Anytime Approximate Formal Feature Attribution

Widespread use of artificial intelligence (AI) algorithms and machine learning (ML) models on the one hand and a number of crucial issues pertaining to them warrant the need for explainable artificial intelligence (XAI). A key explainability question is: given this decision was made, what are the input features which contributed to the decision? Although a range of XAI approaches exist to tackle this problem, most of them have significant limitations. Heuristic XAI approaches suffer from the lack of quality guarantees, and often try to approximate Shapley values, which is not the same as explaining which features contribute to a decision. A recent alternative is so-called formal feature attribution (FFA), which defines feature importance as the fraction of formal abductive explanations (AXp’s) containing the given feature. This measures feature importance from the view of formally reasoning about the model’s behavior. Namely, given a system of constraints logically representing the ML model of interest, computing an AXp requires finding a minimal unsatisfiable subset (MUS) of the system. It is challenging to compute FFA using its definition because that involves counting over all AXp’s (equivalently, counting over MUSes), although one can approximate it. Based on these results, this paper makes several contributions. First, it gives compelling evidence that computing FFA is intractable, even if the set of contrastive formal explanations (CXp’s), which correspond to minimal correction subsets (MCSes) of the logical system, is provided, by proving that the problem is #P-hard. Second, by using the duality between MUSes and MCSes, it proposes an efficient heuristic to switch from MCS enumeration to MUS enumeration on-the-fly resulting in an adaptive explanation enumeration algorithm effectively approximating FFA in an anytime fashion. Finally, experimental results obtained on a range of widely used datasets demonstrate the effectiveness of the proposed FFA approximation approach in terms of the error of FFA approximation as well as the number of explanations computed and their diversity given a fixed time limit.