Concept Bottleneck Models (CBMs) are machine learning models that improve interpretability by grounding their predictions on human-understandable concepts, allowing for targeted interventions in their decision-making process. However, when intervened on, CBMs assume the availability of humans that can identify the need to intervene and always provide correct interventions. Both assumptions are unrealistic and impractical, considering labor costs and human error-proneness. In contrast, Learning to Defer (L2D) extends supervised learning by allowing machine learning models to identify cases where a human is more likely to be correct than the model, thus leading to deferring systems with improved performance. In this work, we gain inspiration from L2D and propose Deferring CBMs (DCBMs), a novel framework that allows CBMs to learn when an intervention is needed. To this end, we model DCBMs as a composition of deferring systems and derive a consistent L2D loss to train them. Moreover, by relying on a CBM architecture, DCBMs can explain why defer occurs on the final task. Our results show that DCBMs achieve high predictive performance and interpretability at the cost of deferring more to humans.

The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models. Some of the most advanced post hoc methods can generate explanations that account for the mutual interactions of input features in the form of logic rules. However, these methods frequently fail to guarantee the consistency of the extracted explanations with the model's underlying reasoning. To bridge this gap, we propose a theoretically grounded approach to ensure coherence and fidelity of the extracted explanations, moving beyond the limitations of current heuristic-based approaches. To this end, drawing from category theory, we introduce an explaining functor which structurally preserves logical entailment between the explanation and the opaque model's reasoning. As a proof of concept, we validate the proposed theoretical constructions on a synthetic benchmark verifying how the proposed approach significantly mitigates the generation of contradictory or unfaithful explanations.

This paper introduces a rigorous mathematical framework for neural network explainability, and more broadly for the explainability of equivariant operators called Group Equivariant Operators (GEOs) based on Group Equivariant Non-Expansive Operators (GENEOs) transformations. The central concept involves quantifying the distance between GEOs by measuring the non-commutativity of specific diagrams. Additionally, the paper proposes a definition of interpretability of GEOs according to a complexity measure that can be defined according to each user preferences. Moreover, we explore the formal properties of this framework and show how it can be applied in classical machine learning scenarios, like image classification with convolutional neural networks.

We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance. While the direct verification of interpretability scales exponentially with the number of variables of the system, we show that this complexity can be mitigated by treating interpretability as a Markovian property and employing neural re-parametrization techniques. Building on these insights, we propose a new modeling paradigm -- neural generation and interpretable execution -- that enables scalable verification of equivariance. This paradigm provides a general approach for designing Neural Interpretable Reasoners that are not only expressive but also transparent.

Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users. Among these techniqes, Concept Bottleneck Models enhance the interpretability of neural networks by integrating a layer of human-understandable concepts. These models, however, necessitate training a new model from the beginning, consuming significant resources and failing to utilize already trained large models. To address this issue, we introduce "AnyCBM", a method that transforms any existing trained model into a Concept Bottleneck Model with minimal impact on computational resources. We provide both theoretical and experimental insights showing the effectiveness of AnyCBMs in terms of classification performances and effectivenss of concept-based interventions on downstream tasks.

Malware detection is a constant challenge in cybersecurity due to the rapid development of new attack techniques. Traditional signature-based approaches struggle to keep pace with the sheer volume of malware samples. Machine learning offers a promising solution, but faces issues of generalization to unseen samples and a lack of explanation for the instances identified as malware. However, human-understandable explanations are especially important in security-critical fields, where understanding model decisions is crucial for trust and legal compliance. While deep learning models excel at malware detection, their black-box nature hinders explainability. Conversely, interpretable models often fall short in performance. To bridge this gap in this application domain, we propose the use of Logic Explained Networks (LENs), which are a recently proposed class of interpretable neural networks providing explanations in the form of First-Order Logic (FOL) rules. This paper extends the application of LENs to the complex domain of malware detection, specifically using the large-scale EMBER dataset. In the experimental results we show that LENs achieve robustness that exceeds traditional interpretable methods and that are rivaling black-box models. Moreover, we introduce a tailored version of LENs that is shown to generate logic explanations with higher fidelity with respect to the model's predictions.

Current deep learning models are not designed to simultaneously address three fundamental questions: predict class labels to solve a given classification task (the "What?"), explain task predictions (the "Why?"), and imagine alternative scenarios that could result in different predictions (the "What if?"). The inability to answer these questions represents a crucial gap in deploying reliable AI agents, calibrating human trust, and deepening human-machine interaction. To bridge this gap, we introduce CounterFactual Concept Bottleneck Models (CF-CBMs), a class of models designed to efficiently address the above queries all at once without the need to run post-hoc searches. Our results show that CF-CBMs produce: accurate predictions (the "What?"), simple explanations for task predictions (the "Why?"), and interpretable counterfactuals (the "What if?"). CF-CBMs can also sample or estimate the most probable counterfactual to: (i) explain the effect of concept interventions on tasks, (ii) show users how to get a desired class label, and (iii) propose concept interventions via "task-driven" interventions.

Explainable AI (XAI) aims to address the human need for safe and reliable AI systems. However, numerous surveys emphasize the absence of a sound mathematical formalization of key XAI notions -- remarkably including the term "explanation" which still lacks a precise definition. To bridge this gap, this paper presents the first mathematically rigorous definitions of key XAI notions and processes, using the well-funded formalism of Category theory. We show that our categorical framework allows to: (i) model existing learning schemes and architectures, (ii) formally define the term "explanation", (iii) establish a theoretical basis for XAI taxonomies, and (iv) analyze commonly overlooked aspects of explaining methods. As a consequence, our categorical framework promotes the ethical and secure deployment of AI technologies as it represents a significant step towards a sound theoretical foundation of explainable AI.

The design of interpretable deep learning models working in relational domains poses an open challenge: interpretable deep learning methods, such as Concept-Based Models (CBMs), are not designed to solve relational problems, while relational models are not as interpretable as CBMs. To address this problem, we propose Relational Concept-Based Models, a family of relational deep learning methods providing interpretable task predictions. Our experiments, ranging from image classification to link prediction in knowledge graphs, show that relational CBMs (i) match generalization performance of existing relational black-boxes (as opposed to non-relational CBMs), (ii) support the generation of quantified concept-based explanations, (iii) effectively respond to test-time interventions, and (iv) withstand demanding settings including out-of-distribution scenarios, limited training data regimes, and scarce concept supervisions.

Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts. However, state-of-the-art concept-based models rely on high-dimensional concept embedding representations which lack a clear semantic meaning, thus questioning the interpretability of their decision process. To overcome this limitation, we propose the Deep Concept Reasoner (DCR), the first interpretable concept-based model that builds upon concept embeddings. In DCR, neural networks do not make task predictions directly, but they build syntactic rule structures using concept embeddings. DCR then executes these rules on meaningful concept truth degrees to provide a final interpretable and semantically-consistent prediction in a differentiable manner. Our experiments show that DCR: (i) improves up to +25% w.r.t. state-of-the-art interpretable concept-based models on challenging benchmarks (ii) discovers meaningful logic rules matching known ground truths even in the absence of concept supervision during training, and (iii), facilitates the generation of counterfactual examples providing the learnt rules as guidance.