How should a machine intelligence perform unsupervised structure discovery over streams of sensory input? One approach to this problem is to cast it as an apperception task [1]. Here, the task is to construct an explicit interpretable theory that both explains the sensory sequence and also satisfies a set of unity conditions, designed to ensure that the constituents of the theory are connected in a

In AI research, synthesizing a plan of action has typically used descriptive models of the actions that abstractly specify what might happen as a result of an action, and are tailored for efficiently computing state transitions. However, executing the planned actions has needed operational models, in which rich computational control structures and closed-loop online decision-making are used to specify

Consequence-based (CB) reasoners combine ideas from resolution and (hyper)tableau calculi for solving key reasoning problems in Description Logics (DLs), such as ontology classification. Existing CB reasoners, however, are only capable of handling DLs without nominals (such as ALCHIQ), or DLs without disjunction (such as Horn-ALCHOIQ). In this paper, we present a consequence-based calculus for concept

In the Shift-Bribery problem we are given an election, a preferred candidate, and the costs of shifting this preferred candidate up the voters' preference orders. The goal is to find such a set of shifts that ensures that the preferred candidate wins the election. We give the first polynomial-time approximation scheme for the Shift-Bribery problem for the case of positional scoring rules, and for the

Research in the social sciences has shown that expectations are an important factor in explanations as used between humans: rather than explaining the cause of an event per se, the explainer will often address another event that did not occur but that the explainee might have expected. For AI-powered systems, this finding suggests that explanation-generating systems may need to identify such end user

Answer Set Programming (ASP) is a well-established paradigm for declarative programming and nonmonotonic reasoning. ASP allows for flexible modelling using rules. ASP rules induce a set of intended models called answer sets. Incoherence, the non-existence of answer sets, is therefore a feature of ASP, indicating that the rules admit no intended models. However, this feature can also be problematic

Borda Count is one of the earliest and most important voting rules and has been central to many applications in artificial intelligence. We study the problem of control in Borda elections where an election chair seeks to either make a designated candidate win (constructive case), or prevent her from winning (destructive case), via actions such as adding, deleting, or partitioning either candidates

A significant challenge for recommender systems (RSs), and in fact for AI systems in general, is the systematic definition of explanations for outputs in such a way that both the explanations and the systems themselves are able to adapt to their human users' needs. In this paper we propose an RS hosting a vast repertoire of explanations, which are customisable to users in their content and format,

Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from such models by learning simple, interpretable explanations. Shapley value is a game theoretic concept that can be used for this purpose. The Shapley value framework has a series of desirable theoretical properties, and can in principle handle any predictive

We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques of the underlying probabilistic logic programming language ProbLog can be adapted for the new language. We theoretically and experimentally demonstrate that DeepProbLog supports (i) both symbolic and subsymbolic

Many computational problems arising in, for instance, artificial intelligence can be realized as infinite-domain constraint satisfaction problems (CSPs) based on partition schemes: a set of pairwise disjoint binary relations (containing the equality relation) whose union spans the underlying domain and which is closed under converse. We first consider partition schemes that contain an acyclic order

Our research is a step toward ascertaining the need for personalization in XAI, and we do so in the context of investigating the value of explanations of AI-driven hints and feedback in Intelligent Tutoring Systems (ITS). We added an explanation functionality to the Adaptive CSP (ACSP) applet, an interactive simulation that helps students learn an algorithm for constraint satisfaction problems by providing

In recent years, several studies proposed privacy-preserving algorithms for solving Distributed Constraint Optimization Problems (DCOPs). Those studies were based on existing DCOP solving algorithms, which they strengthened by implementing cryptographic weaponry that enabled performing the very same computation while protecting sensitive private data. All of those studies assumed that agents do not

Inverse reinforcement learning (IRL) is the problem of inferring the reward function of an agent, given its policy or observed behavior. Analogous to RL, IRL is perceived both as a problem and as a class of methods. By categorically surveying the extant literature in IRL, this article serves as a comprehensive reference for researchers and practitioners of machine learning as well as those new to it

We consider planning problems for graphs, Markov Decision Processes (MDPs), and games on graphs in an explicit state space. While graphs represent the most basic planning model, MDPs represent interaction with nature and games on graphs represent interaction with an adversarial environment. We consider two planning problems with k different target sets: (a) the coverage problem asks whether there is

