Tractable Explanations for d-DNNF Classifiers

2022

AAAI

Self 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.

Section: Tractable Explanationsmentioning

confidence: 99%

Section: Tractable Explanationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Delivering Trustworthy AI through Formal XAI

Marques-Silva

2022

AAAI

Self Cite

“…First, similar to gradient-based methods, they require full knowledge of the original ML model. Second, although for a number of ML models these approaches are shown to be practically effective (Ignatiev, Narodytska, and Marques-Silva 2019b;Izza, Ignatiev, and Marques-Silva 2020;Marques-Silva et al 2020Izza and Marques-Silva 2021;Ignatiev and Marques-Silva 2021;Huang et al 2021;Ignatiev et al 2022;Huang et al 2022;Marques-Silva and Ignatiev 2022), formal approaches to XAI still face scalability issues in case of some other ML models (Ignatiev, Narodytska, and Marques-Silva 2019a) as formal reasoning about ML models is in general computationally expensive.…”

Section: Related Workmentioning

confidence: 99%

Constraint-Driven Explanations for Black-Box ML Models

Shrotri

Narodytska

et al. 2022

AAAI

Self Cite

The need to understand the inner workings of opaque Machine Learning models has prompted researchers to devise various types of post-hoc explanations. A large class of such explainers proceed in two phases: first perturb an input instance whose explanation is sought, and then generate an interpretable artifact to explain the prediction of the opaque model on that instance. Recently, Deutch and Frost proposed to use an additional input from the user: a set of constraints over the input space to guide the perturbation phase. While this approach affords the user the ability to tailor the explanation to their needs, striking a balance between flexibility, theoretical rigor and computational cost has remained an open challenge. We propose a novel constraint-driven explanation generation approach which simultaneously addresses these issues in a modular fashion. Our framework supports the use of expressive Boolean constraints giving the user more flexibility to specify the subspace to generate perturbations from. Leveraging advances in Formal Methods, we can theoretically guarantee strict adherence of the samples to the desired distribution. This also allows us to compute fidelity in a rigorous way, while scaling much better in practice. Our empirical study demonstrates concrete uses of our tool CLIME in obtaining more meaningful explanations with high fidelity.

“…In this paper we measure interpretability in terms of the overall succinctness of the information provided by an ML model to justify a given prediction. Moreover, and building on earlier work, we equate explanations with the so-called abductive explanations (AXps) (Shih, Choi, and Darwiche 2018;Ignatiev, Narodytska, and Marques-Silva 2019a,b;Darwiche and Hirth 2020;Izza, Ignatiev, and Marques-Silva 2020;Ignatiev et al 2020;Barceló et al 2020;Marques-Silva et al 2020, 2021Huang et al 2021;Marques-Silva and Ignatiev 2022;Huang et al 2022), i.e. subset-minimal sets of feature-value pairs that are sufficient for the prediction.…”

Section: Introductionmentioning

confidence: 99%

Using MaxSAT for Efficient Explanations of Tree Ensembles

Izza

Stuckey

et al. 2022

AAAI

Self Cite

Tree ensembles (TEs) denote a prevalent machine learning model that do not offer guarantees of interpretability, that represent a challenge from the perspective of explainable artificial intelligence. Besides model agnostic approaches, recent work proposed to explain TEs with formally-defined explanations, which are computed with oracles for propositional satisfiability (SAT) and satisfiability modulo theories. The computation of explanations for TEs involves linear constraints to express the prediction. In practice, this deteriorates scalability of the underlying reasoners. Motivated by the inherent propositional nature of TEs, this paper proposes to circumvent the need for linear constraints and instead employ an optimization engine for pure propositional logic to efficiently handle the prediction. Concretely, the paper proposes to use a MaxSAT solver and exploit the objective function to determine a winning class. This is achieved by devising a propositional encoding for computing explanations of TEs. Furthermore, the paper proposes additional heuristics to improve the underlying MaxSAT solving procedure. Experimental results obtained on a wide range of publicly available datasets demonstrate that the proposed MaxSAT-based approach is either on par or outperforms the existing reasoning-based explainers, thus representing a robust and efficient alternative for computing formal explanations for TEs.