(Sometimes) Less is More: Mitigating the Complexity of Rule-based Representation for Interpretable Classification

Deep neural networks are widely used in practical applications of AI, however, their inner structure and complexity made them generally not easily interpretable. Model transparency and interpretability are key requirements for multiple scenarios where high performance is not enough to adopt the proposed solution. In this work, a differentiable approximation of $L_0$ regularization is adapted into a logic-based neural network, the Multi-layer Logical Perceptron (MLLP), to study its efficacy in reducing the complexity of its discrete interpretable version, the Concept Rule Set (CRS), while retaining its performance. The results are compared to alternative heuristics like Random Binarization of the network weights, to determine if better results can be achieved when using a less-noisy technique that sparsifies the network based on the loss function instead of a random distribution. The trade-off between the CRS complexity and its performance is discussed.

Integrating Background Knowledge in Medical Semantic Segmentation with Logic Tensor Networks

Semantic segmentation is a fundamental task in medical image analysis, aiding medical decision-making by helping radiologists distinguish objects in an image. Research in this field has been driven by deep learning applications, which have the potential to scale these systems even in the presence of noise and artifacts. However, these systems are not yet perfected. We argue that performance can be improved by incorporating common medical knowledge into the segmentation model's loss function. To this end, we introduce Logic Tensor Networks (LTNs) to encode medical background knowledge using first-order logic (FOL) rules. The encoded rules span from constraints on the shape of the produced segmentation, to relationships between different segmented areas. We apply LTNs in an end-to-end framework with a SwinUNETR for semantic segmentation. We evaluate our method on the task of segmenting the hippocampus in brain MRI scans. Our experiments show that LTNs improve the baseline segmentation performance, especially when training data is scarce. Despite being in its preliminary stages, we argue that neurosymbolic methods are general enough to be adapted and applied to other medical semantic segmentation tasks.

Novel Applications for VAE-based Anomaly Detection Systems

The recent rise in deep learning technologies fueled innovation and boosted scientific research. Their achievements enabled new research directions for deep generative modeling (DGM), an increasingly popular approach that can create novel and unseen data, starting from a given data set. As the technology shows promising applications, many ethical issues also arise. For example, their misuse can enable disinformation campaigns and powerful phishing attempts. Research also indicates different biases affect deep learning models, leading to social issues such as misrepresentation. In this work, we formulate a novel setting to deal with similar problems, showing that a repurposed anomaly detection system effectively generates novel data, avoiding generating specified unwanted data. We propose Variational Auto-encoding Binary Classifiers (V-ABC): a novel model that repurposes and extends the Auto-encoding Binary Classifier (ABC) anomaly detector, using the Variational Auto-encoder (VAE). We survey the limitations of existing approaches and explore many tools to show the model's inner workings in an interpretable way. This proposal has excellent potential for generative applications: models that rely on user-generated data could automatically filter out unwanted content, such as offensive language, obscene images, and misleading information.

Bayes Point Rule Set Learning

Interpretability is having an increasingly important role in the design of machine learning algorithms. However, interpretable methods tend to be less accurate than their black-box counterparts. Among others, DNFs (Disjunctive Normal Forms) are arguably the most interpretable way to express a set of rules. In this paper, we propose an effective bottom-up extension of the popular FIND-S algorithm to learn DNF-type rulesets. The algorithm greedily finds a partition of the positive examples. The produced DNF is a set of conjunctive rules, each corresponding to the most specific rule consistent with a part of positive and all negative examples. We also propose two principled extensions of this method, approximating the Bayes Optimal Classifier by aggregating DNF decision rules. Finally, we provide a methodology to significantly improve the explainability of the learned rules while retaining their generalization capabilities. An extensive comparison with state-of-the-art symbolic and statistical methods on several benchmark data sets shows that our proposal provides an excellent balance between explainability and accuracy.