Explanatory AI (XAI) is on the rise, gaining enormous traction with the computational community, policymakers, and philosophers alike. This article contributes to this debate by first distinguishing scientific XAI (sXAI) from other forms of XAI. It further advances the structure for bona fide sXAI, while remaining neutral regarding preferences for theories of explanations. Three core components are

There are multiple ways of defining nonmonotonic inference relations based on a conditional knowledge base. While the axiomatic system P is an important standard for such plausible nonmonotonic reasoning, inference relations obtained from system Z or from c-representations have been designed which go beyond system P by selecting preferred models for inference. For any class of models M, we propose

Contemporary cost-based goal-recognition assumes rationality: that observed behaviour is more or less optimal. Probabilistic goal recognition systems, however, explicitly depend on some degree of sub-optimality to generate probability distributions. We show that, even when an observed agent is only slightly irrational (sub-optimal), state-of-the-art systems produce counter-intuitive results (though

Several real-world problems in engineering and applied science require the selection of sequences that maximize a given reward function. Optimizing over sequences as opposed to sets requires exploring an exponentially larger search space and can become prohibitive in most cases of practical interest. However, if the objective function is submodular (intuitively, it exhibits a diminishing return property)

This paper is motivated by applications of a Census Bureau interested in releasing aggregate socio-economic data about a large population without revealing sensitive information about any individual. The released information can be the number of individuals living alone, the number of cars they own, or their salary brackets. Recent events have identified some of the privacy challenges faced by these

Previous research in Explainable Artificial Intelligence (XAI) suggests that a main aim of explainability approaches is to satisfy specific interests, goals, expectations, needs, and demands regarding artificial systems (we call these “stakeholders' desiderata”) in a variety of contexts. However, the literature on XAI is vast, spreads out across multiple largely disconnected disciplines, and it often

Predicting the winner of an election and estimating the margin of victory of that election are favorite problems both for news media pundits and computational social choice theorists. Since it is often infeasible to elicit the preferences of all the voters in a typical prediction scenario, a common algorithm used for predicting the winner and estimating the margin of victory is to run the election

Aggregating the preferences of individuals into a collective decision is the core subject of study of social choice theory. In 2006, Procaccia and Rosenschein considered a utilitarian social choice setting, where the agents have explicit numerical values for the alternatives, yet they only report their linear orderings over them. To compare different aggregation mechanisms, Procaccia and Rosenschein

Various logical notions of know-how have been recently proposed and studied in the literature based on different types of epistemic planning in different frameworks. This paper proposes a unified logical framework to incorporate the existing and some new notions of know-how. We define the semantics of the know-how operator using a unified notion of epistemic planning with parameters of different types

In this paper, we introduce ballooning multi-armed bandits (BL-MAB), a novel extension of the classical stochastic MAB model. In the BL-MAB model, the set of available arms grows (or balloons) over time. In contrast to the classical MAB setting where the regret is computed with respect to the best arm overall, the regret in a BL-MAB setting is computed with respect to the best available arm at each

The interest in explainable artificial intelligence has grown strongly in recent years because of the need to convey safety and trust in the ‘how’ and ‘why’ of automated decision-making to users. While a plethora of approaches has been developed, only a few focus on how to use domain knowledge and how this influences the understanding of explanations by users. In this paper, we show that by using ontologies

In aspect-based sentiment analysis (ABSA), many neural models are equipped with an attention mechanism to quantify the contribution of each context word to sentiment prediction. However, such a mechanism suffers from one drawback: only a few frequent words with sentiment polarities are tended to be taken into consideration for final sentiment decision while abundant infrequent sentiment words are ignored

Abstract argumentation frameworks (AFs), originally proposed by Dung, constitute a central formal model for the study of computational aspects of argumentation in AI. Credulous and skeptical acceptance of arguments in a given AF are well-studied problems both in terms of theoretical analysis—especially computational complexity—and the development of practical decision procedures for the problems. However

Large-scale probabilistic knowledge bases are becoming increasingly important in academia and industry. They are continuously extended with new data, powered by modern information extraction tools that associate probabilities with knowledge base facts. The state of the art to store and process such data is founded on probabilistic databases. Many systems based on probabilistic databases, however, still

We study the parameterized complexity of the propositional satisfiability (SAT) and the more general model counting (#SAT) problems and obtain novel fixed-parameter algorithms that exploit the structural properties of input formulas. In the first part of the paper, we parameterize by the treewidth of the following two graphs associated with CNF formulas: the consensus graph and the conflict graph.

