Showing papers in "Journal of Artificial Intelligence Research in 2018"
TL;DR: The Synthetic Minority Oversampling Technique (SMOTE) preprocessing algorithm is considered "de facto" standard in the framework of learning from imbalanced data because of its simplicity in the design, as well as its robustness when applied to different type of problems.
Abstract: The Synthetic Minority Oversampling Technique (SMOTE) preprocessing algorithm is considered "de facto" standard in the framework of learning from imbalanced data. This is due to its simplicity in the design of the procedure, as well as its robustness when applied to different type of problems. Since its publication in 2002, SMOTE has proven successful in a variety of applications from several different domains. SMOTE has also inspired several approaches to counter the issue of class imbalance, and has also significantly contributed to new supervised learning paradigms, including multilabel classification, incremental learning, semi-supervised learning, multi-instance learning, among others. It is standard benchmark for learning from imbalanced data. It is also featured in a number of different software packages -- from open source to commercial. In this paper, marking the fifteen year anniversary of SMOTE, we reect on the SMOTE journey, discuss the current state of affairs with SMOTE, its applications, and also identify the next set of challenges to extend SMOTE for Big Data problems.
905 citations
TL;DR: A survey of the state of the art in natural language generation can be found in this article, with an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organized.
Abstract: This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past two decades, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of recent research topics that have arisen partly as a result of growing synergies between NLG and other areas of artifical intelligence; (c) draw attention to the challenges in NLG evaluation, relating them to similar challenges faced in other areas of nlp, with an emphasis on different evaluation methods and the relationships between them.
562 citations
TL;DR: Differentiable Inductive Logic Programming (DILP) as mentioned in this paper is a differentiable inductive logic framework that can not only solve tasks which traditional ILP systems are suited for, but shows a robustness to noise and error in the training data which ILP cannot cope with.
Abstract: Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increases, so too does the variance of the model, yielding a nearly ubiquitous overfitting problem. Although mitigated by a variety of model regularisation methods, the common cure is to seek large amounts of training data--which is not necessarily easily obtained--that sufficiently approximates the data distribution of the domain we wish to test on. In contrast, logic programming methods such as Inductive Logic Programming offer an extremely data-efficient process by which models can be trained to reason on symbolic domains. However, these methods are unable to deal with the variety of domains neural networks can be applied to: they are not robust to noise in or mislabelling of inputs, and perhaps more importantly, cannot be applied to non-symbolic domains where the data is ambiguous, such as operating on raw pixels. In this paper, we propose a Differentiable Inductive Logic framework, which can not only solve tasks which traditional ILP systems are suited for, but shows a robustness to noise and error in the training data which ILP cannot cope with. Furthermore, as it is trained by backpropagation against a likelihood objective, it can be hybridised by connecting it with neural networks over ambiguous data in order to be applied to domains which ILP cannot address, while providing data efficiency and generalisation beyond what neural networks on their own can achieve.
366 citations
TL;DR: A big picture look at how the Arcade Learning Environment is being used by the research community is taken, revisiting challenges posed when the ALE was introduced, summarizing the state-of-the-art in various problems and highlighting problems that remain open.
Abstract: The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of different problem settings and it has been receiving increasing attention from the scientific community, leading to some high-profile success stories such as the much publicized Deep Q-Networks (DQN). In this article we take a big picture look at how the ALE is being used by the research community. We show how diverse the evaluation methodologies in the ALE have become with time, and highlight some key concerns when evaluating agents in the ALE. We use this discussion to present some methodological best practices and provide new benchmark results using these best practices. To further the progress in the field, we introduce a new version of the ALE that supports multiple game modes and provides a form of stochasticity we call sticky actions. We conclude this big picture look by revisiting challenges posed when the ALE was introduced, summarizing the state-of-the-art in various problems and highlighting problems that remain open.
305 citations
TL;DR: In this article, a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based, is presented.
