Continual learning constrains models to learn new tasks over time without forgetting what they have already learned. A key challenge in this setting is catastrophic forgetting, where learning new information causes the model to lose its performance on previous tasks. Recently, explainable AI has been proposed as a promising way to better understand and reduce forgetting. In particular, self-explainable models are useful because they generate explanations during prediction, which can help preserve knowledge. However, most existing explainable approaches use post-hoc explanations or require additional memory for each new task, resulting in limited scalability. In this work, we introduce CIP-Net, an exemplar-free self-explainable prototype-based model designed for continual learning. CIP-Net avoids storing past examples and maintains a simple architecture, while still providing useful explanations and strong performance. We demonstrate that CIP-Net achieves state-of-the-art performances compared to previous exemplar-free and self-explainable methods in both task- and class-incremental settings, while bearing significantly lower memory-related overhead. This makes it a practical and interpretable solution for continual learning.

Graph Neural Networks (GNNs) have proven their effectiveness in various graph-structured data applications. However, one of the significant challenges in the realm of GNNs is representation learning, a critical concept that bridges graph pooling, aimed at creating compressed graph representations, and explainable artificial intelligence, which focuses on building models with transparent reasoning mechanisms. This research paper introduces a novel approach called Interpretable Memory-based Prototypical Pooling (IMPO) to address this challenge. IMPO is a graph pooling layer designed to enhance the interpretability of GNNs while maintaining high performance in graph classification tasks. It builds upon the MemPool algorithm and incorporates prototypical components to cluster nodes around class-aware centroids. This approach allows IMPO to selectively aggregate relevant substructures, paving the way for generating more interpretable graph representations. The experimental results in our study underscore the potential of pooling architectures in constructing inherently explainable GNNs. Notably, IMPO achieves state-of-the-art results in both classification and explanatory capacities across a diverse set of graph classification datasets.

Explainable AI seeks to unveil the intricacies of black box models through post-hoc strategies or self-interpretable models. In this paper, we tackle the problem of building layers that are intrinsically explainable through logic rules. In particular, we address current state-of-the-art methods’ lack of fidelity and expressivity by introducing a transparent explainable logic layer (TELL). We propose to constrain a feed-forward layer with positive weights, which, combined with particular activation functions, offer the possibility of a direct translation into logic rules. Additionally, this approach overcomes the limitations of previous models, linked to their applicability to binary data only, by proposing a new way to automatically threshold real values and incorporate the obtained predicates into logic rules. We show that, compared to state-of-the-art, TELL achieves similar classification performances and, at the same time, provides higher explanatory power, measured by the agreement between models’ outputs and the activation of the logic explanations. In addition, TELL offers a broader spectrum of applications thanks to the possibility of its use on real data.

Non-markovian Reinforcement Learning (RL) tasks are very hard to solve, because agents must consider the entire history of state-action pairs to act rationally in the environment. Most works use symbolic formalisms (as Linear Temporal Logic or automata) to specify the temporally-extended task. These approaches only work in finite and discrete state environments or continuous problems for which a mapping between the raw state and a symbolic interpretation is known as a symbol grounding (SG) function. Here, we define Neural Reward Machines (NRM), an automata-based neurosymbolic framework that can be used for both reasoning and learning in non-symbolic non-markovian RL domains, which is based on the probabilistic relaxation of Moore Machines. We combine RL with semisupervised symbol grounding (SSSG) and we show that NRMs can exploit high-level symbolic knowledge in non-symbolic environments without any knowledge of the SG function, outperforming Deep RL methods which cannot incorporate prior knowledge. Moreover, we advance the research in SSSG, proposing an algorithm for analysing the groundability of temporal specifications, which is more efficient than baseline techniques of a factor 103.

In this work, we introduce DeepDFA, a novel approach to identifying Deterministic Finite Automata (DFAs) from traces, harnessing a differentiable yet discrete model. Inspired by both the probabilistic relaxation of DFAs and Recurrent Neural Networks (RNNs), our model offers interpretability post-training, alongside reduced complexity and enhanced training efficiency compared to traditional RNNs. Moreover, by leveraging gradient-based optimization, our method surpasses combinatorial approaches in both scalability and noise resilience. Validation experiments conducted on target regular languages of varying size and complexity demonstrate that our approach is accurate, fast, and robust to noise in both the input symbols and the output labels of training data, integrating the strengths of both logical grammar induction and deep learning.