While the interpretability of machine learning models is often equated with their mere syntactic comprehensibility, we think that interpretability goes beyond that, and that human interpretability should also be investigated from the point of view of cognitive science. The goal of this paper is to discuss to what extent cognitive biases may affect human understanding of interpretable machine learning

This paper introduces CLEO, a novel preference elicitation algorithm capable of recommending complex configurable objects characterized by both discrete and continuous attributes and constraints defined over them. While existing preference elicitation techniques focus on searching for the best instance in a database of candidates, CLEO takes a constructive approach to recommendation through interactive

Counterfactual explanations, which deal with “why not?” scenarios, can provide insightful explanations to an AI agent's behavior [Miller [38]]. In this work, we focus on generating counterfactual explanations for deep reinforcement learning (RL) agents which operate in visual input environments like Atari. We introduce counterfactual state explanations, a novel example-based approach to counterfactual

We show how to integrate a variable elimination approach to solving influence diagrams with a value iteration approach to solving finite-horizon partially observable Markov decision processes (POMDPs). The integration of these approaches creates a variable elimination algorithm for influence diagrams that has much more relaxed constraints on elimination order, which allows improved scalability in many

In this paper, we describe a post-hoc explanation-by-example approach to eXplainable AI (XAI), where a black-box, deep learning system is explained by reference to a more transparent, proxy model (in this situation a case-based reasoner), based on a feature-weighting analysis of the former that is used to find explanatory cases from the latter (as one instance of the so-called Twin Systems approach)

This paper proposes a logical framework for representing and reasoning about imperfect information games. We first extend Game Description Language (GDL) with the standard epistemic operators and provide it with a semantics based on the epistemic state transition model. We then demonstrate how to use the language to represent the rules of an imperfect information game and formalize common game properties

Artificial Intelligence (AI) has come to prominence as one of the major components of our society, with applications in most aspects of our lives. In this field, complex and highly nonlinear machine learning models such as ensemble models, deep neural networks, and Support Vector Machines have consistently shown remarkable accuracy in solving complex tasks. Although accurate, AI models often are “black

Feature attribution is widely used in interpretable machine learning to explain how influential each measured input feature value is for an output inference. However, measurements can be uncertain, and it is unclear how the awareness of input uncertainty can affect the trust in explanations. We propose and study two approaches to help users to manage their perception of uncertainty in a model explanation:

Probabilistic Logic Programming (PLP) is a powerful paradigm for the representation of uncertain relations among objects. Recently, programs with continuous variables, also called hybrid programs, have been proposed and assigned a semantics. Hybrid programs are capable of representing real-world measurements but unfortunately the semantics proposal was imprecise so the definition did not assign a probability

Learning with noisy labels has attracted much attention during the past few decades. A fundamental problem is how to estimate noise proportions from corrupted data. Previous studies on this issue resort to the estimations of class distributions, conditional distributions, or the kernel embedding of distributions. In this paper, we present another simple and effective approach for noise estimation.

Trust models have become invaluable in dynamic scenarios, such as Internet applications, since they provide means for estimating trustworthiness of potential interaction counterparts. Currently, the majority of trust models require ratings to be expressed absolutely, that is as values from some predefined scale. However, literature shows that expressing ratings absolutely can be challenging for users

Multiple Object Tracking (MOT) has gained increasing attention due to its academic and commercial potential. Although different approaches have been proposed to tackle this problem, it still remains challenging due to factors like abrupt appearance changes and severe object occlusions. In this work, we contribute the first comprehensive and most recent review on this problem. We inspect the recent

This paper attempts to answer a central question in unsupervised learning: what does it mean to “make sense” of a sensory sequence? In our formalization, making sense involves constructing a symbolic causal theory that both explains the sensory sequence and also satisfies a set of unity conditions. The unity conditions insist that the constituents of the causal theory – objects, properties, and laws

We study the problem of fair division when the set of resources contains both divisible and indivisible goods. Classic fairness notions such as envy-freeness (EF) and envy-freeness up to one good (EF1) cannot be directly applied to this mixed goods setting. In this work, we propose a new fairness notion, envy-freeness for mixed goods (EFM), which is a direct generalization of both EF and EF1 to the

Reasoning with probabilistic information has recently attracted considerable attention in argumentation, and formalisms of Probabilistic Abstract Argumentation (PAA), Probabilistic Bipolar Argumentation (PBA) and Probabilistic Structured Argumentation (PSA) have been proposed. These foundational advances have been complemented with investigations on the complexity of some approaches to PAA and PBA