Abstract: Over the past years, distributed semantic representations have proved to be effective and flexible keepers of prior knowledge to be integrated into downstream applications. This survey focuses on the representation of meaning. We start from the theoretical background behind word vector space models and highlight one of their major limitations: the meaning conflation deficiency, which arises from representing a word with all its possible meanings as a single vector. Then, we explain how this deficiency can be addressed through a transition from the word level to the more fine-grained level of word senses (in its broader acceptation) as a method for modelling unambiguous lexical meaning. We present a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based. Finally, this survey covers the main evaluation procedures and applications for this type of representation, and provides an analysis of four of its important aspects: interpretability, sense granularity, adaptability to different domains and compositionality.
268 citations
TL;DR: The results from a large survey of machine learning researchers on their beliefs about progress in AI suggest there is a 50% chance of AI outperforming humans in all tasks in 45 years and of automating all human jobs in 120 years.
Abstract: Advances in artificial intelligence (AI) will transform modern life by reshaping transportation, health, science, finance, and the military. To adapt public policy, we need to better anticipate these advances. Here we report the results from a large survey of machine learning researchers on their beliefs about progress in AI. Researchers predict AI will outperform humans in many activities in the next ten years, such as translating languages (by 2024), writing high-school essays (by 2026), driving a truck (by 2027), working in retail (by 2031), writing a bestselling book (by 2049), and working as a surgeon (by 2053). Researchers believe there is a 50% chance of AI outperforming humans in all tasks in 45 years and of automating all human jobs in 120 years, with Asian respondents expecting these dates much sooner than North Americans. These results will inform discussion amongst researchers and policymakers about anticipating and managing trends in AI.
265 citations
TL;DR: The results establish a principled link between high-level actions and abstract representations, a concrete theoretical foundation for constructing abstract representations with provable properties, and a practical mechanism for autonomously learning abstract high- level representations.
Abstract: We consider the problem of constructing abstract representations for planning in high-dimensional, continuous environments We assume an agent equipped with a collection of high-level actions, and construct representations provably capable of evaluating plans composed of sequences of those actions
We first consider the deterministic planning case, and show that the relevant computation involves set operations performed over sets of states We define the specific collection of sets that is necessary and sufficient for planning, and use them to construct a grounded abstract symbolic representation that is provably suitable for deterministic planning The resulting representation can be expressed in PDDL, a canonical high-level planning domain language; we construct such a representation for the Playroom domain and solve it in milliseconds using an off-the-shelf planner
We then consider probabilistic planning, which we show requires generalizing from sets of states to distributions over states We identify the specific distributions required for planning, and use them to construct a grounded abstract symbolic representation that correctly estimates the expected reward and probability of success of any plan In addition, we show that learning the relevant probability distributions corresponds to specific instances of probabilistic density estimation and probabilistic classification We construct an agent that autonomously learns the correct abstract representation of a computer game domain, and rapidly solves it
Finally, we apply these techniques to create a physical robot system that autonomously learns its own symbolic representation of a mobile manipulation task directly from sensorimotor data---point clouds, map locations, and joint angles---and then plans using that representation Together, these results establish a principled link between high-level actions and abstract representations, a concrete theoretical foundation for constructing abstract representations with provable properties, and a practical mechanism for autonomously learning abstract high-level representations
234 citations
TL;DR: It is argued that diagnostic classification, unlike most visualisation techniques, does scale up from small networks in a toy domain, to larger and deeper recurrent networks dealing with real-life data, and may therefore contribute to a better understanding of the internal dynamics of current state-of-the-art models in natural language processing.
