show abstract

Argumentative explanations for interactive recommendations

Cited by 40 publications

References 78 publications

On Tackling Explanation Redundancy in Decision Trees

On Tackling Explanation Redundancy in Decision Trees

Delivering Trustworthy AI through Formal XAI

On Natural Language User Profiles for Transparent and Scrutable Recommendation

Contact Info

Product

Resources

About