We study multiagent epistemic planning with a simple epistemic logic whose language is a restriction of that of standard epistemic logic. Its formulas are boolean combinations of observability atoms: sequences of ‘knowing whether’ operators followed by propositional variables. This compares favourably with other restricted languages where formulas are boolean combinations of epistemic literals: sequences

In this paper, we propose a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by learning a nonlinear embedding of a high-dimensional activation vector of a deep network layer into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can be constructed from the few concepts extracted by our

With the recent successes of black-box models in Artificial Intelligence (AI) and the growing interactions between humans and AIs, explainability issues have risen. In this article, in the context of high-stake applications, we propose an approach for explainable classification and annotation of images. It is based on a transparent model, whose reasoning is accessible and human understandable, and

Several different frameworks have been proposed to model and reason about knowledge in dynamic multi-agent settings, among them the logic-programming-based game description language GDL-III and dynamic epistemic logic (DEL). GDL-III and DEL have complementary strengths and weaknesses in terms of ease of modeling and simplicity of semantics. In this paper, we formally study the expressiveness of GDL-III

OWL 2 QL is a standard profile of the OWL 2 ontology language, specifically tailored to Ontology-Based Data Management. Inspired by recent work on higher-order Description Logics, in this paper we present a new semantics for OWL 2 QL ontologies, called Metamodeling Semantics (MS), and show that, in contrast to the official Direct Semantics (DS) for OWL 2, it allows exploiting the metamodeling capabilities

Sensor-based activity recognition aims to recognize users' activities from multi-dimensional streams of sensor readings received from ubiquitous sensors. It has been shown that data segmentation and feature extraction are two crucial steps in developing machine learning-based models for sensor-based activity recognition. However, most previous studies were only focused on the latter step by assuming

The rapid adoption of wireless sensor devices has made it easier to record location information of people in a variety of spaces (e.g., exhibition halls). Location information is often aggregated due to privacy and/or cost concerns. The aggregated data we use as input consist of the numbers of incoming and outgoing people at each location and at each time step. Since the aggregated data lack tracking

In classification, an algorithm learns to classify a given instance based on a set of observed attribute values. In many real world cases testing the value of an attribute incurs a cost. Furthermore, there can also be a cost associated with the misclassification of an instance. Cost sensitive classification attempts to minimize the expected cost of classification, by deciding after each observed attribute

Dependency syntax has been demonstrated highly useful for a number of natural language processing (NLP) tasks. Typical approaches of utilizing dependency syntax include Tree-RNN and Tree-Linearization, both of which exploit explicit 1-best tree outputs from a well-trained parser as inputs. However, these approaches may suffer from error propagation due to the inevitable errors contained in the 1-best

Evaluating local explanation methods is a difficult task due to the lack of a shared and universally accepted definition of explanation. In the literature, one of the most common ways to assess the performance of an explanation method is to measure the fidelity of the explanation with respect to the classification of a black box model adopted by an Artificial Intelligent system for making a decision

Real-world multi-agent systems such as warehouse robots operate under significant time constraints – in such settings, rather than spending significant amounts of time solving for optimal paths, it is instead preferable to find valid, collision-free paths quickly, even if suboptimal, and given additional time, to iteratively refine such paths to improve their cost. In such domains, we observe that

The bounded confidence model has been widely used to formally study groups of agents who are sharing opinions with those in their epistemic neighborhood. We revisit the model with an eye toward studying mis- and disinformation campaigns, which have been much in the news of late. To that end, we introduce typed agents into the model, specifically agents who can be irresponsible in different ways, most

Planning deals with the task of finding an ordered set of actions that achieves some goals from an initial state. In many real-world applications it is unfeasible to find a plan achieving all goals due to limitations in the available resources. A common case consists of having a bound on a given cost measure that is less than the optimal cost needed to achieve all goals. Oversubscription planning (OSP)

This paper presents a bidirectional search algorithm that dynamically improves the bounds during its execution. It has the property that it always terminates on or before the forward search meets the backward search. Computational experiments on the pancake problem, the sliding tile puzzle, and the topspin problem demonstrate that it is capable of solving problems using significantly fewer node expansions

We study a generalization of the classical stable matching problem that allows for cardinal preferences (as opposed to ordinal) and fractional matchings (as opposed to integral). In this cardinal setting, stable fractional matchings can have much larger social welfare than stable integral ones. Our goal is to understand the computational complexity of finding an optimal (i.e., welfare-maximizing) stable