Abstract: We investigate how neural networks can learn and process languages with hierarchical, compositional semantics. To this end, we define the artifical task of processing nested arithmetic expressions, and study whether different types of neural networks can learn to compute their meaning. We find that recursive neural networks can implement a generalising solution to this problem, and we visualise this solution by breaking it up in three steps: project, sum and squash. As a next step, we investigate recurrent neural networks, and show that a gated recurrent unit, that processes its input incrementally, also performs very well on this task: the network learns to predict the outcome of the arithmetic expressions with high accuracy, although performance deteriorates somewhat with increasing length. To develop an understanding of what the recurrent network encodes, visualisation techniques alone do not suffice. Therefore, we develop an approach where we formulate and test multiple hypotheses on the information encoded and processed by the network. For each hypothesis, we derive predictions about features of the hidden state representations at each time step, and train 'diagnostic classifiers' to test those predictions. Our results indicate that the networks follow a strategy similar to our hypothesised 'cumulative strategy', which explains the high accuracy of the network on novel expressions, the generalisation to longer expressions than seen in training, and the mild deterioration with increasing length. This in turn shows that diagnostic classifiers can be a useful technique for opening up the black box of neural networks. We argue that diagnostic classification, unlike most visualisation techniques, does scale up from small networks in a toy domain, to larger and deeper recurrent networks dealing with real-life data, and may therefore contribute to a better understanding of the internal dynamics of current state-of-the-art models in natural language processing.
201 citations
TL;DR: An overview of the DCOP model is provided, giving a classification of its multiple extensions and addressing both resolution methods and applications that find a natural mapping within each class of DCOPs.
Abstract: The field of multi-agent system (MAS) is an active area of research within artificial intelligence, with an increasingly important impact in industrial and other real-world applications. In a MAS, autonomous agents interact to pursue personal interests and/or to achieve common objectives. Distributed Constraint Optimization Problems (DCOPs) have emerged as a prominent agent model to govern the agents' autonomous behavior, where both algorithms and communication models are driven by the structure of the specific problem. During the last decade, several extensions to the DCOP model have been proposed to enable support of MAS in complex, real-time, and uncertain environments.
This survey provides an overview of the DCOP model, offering a classification of its multiple extensions and addressing both resolution methods and applications that find a natural mapping within each class of DCOPs. The proposed classification suggests several future perspectives for DCOP extensions and identifies challenges in the design of efficient resolution algorithms, possibly through the adaptation of strategies from different areas.
139 citations
TL;DR: This paper statistically measure the discriminative power of every single feature found within a deep CNN, when used for characterizing every class of 11 datasets, and finds that all CNN features can be used for knowledge representation purposes both by their presence or by their absence.
Abstract: Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within a trained CNN model (in the case of image data), and reusing it for other purposes is a field of interest, as it provides access to the visual descriptors previously learnt by the CNN after processing millions of images, without requiring an expensive training phase. Contributions to this field (commonly known as feature representation transfer or transfer learning) have been purely empirical so far, extracting all CNN features from a single layer close to the output and testing their performance by feeding them to a classifier. This approach has provided consistent results, although its relevance is limited to classification tasks. In a completely different approach, in this paper we statistically measure the discriminative power of every single feature found within a deep CNN, when used for characterizing every class of 11 datasets. We seek to provide new insights into the behavior of CNN features, particularly the ones from convolutional layers, as this can be relevant for their application to knowledge representation and reasoning. Our results confirm that low and middle level features may behave differently to high level features, but only under certain conditions. We find that all CNN features can be used for knowledge representation purposes both by their presence or by their absence, doubling the information a single CNN feature may provide. We also study how much noise these features may include, and propose a thresholding approach to discard most of it. All these insights have a direct application to the generation of CNN embedding spaces.
84 citations
TL;DR: A lifted framework in which first-order rules are used to describe the structure of a given problem setting, which allows for a declarative specification of latent relational structures, which can then be efficiently discovered in a given data set using neural network learning.
