Human reasoning can often be understood as an interplay between two systems: the intuitive and associative ("System 1") and the deliberative and logical ("System 2"). Neural sequence models -- which have been increasingly successful at performing complex, structured tasks -- exhibit the advantages and failure modes of System 1: they are fast and learn patterns from data, but are often inconsistent and incoherent. In this work, we seek a lightweight, training-free means of improving existing System 1-like sequence models by adding System 2-inspired logical reasoning. We explore several variations on this theme in which candidate generations from a neural sequence model are examined for logical consistency by a symbolic reasoning module, which can either accept or reject the generations. Our approach uses neural inference to mediate between the neural System 1 and the logical System 2. Results in robust story generation and grounded instruction-following show that this approach can increase the coherence and accuracy of neurally-based generations.

The constraint satisfaction problem (CSP) has important applications in computer science and AI. In particular, infinite-domain CSPs have been intensively used in subareas of AI such as spatio-temporal reasoning. Since constraint satisfaction is a computationally hard problem, much work has been devoted to identifying restricted problems that are efficiently solvable. One way of doing this is to restrict the interactions of variables and constraints, and a highly successful approach is to bound the treewidth of the underlying primal graph. Bodirsky & Dalmau [J. Comput. System. Sci. 79(1), 2013] and Huang et al. [Artif. Intell. 195, 2013] proved that CSP$(\Gamma)$ can be solved in $n^{f(w)}$ time (where $n$ is the size of the instance, $w$ is the treewidth of the primal graph and $f$ is a computable function) for certain classes of constraint languages $\Gamma$. We improve this bound to $f(w) \cdot n^{O(1)}$, where the function $f$ only depends on the language $\Gamma$, for CSPs whose basic relations have the patchwork property. Hence, such problems are fixed-parameter tractable and our algorithm is asymptotically faster than the previous ones. Additionally, our approach is not restricted to binary constraints, so it is applicable to a strictly larger class of problems than that of Huang et al. However, there exist natural problems that are covered by Bodirsky & Dalmau's algorithm but not by ours, and we begin investigating ways of generalising our results to larger families of languages. We also analyse our algorithm with respect to its running time and show that it is optimal (under the Exponential Time Hypothesis) for certain languages such as Allen's Interval Algebra.

Stochastic local search (SLS) is a successful paradigm for solving the satisfiability problem of propositional logic. A recent development in this area involves solving not the original instance, but a modified, yet logically equivalent one. Empirically, this technique was found to be promising as it improves the performance of state-of-the-art SLS solvers. Currently, there is only a shallow understanding of how this modification technique affects the runtimes of SLS solvers. Thus, we model this modification process and conduct an empirical analysis of the hardness of logically equivalent formulas. Our results are twofold. First, if the modification process is treated as a random process, a lognormal distribution perfectly characterizes the hardness; implying that the hardness is long-tailed. This means that the modification technique can be further improved by implementing an additional restart mechanism. Thus, as a second contribution, we theoretically prove that all algorithms exhibiting this long-tail property can be further improved by restarts. Consequently, all SAT solvers employing this modification technique can be enhanced.

Automated commonsense reasoning is essential for building human-like AI systems featuring, for example, explainable AI. Event Calculus (EC) is a family of formalisms that model commonsense reasoning with a sound, logical basis. Previous attempts to mechanize reasoning using EC faced difficulties in the treatment of the continuous change in dense domains (e.g., time and other physical quantities), constraints among variables, default negation, and the uniform application of different inference methods, among others. We propose the use of s(CASP), a query-driven, top-down execution model for Predicate Answer Set Programming with Constraints, to model and reason using EC. We show how EC scenarios can be naturally and directly encoded in s(CASP) and how it enables deductive and abductive reasoning tasks in domains featuring constraints involving both dense time and dense fluents.

In this paper, we discuss how certain radio access network optimization problems can be modelled using the concept of constraint satisfaction problems in artificial intelligence, and solved at scale using a quantum computer. As a case study, we discuss root sequence index (RSI) assignment problem - an important LTE/NR physical random access channel configuration related automation use-case. We formulate RSI assignment as quadratic unconstrained binary optimization (QUBO) problem constructed using data ingested from a commercial mobile network, and solve it using a cloud-based commercially available quantum computing platform. Results show that quantum annealing solver can successfully assign conflict-free RSIs. Comparison with well-known heuristics reveals that some classic algorithms are even more effective in terms of solution quality and computation time. The non-quantum advantage is due to the fact that current implementation is a semi-quantum proof-of-concept algorithm. Also, the results depend on the type of quantum computer used. Nevertheless, the proposed framework is highly flexible and holds tremendous potential for harnessing the power of quantum computing in mobile network automation.