Abstract Molecular property prediction is a fundamental task in the field of drug discovery. Several works use graph neural networks to leverage molecular graph representations. Although they have been successfully applied in a variety of applications, their decision process is not transparent. In this work, we adapt concept whitening to graph neural networks. This approach is an explainability method used to build an inherently interpretable model, which allows identifying the concepts and consequently the structural parts of the molecules that are relevant for the output predictions. We test popular models on several benchmark datasets from MoleculeNet. Starting from previous work, we identify the most significant molecular properties to be used as concepts to perform classification. We show that the addition of concept whitening layers brings an improvement in both classification performance and interpretability. Finally, we provide several structural and conceptual explanations for the predictions.

A critical challenge in neuro-symbolic (NeSy) approaches is to handle the symbol grounding problem without direct supervision. That is mapping high-dimensional raw data into an interpretation over a finite set of abstract concepts with a known meaning, without using labels. In this work, we ground symbols into sequences of images by exploiting symbolic logical knowledge in the form of Linear Temporal Logic over finite traces (LTLf) formulas, and sequence-level labels expressing if a sequence of images is compliant or not with the given formula. Our approach is based on translating the LTLf formula into an equivalent deterministic finite automaton (DFA) and interpreting the latter in fuzzy logic. Experiments show that our system outperforms recurrent neural networks in sequence classification and can reach high image classification accuracy without being trained with any single-image label.

Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations (i.e., the highest ones) used to check the alignment, thus lacking completeness. In this paper, we propose a generalization, called Clustered Compositional Explanations, that combines Compositional Explanations with clustering and a novel search heuristic to approximate a broader spectrum of the neuron behavior. We define and address the problems connected to the application of these methods to multiple ranges of activations, analyze the insights retrievable by using our algorithm, and propose desiderata qualities that can be used to study the explanations returned by different algorithms.

Abstract Deep neural networks are the driving force of the recent explosion of machine learning applications in everyday life. However, they usually require a lot of training data to work well, and they act as black-boxes, making predictions without any explanation about them. This paper presents Memory Wrap, a module (i.e, a set of layers) that can be added to deep learning models to improve their performance and interpretability in settings where few data are available. Memory Wrap adopts a sparse content-attention mechanism between the input and some memories of past training samples. We show that adding Memory Wrap to standard deep neural networks improves their performance when they learn from a limited set of data, and allows them to reach comparable performance when they learn from the full dataset. We discuss how the analysis of its structure and content-attention weights helps to get insights about its decision process and makes their predictions more interpretable, compared to the same networks without Memory Wrap. We test our approach on image classification tasks using several networks on three different datasets, namely CIFAR10, SVHN, and CINIC10.

Abstract The use and creation of machine‐learning‐based solutions to solve problems or reduce their computational costs are becoming increasingly widespread in many domains. Deep Learning plays a large part in this growth. However, it has drawbacks such as a lack of explainability and behaving as a black‐box model. During the last few years, Visual Analytics has provided several proposals to cope with these drawbacks, supporting the emerging eXplainable Deep Learning field. This survey aims to (i) systematically report the contributions of Visual Analytics for eXplainable Deep Learning; (ii) spot gaps and challenges; (iii) serve as an anthology of visual analytical solutions ready to be exploited and put into operation by the Deep Learning community (architects, trainers and end users) and (iv) prove the degree of maturity, ease of integration and results for specific domains. The survey concludes by identifying future research challenges and bridging activities that are helpful to strengthen the role of Visual Analytics as effective support for eXplainable Deep Learning and to foster the adoption of Visual Analytics solutions in the eXplainable Deep Learning community. An interactive explorable version of this survey is available online at https://aware‐diag‐sapienza.github.io/VA4XDL .