Abstract: We propose a method to combine the interpretability and expressive power of firstorder logic with the effectiveness of neural network learning. In particular, we introduce a lifted framework in which first-order rules are used to describe the structure of a given problem setting. These rules are then used as a template for constructing a number of neural networks, one for each training and testing example. As the different networks corresponding to different examples share their weights, these weights can be efficiently learned using stochastic gradient descent. Our framework provides a flexible way for implementing and combining a wide variety of modelling constructs. In particular, the use of first-order logic allows for a declarative specification of latent relational structures, which can then be efficiently discovered in a given data set using neural network learning. Experiments on 78 relational learning benchmarks clearly demonstrate the effectiveness of the framework.
TL;DR: It is demonstrated that textual descriptions of environments provide a compact intermediate channel to facilitate effective policy transfer and by learning to ground the meaning of text to the dynamics of the environment such as transitions and rewards, an autonomous agent can effectively bootstrap policy learning on a new domain given its description.
Abstract: In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL). Despite the wide-spread application of deep RL techniques, learning generalized poli...
TL;DR: It is shown that datalogMTL is EXPSPACE-complete even with punctual intervals, in which case full MTL is known to be undecidable, and it is proved that nonrecursive datalog MTL is PSPACE- complete for combined complexity and in AC0 for data complexity.
Abstract: We propose a novel framework for ontology-based access to temporal log data using a datalog extension datalogMTL of a Horn fragment of the metric temporal logic MTL. We show that datalogMTL is ExpSpace-complete even with punctual intervals, in which case full MTL is known to be undecidable. We also prove that nonrecursive datalogMTL is PSpace-complete for combined complexity and in AC0 for data complexity. We demonstrate by two real-world use cases that nonrecursive datalogMTL programs can express complex temporal concepts from typical user queries and thereby facilitate access to temporal log data. Our experiments with Siemens turbine data and MesoWest weather data show that datalogMTL ontology-mediated queries are efficient and scale on large datasets of up to 8.3GB.
TL;DR: This work proposes a CEGAR algorithm for computing abstraction heuristics for optimal classical planning, and introduces two methods for producing diverse sets ofHeuristics within this framework, one based on goal atoms, the other based on landmarks.
Abstract: Counterexample-guided abstraction refinement (CEGAR) is a method for incrementally computing abstractions of transition systems. We propose a CEGAR algorithm for computing abstraction heuristics for optimal classical planning. Starting from a coarse abstraction of the planning task, we iteratively compute an optimal abstract solution, check if and why it fails for the concrete planning task and refine the abstraction so that the same failure cannot occur in future iterations. A key ingredient of our approach is a novel class of abstractions for classical planning tasks that admits efficient and very fine-grained refinement. Since a single abstraction usually cannot capture enough details of the planning task, we also introduce two methods for producing diverse sets of heuristics within this framework, one based on goal atoms, the other based on landmarks. In order to sum their heuristic estimates admissibly we introduce a new cost partitioning algorithm called saturated cost partitioning. We show that the resulting heuristics outperform other state-of-the-art abstraction heuristics in many benchmark domains.
TL;DR: The ScottyActivity planner is presented, that is able to generate practical hybrid activity and motion plans over long horizons by employing recent methods in convex optimization combined with methods for planning with relaxed plan graphs and heuristic forward search, and can solve a broad class of robotic planning problems.