In critical infrastructures like airports, much care has to be devoted in protecting radio communication networks from external electromagnetic interference. Protection of such mission-critical radio communication networks is usually tackled by exploiting radiogoniometers: at least three suitably deployed radiogoniometers, and a gateway gathering information from them, permit to monitor and localise sources of electromagnetic emissions that are not supposed to be present in the monitored area. Typically, radiogoniometers are connected to the gateway through relay nodes. As a result, some degree of fault-tolerance for the network of relay nodes is essential in order to offer a reliable monitoring. On the other hand, deployment of relay nodes is typically quite expensive. As a result, we have two conflicting requirements: minimise costs while guaranteeing a given fault-tolerance. In this paper, we address the problem of computing a deployment for relay nodes that minimises the relay node network cost while at the same time guaranteeing proper working of the network even when some of the relay nodes (up to a given maximum number) become faulty (fault-tolerance). We show that, by means of a computation-intensive pre-processing on a HPC infrastructure, the above optimisation problem can be encoded as a 0/1 Linear Program, becoming suitable to be approached with standard Artificial Intelligence reasoners like MILP, PB-SAT, and SMT/OMT solvers. Our problem formulation enables us to present experimental results comparing the performance of these three solving technologies on a real case study of a relay node network deployment in areas of the Leonardo da Vinci Airport in Rome, Italy.

We build on a recently proposed method for explaining solutions of constraint satisfaction problems. An explanation here is a sequence of simple inference steps, where the simplicity of an inference step is measured by the number and types of constraints and facts used, and where the sequence explains all logical consequences of the problem. We build on these formal foundations and tackle two emerging questions, namely how to generate explanations that are provably optimal (with respect to the given cost metric) and how to generate them efficiently. To answer these questions, we develop 1) an implicit hitting set algorithm for finding optimal unsatisfiable subsets; 2) a method to reduce multiple calls for (optimal) unsatisfiable subsets to a single call that takes constraints on the subset into account, and 3) a method for re-using relevant information over multiple calls to these algorithms. The method is also applicable to other problems that require finding cost-optimal unsatiable subsets. We specifically show that this approach can be used to effectively find sequences of optimal explanation steps for constraint satisfaction problems like logic grid puzzles.

Restless and collapsing bandits are commonly used to model constrained resource allocation in settings featuring arms with action-dependent transition probabilities, such as allocating health interventions among patients [Whittle, 1988; Mate et al., 2020]. However, state-of-the-art Whittle-index-based approaches to this planning problem either do not consider fairness among arms, or incentivize fairness without guaranteeing it [Mate et al., 2021]. Additionally, their optimality guarantees only apply when arms are indexable and threshold-optimal. We demonstrate that the incorporation of hard fairness constraints necessitates the coupling of arms, which undermines the tractability, and by extension, indexability of the problem. We then introduce ProbFair, a probabilistically fair stationary policy that maximizes total expected reward and satisfies the budget constraint, while ensuring a strictly positive lower bound on the probability of being pulled at each timestep. We evaluate our algorithm on a real-world application, where interventions support continuous positive airway pressure (CPAP) therapy adherence among obstructive sleep apnea (OSA) patients, as well as simulations on a broader class of synthetic transition matrices.

We present a tool-supported approach for the synthesis, verification and validation of the control software responsible for the safety of the human-robot interaction in manufacturing processes that use collaborative robots. In human-robot collaboration, software-based safety controllers are used to improve operational safety, e.g., by triggering shutdown mechanisms or emergency stops to avoid accidents. Complex robotic tasks and increasingly close human-robot interaction pose new challenges to controller developers and certification authorities. Key among these challenges is the need to assure the correctness of safety controllers under explicit (and preferably weak) assumptions. Our controller synthesis, verification and validation approach is informed by the process, risk analysis, and relevant safety regulations for the target application. Controllers are selected from a design space of feasible controllers according to a set of optimality criteria, are formally verified against correctness criteria, and are translated into executable code and validated in a digital twin. The resulting controller can detect the occurrence of hazards, move the process into a safe state, and, in certain circumstances, return the process to an operational state from which it can resume its original task. We show the effectiveness of our software engineering approach through a case study involving the development of a safety controller for a manufacturing work cell equipped with a collaborative robot.

We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants given repeated observations, enabling the server to recover privileged information about individual users' private training data via traditional gradient inference attacks. Our method revolves around reconstructing participant information (e.g: which rounds of training users participated in) from aggregated model updates by leveraging summary information from device analytics commonly used to monitor, debug, and manage federated learning systems. Our attack is parallelizable and we successfully disaggregate user updates on settings with up to thousands of participants. We quantitatively and qualitatively demonstrate significant improvements in the capability of various inference attacks on the disaggregated updates. Our attack enables the attribution of learned properties to individual users, violating anonymity, and shows that a determined central server may undermine the secure aggregation protocol to break individual users' data privacy in federated learning.