Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networks

The lack of transparency of Deep Neural Networks continues to be a limitation that severely undermines their reliability and usage in high-stakes applications. Promising approaches to overcome such limitations are Prototype-Based Self-Explainable Neural Networks (PSENNs), whose predictions rely on the similarity between the input at hand and a set of prototypical representations of the output classes, offering therefore a deep, yet transparent-by-design, architecture. So far, such models have been designed by considering pointwise estimates for the prototypes, which remain fixed after the learning phase of the model. In this paper, we introduce a probabilistic reformulation of PSENNs, called Prob-PSENN, which replaces point estimates for the prototypes with probability distributions over their values. This provides not only a more flexible framework for an end-to-end learning of prototypes, but can also capture the explanatory uncertainty of the model, which is a missing feature in previous approaches. In addition, since the prototypes determine both the explanation and the prediction, Prob-PSENNs allow us to detect when the model is making uninformed or uncertain predictions, and to obtain valid explanations for them. Our experiments demonstrate that Prob-PSENNs provide more meaningful and robust explanations than their non-probabilistic counterparts, thus enhancing the explainability and reliability of the models.

Leveraging Constraint Programming in a Deep Learning Approach for Dynamically Solving the Flexible Job-Shop Scheduling Problem

Recent advancements in the flexible job-shop scheduling problem (FJSSP) are primarily based on deep reinforcement learning (DRL) due to its ability to generate high-quality, real-time solutions. However, DRL approaches often fail to fully harness the strengths of existing techniques such as exact methods or constraint programming (CP), which can excel at finding optimal or near-optimal solutions for smaller instances. This paper aims to integrate CP within a deep learning (DL) based methodology, leveraging the benefits of both. In this paper, we introduce a method that involves training a DL model using optimal solutions generated by CP, ensuring the model learns from high-quality data, thereby eliminating the need for the extensive exploration typical in DRL and enhancing overall performance. Further, we integrate CP into our DL framework to jointly construct solutions, utilizing DL for the initial complex stages and transitioning to CP for optimal resolution as the problem is simplified. Our hybrid approach has been extensively tested on three public FJSSP benchmarks, demonstrating superior performance over five state-of-the-art DRL approaches and a widely-used CP solver. Additionally, with the objective of exploring the application to other combinatorial optimization problems, promising preliminary results are presented on applying our hybrid approach to the traveling salesman problem, combining an exact method with a well-known DRL method.

Solving large flexible job shop scheduling instances by generating a diverse set of scheduling policies with deep reinforcement learning

The Flexible Job Shop Scheduling Problem (FJSSP) has been extensively studied in the literature, and multiple approaches have been proposed within the heuristic, exact, and metaheuristic methods. However, the industry's demand to be able to respond in real-time to disruptive events has generated the necessity to be able to generate new schedules within a few seconds. Among these methods, under this constraint, only dispatching rules (DRs) are capable of generating schedules, even though their quality can be improved. To improve the results, recent methods have been proposed for modeling the FJSSP as a Markov Decision Process (MDP) and employing reinforcement learning to create a policy that generates an optimal solution assigning operations to machines. Nonetheless, there is still room for improvement, particularly in the larger FJSSP instances which are common in real-world scenarios. Therefore, the objective of this paper is to propose a method capable of robustly solving large instances of the FJSSP. To achieve this, we propose a novel way of modeling the FJSSP as an MDP using graph neural networks. We also present two methods to make inference more robust: generating a diverse set of scheduling policies that can be parallelized and limiting them using DRs. We have tested our approach on synthetically generated instances and various public benchmarks and found that our approach outperforms dispatching rules and achieves better results than three other recent deep reinforcement learning methods on larger FJSSP instances.

Neuroevolutionary algorithms driven by neuron coverage metrics for semi-supervised classification

In some machine learning applications the availability of labeled instances for supervised classification is limited while unlabeled instances are abundant. Semi-supervised learning algorithms deal with these scenarios and attempt to exploit the information contained in the unlabeled examples. In this paper, we address the question of how to evolve neural networks for semi-supervised problems. We introduce neuroevolutionary approaches that exploit unlabeled instances by using neuron coverage metrics computed on the neural network architecture encoded by each candidate solution. Neuron coverage metrics resemble code coverage metrics used to test software, but are oriented to quantify how the different neural network components are covered by test instances. In our neuroevolutionary approach, we define fitness functions that combine classification accuracy computed on labeled examples and neuron coverage metrics evaluated using unlabeled examples. We assess the impact of these functions on semi-supervised problems with a varying amount of labeled instances. Our results show that the use of neuron coverage metrics helps neuroevolution to become less sensitive to the scarcity of labeled data, and can lead in some cases to a more robust generalization of the learned classifiers.