Abstract:
The state of the art practice in robotics planning is to script behaviors manually, where each behavior is typically generated using trajectory optimization. However, in order for robots to be able to act robustly and adapt to novel situations, they need to plan these activity sequences autonomously. Since the conditions and effects of these behaviors are tightly coupled through time, state and control variables, many problems require that the tasks of activity planning and trajectory optimization are considered together. There are two key issues underlying effective hybrid activity and trajectory planning: the sufficiently accurate modeling of robot dynamics and the capability of planning over long horizons. Hybrid activity and trajectory planners that employ mixed integer programming within a discrete time formulation are able to accurately model complex dynamics for robot vehicles, but are often restricted to relatively short horizons. On the other hand, current hybrid activity planners that employ continuous time formulations can handle longer horizons but they only allow actions to have continuous effects with constant rate of change, and restrict the allowed state constraints to linear inequalities. This is insufficient for many robotic applications and it greatly limits the expressivity of the problems that these approaches can solve. In this work we present the ScottyActivity planner, that is able to generate practical hybrid activity and motion plans over long horizons by employing recent methods in convex optimization combined with methods for planning with relaxed plan graphs and heuristic forward search. Unlike other continuous time planners, ScottyActivity can solve a broad class of robotic planning problems by supporting convex quadratic constraints on state variables and control variables that are jointly constrained and that affect multiple state variables simultaneously. In order to support planning over long horizons, ScottyActivity does not resort to time, state or control variable discretization. While straightforward formulations of consistency checks are not convex and do not scale, we present an efficient convex formulation, in the form of a Second Order Cone Program (SOCP), that is very fast to solve. We also introduce several new realistic domains that demonstrate the capabilities and scalability of our approach, and their simplified linear versions, that we use to compare with other state of the art planners. This work demonstrates the power of integrating advanced convex optimization techniques with discrete search methods and paves the way for extensions dealing with non-convex disjoint constraints, such as obstacle avoidance.
TL;DR: It is shown how to generate " really hard " random instances for subgraph isomorphism problems, which are computationally challenging with a couple of hundred vertices in the target, and only twenty pattern vertices.
Abstract: The subgraph isomorphism problem involves deciding whether a copy of a pattern graph occurs inside a larger target graph. The non-induced version allows extra edges in the target, whilst the induced version does not. Although both variants are NP-complete, algorithms inspired by constraint programming can operate comfortably on many real-world problem instances with thousands of vertices. However, they cannot handle arbitrary instances of this size. We show how to generate " really hard " random instances for subgraph isomorphism problems, which are computationally challenging with a couple of hundred vertices in the target, and only twenty pattern vertices. For the non-induced version of the problem, these instances lie on a satisfiable / unsatisfiable phase transition, whose location we can predict; for the induced variant, much richer behaviour is observed, and constrained-ness gives a better measure of difficulty than does proximity to a phase transition. These results have practical consequences: we explain why the widely researched " filter / verify " indexing technique used in graph databases is founded upon a misunderstanding of the empirical hardness of NP-complete problems, and cannot be beneficial when paired with any reasonable subgraph isomorphism algorithm.
TL;DR: It is shown that the framework of heuristic AND/OR search, which exploits conditional independence in the graphical model, coupled with variational-based mini-bucket heuristics can be extended to this task and yield powerful state-of-the-art schemes.
Abstract:
Mixed inference such as the marginal MAP query (some variables marginalized by summation and others by maximization) is key to many prediction and decision models. It is known to be extremely hard; the problem is NPPP-complete while the decision problem for MAP is only NP-complete and the summation problem is #P-complete. Consequently, approximation anytime schemes are essential. In this paper, we show that the framework of heuristic AND/OR search, which exploits conditional independence in the graphical model, coupled with variational-based mini-bucket heuristics can be extended to this task and yield powerful state-of-the-art schemes. Specifically, we explore the complementary properties of best-first search for reducing the number of conditional sums and providing time-improving upper bounds, with depth-first search for rapidly generating and improving solutions and lower bounds. We show empirically that a class of solvers that interleaves depth-first with best-first schemes emerges as the most competitive anytime scheme.
TL;DR: The authors proposed FIGMENT, which combines a global model that computes scores based on global information of an entity and a context model that evaluates the individual occurrences of the entity and then aggregates the scores.