Deep reinforcement learning has achieved impressive results in recent years; yet, it is still severely troubled by environments showcasing sparse rewards. On top of that, not all sparse-reward environments are created equal, i.e., they can differ in the presence or absence of various features, with many of them having a great impact on learning. In light of this, the present work puts together a literature compilation of such environmental features, covering particularly those that have been taken advantage of and those that continue to pose a challenge. We expect this effort to provide guidance to researchers for assessing the generality of their new proposals and to call their attention to issues that remain unresolved when dealing with sparse rewards.

The year 2020 saw the covid-19 virus lead to one of the worst global pandemics in history. As a result, governments around the world have been faced with the challenge of protecting public health while keeping the economy running to the greatest extent possible. Epidemiological models provide insight into the spread of these types of diseases and predict the effects of possible intervention policies. However, to date, even the most data-driven intervention policies rely on heuristics. In this paper, we study how reinforcement learning (RL) and Bayesian inference can be used to optimize mitigation policies that minimize economic impact without overwhelming hospital capacity. Our main contributions are (1) a novel agent-based pandemic simulator which, unlike traditional models, is able to model fine-grained interactions among people at specific locations in a community; (2) an RLbased methodology for optimizing fine-grained mitigation policies within this simulator; and (3) a Hidden Markov Model for predicting infected individuals based on partial observations regarding test results, presence of symptoms, and past physical contacts. This article is part of the special track on AI and COVID-19.

In this paper we present a novel mechanism to get explanations that allow to better understand network predictions when dealing with sequential data. Specifically, we adopt memory-based networks — Differential Neural Computers — to exploit their capability of storing data in memory and reusing it for inference. By tracking both the memory access at prediction time, and the information stored by the network at each step of the input sequence, we can retrieve the most relevant input steps associated to each prediction. We validate our approach (1) on a modified T-maze, which is a non-Markovian discrete control task evaluating an algorithm’s ability to correlate events far apart in history, and (2) on the Story Cloze Test, which is a commonsense reasoning framework for evaluating story understanding that requires a system to choose the correct ending to a four-sentence story. Our results show that we are able to explain agent’s decisions in (1) and to reconstruct the most relevant sentences used by the network to select the story ending in (2). Additionally, we show not only that by removing those sentences the network prediction changes, but also that the same are sufficient to reproduce the inference.

Research on multi-robot systems has demonstrated promising results in manifold applications and domains. Still, efficiently learning an effective robot behaviors is very difficult, due to unstructured scenarios, high uncertainties, and large state dimensionality (e.g, hyper-redundant and groups of robot). To alleviate this problem, we present Q-CP a cooperative model-based reinforcement learning algorithm, which exploits action values to both (1) guide the exploration of the state space and (2) generate effective policies. Specifically, we exploit Q-learning to attack the curse-of-dimensionality in the iterations of a Monte-Carlo Tree Search. We implement and evaluate Q-CP on different stochastic cooperative (general-sum) games: (1) a simple cooperative navigation problem among 3 robots, (2) a cooperation scenario between a pair of KUKA YouBots performing hand-overs, and (3) a coordination task between two mobile robots entering a door. The obtained results show the effectiveness of Q- CP in the chosen applications, where action values drive the exploration and reduce the computational demand of the planning process while achieving good performance.

As autonomous robots are increasingly being introduced in real-world environments operating for long periods of time, the difficulties of long-term mapping are attracting the attention of the robotics research community. This paper proposes a full SLAM system capable of handling the dynamics of the environment across a single or multiple mapping sessions. Using the pose graph SLAM paradigm, the system works on local maps in the form of 2D point cloud data which are updated over time to store the most up-to-date state of the environment. The core of our system is an efficient ICP-based alignment and merging procedure working on the clouds that copes with non-static entities of the environment. Furthermore, the system retains the graph complexity by removing out-dated nodes upon robust inter- and intra-session loop closure detections while graph coherency is preserved by using condensed measurements. Experiments conducted with real data from longterm SLAM datasets demonstrate the efficiency, accuracy and effectiveness of our system in the management of the mapping problem during long-term robot operation.