On the Hyperparameters influencing a PINN's generalization beyond the training domain

Physics-Informed Neural Networks (PINNs) are Neural Network architectures trained to emulate solutions of differential equations without the necessity of solution data. They are currently ubiquitous in the scientific literature due to their flexible and promising settings. However, very little of the available research provides practical studies that aim for a better quantitative understanding of such architecture and its functioning. In this paper, we analyze the performance of PINNs for various architectural hyperparameters and algorithmic settings based on a novel error metric and other factors such as training time. The proposed metric and approach are tailored to evaluate how well a PINN generalizes to points outside its training domain. Besides, we investigate the effect of the algorithmic setup on the outcome prediction of a PINN, inside and outside its training domain, to explore the effect of each hyperparameter. Through our study, we assess how the algorithmic setup of PINNs influences their potential for generalization and deduce the settings which maximize the potential of a PINN for accurate generalization. The study that we present returns insightful and at times counterintuitive results on PINNs. These results can be useful in PINN applications when defining the model and evaluating it.

When and How to Fool Explainable Models (and Humans) with Adversarial Examples

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial examples or out-of-distribution inputs. In this paper, we explore the possibilities and limits of adversarial attacks for explainable machine learning models. First, we extend the notion of adversarial examples to fit in explainable machine learning scenarios, in which the inputs, the output classifications and the explanations of the model's decisions are assessed by humans. Next, we propose a comprehensive framework to study whether (and how) adversarial examples can be generated for explainable models under human assessment, introducing novel attack paradigms. In particular, our framework considers a wide range of relevant (yet often ignored) factors such as the type of problem, the user expertise or the objective of the explanations in order to identify the attack strategies that should be adopted in each scenario to successfully deceive the model (and the human). These contributions intend to serve as a basis for a more rigorous and realistic study of adversarial examples in the field of explainable machine learning.

Redefining Neural Architecture Search of Heterogeneous Multi-Network Models by Characterizing Variation Operators and Model Components

With neural architecture search methods gaining ground on manually designed deep neural networks -even more rapidly as model sophistication escalates-, the research trend shifts towards arranging different and often increasingly complex neural architecture search spaces. In this conjuncture, delineating algorithms which can efficiently explore these search spaces can result in a significant improvement over currently used methods, which, in general, randomly select the structural variation operator, hoping for a performance gain. In this paper, we investigate the effect of different variation operators in a complex domain, that of multi-network heterogeneous neural models. These models have an extensive and complex search space of structures as they require multiple sub-networks within the general model in order to answer to different output types. From that investigation, we extract a set of general guidelines, whose application is not limited to that particular type of model, and are useful to determine the direction in which an architecture optimization method could find the largest improvement. To deduce the set of guidelines, we characterize both the variation operators, according to their effect on the complexity and performance of the model; and the models, relying on diverse metrics which estimate the quality of the different parts composing it.

On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future

Neuroevolutionary algorithms, automatic searches of neural network structures by means of evolutionary techniques, are computationally costly procedures. In spite of this, due to the great performance provided by the architectures which are found, these methods are widely applied. The final outcome of neuroevolutionary processes is the best structure found during the search, and the rest of the procedure is commonly omitted in the literature. However, a good amount of residual information consisting of valuable knowledge that can be extracted is also produced during these searches. In this paper, we propose an approach that extracts this information from neuroevolutionary runs, and use it to build a metamodel that could positively impact future neural architecture searches. More specifically, by inspecting the best structures found during neuroevolutionary searches of generative adversarial networks with varying characteristics (e.g., based on dense or convolutional layers), we propose a Bayesian network-based model which can be used to either find strong neural structures right away, conveniently initialize different structural searches for different problems, or help future optimization of structures of any type to keep finding increasingly better structures where uninformed methods get stuck into local optima.

Analysis of Dominant Classes in Universal Adversarial Perturbations

The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion. Indeed, many different strategies can be employed to efficiently generate adversarial attacks, some of them relying on different theoretical justifications. Among these strategies, universal (input-agnostic) perturbations are of particular interest, due to their capability to fool a network independently of the input in which the perturbation is applied. In this work, we investigate an intriguing phenomenon of universal perturbations, which has been reported previously in the literature, yet without a proven justification: universal perturbations change the predicted classes for most inputs into one particular (dominant) class, even if this behavior is not specified during the creation of the perturbation. In order to justify the cause of this phenomenon, we propose a number of hypotheses and experimentally test them using a speech command classification problem in the audio domain as a testbed. Our analyses reveal interesting properties of universal perturbations, suggest new methods to generate such attacks and provide an explanation of dominant classes, under both a geometric and a data-feature perspective.