Abstract: Extracting information about entities remains an important research area. This paper addresses the problem of corpus-level entity typing, i.e., inferring from a large corpus that an entity is a member of a class, such as “food” or “artist”. The application of entity typing we are interested in is knowledge base completion, specifically, to learn which classes an entity is a member of. We propose FIGMENT to tackle this problem. FIGMENT is embedding-based and combines (i) a global model that computes scores based on global information of an entity and (ii) a context model that first evaluates the individual occurrences of an entity and then aggregates the scores. Each of the two proposed models has specific properties. For the global model, learning highquality entity representations is crucial because it is the only source used for the predictions. Therefore, we introduce representations using the name and contexts of entities on the three levels of entity, word, and character. We show that each level provides complementary information and a multi-level representation performs best. For the context model, we need to use distant supervision since there are no context-level labels available for entities. Distantly supervised labels are nois and this harms the performance of models. Therefore, we introduce and apply new algorithms for noise mitigation using multi-instance learning. We show the effectiveness of our models on a large entity typing dataset built from Freebase.
TL;DR: It is argued that the decision to embrace AI will lead to positive impacts on society, including businesses, organizations and individuals, as well as on the AI industry itself.
Abstract: The United Arab Emirates (UAE) is the first country in the world to appoint a State Minister for Artificial Intelligence (AI). The UAE is embracing AI in society at the governmental level, which is leading to a new generations of digital government (which we are labeling Gov. 3.0). This paper argues that the decision to embrace AI will lead to positive impacts on society, including businesses, organizations and individuals, as well as on the AI industry itself. This paper discusses the societal impacts of AI at a macro (country-wide) level.
This article is part of the special track on AI and Society.
TL;DR: In this paper, the authors consider fractional hedonic games, a subclass of coalition formation games that can be succinctly modeled by means of a graph in which nodes represent agents and edge weights the degree of preference of the corresponding endpoints, and provide existence, efficiency and complexity results for games played on both general and specific graph topologies.
Abstract: We consider fractional hedonic games, a subclass of coalition formation games that can be succinctly modeled by means of a graph in which nodes represent agents and edge weights the degree of preference of the corresponding endpoints. The happiness or utility of an agent for being in a coalition is the average value she ascribes to its members. We adopt Nash stable outcomes as the target solution concept; that is we focus on states in which no agent can improve her utility by unilaterally changing her own group. We provide existence, efficiency and complexity results for games played on both general and specific graph topologies. As to the efficiency results, we mainly study the quality of the best Nash stable outcome and refer to the ratio between the social welfare of an optimal coalition structure and the one of such an equilibrium as to the price of stability. In this respect, we remark that a best Nash stable outcome has a natural meaning of stability, since it is the optimal solution among the ones which can be accepted by selfish agents. We provide upper and lower bounds on the price of stability for different topologies, both in case of weighted and unweighted edges. Beside the results for general graphs, we give refined bounds for various specific cases, such as triangle-free, bipartite graphs and tree graphs. For these families, we also show how to efficiently compute Nash stable outcomes with provable good social welfare.
TL;DR: An overview of the main trends and principled approaches for performing inference in hybrid Bayesian networks is provided and an overview of established software systems supporting inference in these types of models is provided.
Abstract: Hybrid Bayesian networks have received an increasing attention during the last years. The difference with respect to standard Bayesian networks is that they can host discrete and continuous variabl...
TL;DR: This work proposes a new approach for capturing this decision-making process through counterfactual reasoning in pairwise comparisons and demonstrates that this approach accurately learns multifaceted heuristics on a synthetic and real world data sets.
Abstract: : AbstractScheduling techniques are typically developed for specificindustries and applications through extensive interviewswith domain experts to codify effective heuristicsand solution strategies. As an alternative, we presenta technique called Collaborative Optimization via ApprenticeshipScheduling (COVAS), which performs machinelearning using human expert demonstration, inconjunction with optimization, to automatically and efficientlyproduce optimal solutions to challenging real worldscheduling problems. COVAS first learns a policyfrom human scheduling demonstration via apprenticeshiplearning, then uses this initial solution to provide atight bound on the value of the optimal solution, therebysubstantially improving the efficiency of a branch-and boundsearch for an optimal schedule. We demonstratethis technique on a variant of the weapon-to-target assignmentproblem, and show that it generates substantiallysuperior solutions to those produced by human domainexperts, at a rate up to 10 times faster than anoptimization approach that does not incorporate humanexpert demonstration.
TL;DR: This paper surveys the current state of the art in Natural Language Generation, defined as the task of generating text or speech from non-linguistic input.
Abstract: This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view o...
TL;DR: This work introduces Pike, an executive for human-robot teams, that allows the robot to continuously and concurrently reason about what a human is doing as execution proceeds, as well as adapt appropriately, resulting in a mixed-initiative execution where humans and robots interact fluidly to complete task goals.
Abstract: There is huge demand for robots to work alongside humans in heterogeneous teams. To achieve a high degree of fluidity, robots must be able to (1) recognize their human co-worker's intent, and (2) adapt to this intent accordingly, providing useful aid as a teammate. The literature to date has made great progress in these two areas -- recognition and adaptation -- but largely as separate research activities. In this work, we present a unified approach to these two problems, in which recognition and adaptation occur concurrently and holistically within the same framework. We introduce Pike, an executive for human-robot teams, that allows the robot to continuously and concurrently reason about what a human is doing as execution proceeds, as well as adapt appropriately. The result is a mixed-initiative execution where humans and robots interact fluidly to complete task goals.Key to our approach is our task model: a contingent, temporally-flexible team-plan with explicit choices for both the human and robot. This allows a single set of algorithms to find implicit constraints between sets of choices for the human and robot (as determined via causal link analysis and temporal reasoning), narrowing the possible decisions a rational human would take (hence achieving intent recognition) as well as the possible actions a robot could consistently take (hence achieving adaptation). Pike makes choices based on the preconditions of actions in the plan, temporal constraints, unanticipated disturbances, and choices made previously (by either agent).Innovations of this work include (1) a framework for concurrent intent recognition and adaptation for contingent, temporally-flexible plans, (2) the generalization of causal links for contingent, temporally-flexible plans along with related extraction algorithms, and (3) extensions to a state-of-the-art dynamic execution system to utilize these causal links for decision making.
TL;DR: This article provides the first axiomatic characterization of game-theoretic centralities, and shows that every possible centrality measure can be obtained following the game- theoretic approach.
Abstract: One of the fundamental research challenges in network science is centrality analysis, i.e., identifying the nodes that play the most important roles in the network. In this article, we focus on the...
TL;DR: A method to solve subproblems in a two-stage fashion using approximation algorithms is proposed, which is a new approximate method for Constrained POMDPs in single-agent settings, but also in settings in which multiple independent agents share a global constraint.
Abstract: In several real-world domains it is required to plan ahead while there are finite resources available for executing the plan. The limited availability of resources imposes constraints on the plans that can be executed, which need to be taken into account while computing a plan. A Constrained Partially Observable Markov Decision Process (Constrained POMDP) can be used to model resource-constrained planning problems which include uncertainty and partial observability. Constrained POMDPs provide a framework for computing policies which maximize expected reward, while respecting constraints on a secondary objective such as cost or resource consumption. Column generation for linear programming can be used to obtain Constrained POMDP solutions. This method incrementally adds columns to a linear program, in which each column corresponds to a POMDP policy obtained by solving an unconstrained subproblem. Column generation requires solving a potentially large number of POMDPs, as well as exact evaluation of the resulting policies, which is computationally difficult. We propose a method to solve subproblems in a two-stage fashion using approximation algorithms. First, we use a tailored point-based POMDP algorithm to obtain an approximate subproblem solution. Next, we convert this approximate solution into a policy graph, which we can evaluate efficiently. The resulting algorithm is a new approximate method for Constrained POMDPs in single-agent settings, but also in settings in which multiple independent agents share a global constraint. Experiments based on several domains show that our method outperforms the current state of the art.
TL;DR: Pearl's back-door adjustment is used as a predictive framework to develop a model robust to confounding shift under the condition that Z is observed at training time and it is shown that this approach is able to outperform baselines in controlled cases where confounding shift is manually injected between fitting time and prediction time.
Abstract: As statistical classifiers become integrated into real-world applications, it is important to consider not only their accuracy but also their robustness to changes in the data distribution. Although identifying and controlling for confounding variables Z-correlated with both the input X of a classifier and its output Y-has been assiduously studied in empirical social science, it is often neglected in text classification. This can be understood by the fact that, if we assume that the impact of confounding variables does not change between the time we fit a model and the time we use it, then prediction accuracy should only be slightly affected. We show in this paper that this assumption often does not hold and that when the influence of a confounding variable changes from training time to prediction time (i.e. under confounding shift), the classifier accuracy can degrade rapidly. We use Pearl's back-door adjustment as a predictive framework to develop a model robust to confounding shift under the condition that Z is observed at training time. Our approach does not make any causal conclusions but by experimenting on 6 datasets, we show that our approach is able to outperform baselines 1) in controlled cases where confounding shift is manually injected between fitting time and prediction time 2) in natural experiments where confounding shift appears either abruptly or gradually 3) in cases where there is one or multiple confounders. Finally, we discuss multiple issues we encountered during this research such as the effect of noise in the observation of Z and the importance of only controlling for confounding variables.
TL;DR: It is proved that distributed epistemic gossip protocols are implementable, that their partial correctness is decidable and that termination and two forms of fair termination of these protocols are decidable, as well.
Abstract: Gossip protocols aim at arriving, by means of point-to-point or group communications, at a situation in which all the agents know each other secrets. Distributed epistemic gossip protocols use as guards formulas from a simple epistemic logic and as statements calls between the agents. They are natural examples of knowledge based programs. We prove here that these protocols are implementable, that their partial correctness is decidable and that termination and two forms of fair termination of these protocols are decidable, as well. To establish these results we show that the definition of semantics and of truth of the underlying logic are decidable.
TL;DR: The new neural MT approach is reported together with a description of the foundational related works and recent approaches on using subword, characters and training with multilingual languages, among others.
Abstract: In the last years, deep learning algorithms have highly revolutionized several areas including speech, image and natural language processing. The specific field of Machine Translation (MT) has not remained invariant. Integration of deep learning in MT varies from re-modeling existing features into standard statistical systems to the development of a new architecture. Among the different neural networks, research works use feedforward neural networks, recurrent neural networks and the encoder-decoder schema. These architectures are able to tackle challenges as having low-resources or morphology variations.
This manuscript focuses on describing how these neural networks have been integrated to enhance different aspects and models from statistical MT, including language modeling, word alignment, translation, reordering, and rescoring. Then, we report the new neural MT approach together with a description of the foundational related works and recent approaches on using subword, characters and training with multilingual languages, among others. Finally, we include an analysis of the corresponding challenges and future work in using deep learning in MT.
TL;DR: This paper investigates the exchange problem where each agent is initially endowed with indivisible goods, agents' preferences are assumed to be conditionally lexicographic, and side payments are prohibited and proposes an exchange rule called augmented top-trading-cycles (ATTC), based on the original TTC procedure.
Abstract: Core-selection is a crucial property of rules in the literature of resource allocation. It is also desirable, from the perspective of mechanism design, to address the incentive of agents to cheat by misreporting their preferences. This paper investigates the exchange problem where (i) each agent is initially endowed with (possibly multiple) indivisible goods, (ii) agents' preferences are assumed to be conditionally lexicographic, and (iii) side payments are prohibited. We propose an exchange rule called augmented top-trading-cycles (ATTC), based on the original TTC procedure. We first show that ATTC is core-selecting and runs in polynomial time with respect to the number of goods. We then show that finding a beneficial misreport under ATTC is NP-hard. We finally clarify relationship of misreporting with splitting and hiding, two different types of manipulations, under ATTC.