-
Integration of memory systems supporting non-symbolic representations in an architecture for lifelong development of artificial agents Artif. Intell. (IF 5.1) Pub Date : 2024-09-12 François Suro, Fabien Michel, Tiberiu Stratulat
Compared to autonomous agent learning, lifelong agent learning tackles the additional challenge of accumulating skills in a way favourable to long term development. What an agent learns at a given moment can be an element for the future creation of behaviours of greater complexity, whose purpose cannot be anticipated.
-
-
PathLAD+: Towards effective exact methods for subgraph isomorphism problem Artif. Intell. (IF 5.1) Pub Date : 2024-09-06 Yiyuan Wang, Chenghou Jin, Shaowei Cai
The subgraph isomorphism problem (SIP) is a challenging problem with wide practical applications. In the last decade, despite being a theoretical hard problem, researchers designed various algorithms for solving SIP. In this work, we propose five main strategies and develop an improved exact algorithm for SIP. First, we design a probing search procedure to try whether the search procedure can successfully
-
Interval abstractions for robust counterfactual explanations Artif. Intell. (IF 5.1) Pub Date : 2024-09-02 Junqi Jiang, Francesco Leofante, Antonio Rago, Francesca Toni
Counterfactual Explanations (CEs) have emerged as a major paradigm in explainable AI research, providing recourse recommendations for users affected by the decisions of machine learning models. However, CEs found by existing methods often become invalid when slight changes occur in the parameters of the model they were generated for. The literature lacks a way to provide exhaustive robustness guarantees
-
Polynomial calculus for optimization Artif. Intell. (IF 5.1) Pub Date : 2024-08-29 Ilario Bonacina, Maria Luisa Bonet, Jordi Levy
MaxSAT is the problem of finding an assignment satisfying the maximum number of clauses in a CNF formula. We consider a natural generalization of this problem to generic sets of polynomials and propose a weighted version of Polynomial Calculus to address this problem.
-
Approximating problems in abstract argumentation with graph convolutional networks Artif. Intell. (IF 5.1) Pub Date : 2024-08-29 Lars Malmqvist, Tangming Yuan, Peter Nightingale
In this article, we present a novel approximation approach for abstract argumentation using a customized Graph Convolutional Network (GCN) architecture and a tailored training method. Our approach demonstrates promising results in approximating abstract argumentation tasks across various semantics, setting a new state of the art for performance on certain tasks. We provide a detailed analysis of approximation
-
Characterising harmful data sources when constructing multi-fidelity surrogate models Artif. Intell. (IF 5.1) Pub Date : 2024-08-23 Nicolau Andrés-Thió, Mario Andrés Muñoz, Kate Smith-Miles
Surrogate modelling techniques have seen growing attention in recent years when applied to both modelling and optimisation of industrial design problems. These techniques are highly relevant when assessing the performance of a particular design carries a high cost, as the overall cost can be mitigated via the construction of a model to be queried in lieu of the available high-cost source. The construction
-
Is it possible to find the single nearest neighbor of a query in high dimensions? Artif. Intell. (IF 5.1) Pub Date : 2024-08-21 Kai Ming Ting, Takashi Washio, Ye Zhu, Yang Xu, Kaifeng Zhang
We investigate an open question in the study of the curse of dimensionality: Is it possible to find the single nearest neighbor of a query in high dimensions? Using the notion of (in)distinguishability to examine whether the feature map of a kernel is able to distinguish two distinct points in high dimensions, we analyze this ability of a metric-based Lipschitz continuous kernel as well as that of
-
Abstract argumentation frameworks with strong and weak constraints Artif. Intell. (IF 5.1) Pub Date : 2024-08-20 Gianvincenzo Alfano, Sergio Greco, Domenico Mandaglio, Francesco Parisi, Irina Trubitsyna
Dealing with controversial information is an important issue in several application contexts. Formal argumentation enables reasoning on arguments for and against a claim to decide on an outcome. Dung's abstract Argumentation Framework (AF) has emerged as a central formalism in argument-based reasoning. Key aspects of the success and popularity of Dung's framework include its simplicity and expressiveness
-
Bisimulation between base argumentation and premise-conclusion argumentation Artif. Intell. (IF 5.1) Pub Date : 2024-08-20 Jinsheng Chen, Beishui Liao, Leendert van der Torre
The structured argumentation system that represents arguments by premise-conclusion pairs is called premise-conclusion argumentation (PA) and the one that represents arguments by their premises is called base argumentation (BA). To assess whether BA and PA have the same ability in argument evaluation by extensional semantics, this paper defines the notion of extensional equivalence between BA and PA
-
On generalized notions of consistency and reinstatement and their preservation in formal argumentation Artif. Intell. (IF 5.1) Pub Date : 2024-08-18 Pietro Baroni, Federico Cerutti, Massimiliano Giacomin
We present a conceptualization providing an original domain-independent perspective on two crucial properties in reasoning: consistency and reinstatement. They emerge as a pair of dual characteristics, representing complementary requirements on the outcomes of reasoning processes. Central to our formalization are two underlying parametric relations: incompatibility and reinstatement violation. Different
-
Addressing maximization bias in reinforcement learning with two-sample testing Artif. Intell. (IF 5.1) Pub Date : 2024-08-16 Martin Waltz, Ostap Okhrin
Value-based reinforcement-learning algorithms have shown strong results in games, robotics, and other real-world applications. Overestimation bias is a known threat to those algorithms and can sometimes lead to dramatic performance decreases or even complete algorithmic failure. We frame the bias problem statistically and consider it an instance of estimating the maximum expected value (MEV) of a set
-
Modular control architecture for safe marine navigation: Reinforcement learning with predictive safety filters Artif. Intell. (IF 5.1) Pub Date : 2024-08-13 Aksel Vaaler, Svein Jostein Husa, Daniel Menges, Thomas Nakken Larsen, Adil Rasheed
Many autonomous systems are safety-critical, making it essential to have a closed-loop control system that satisfies constraints arising from underlying physical limitations and safety aspects in a robust manner. However, this is often challenging to achieve for real-world systems. For example, autonomous ships at sea have nonlinear and uncertain dynamics and are subject to numerous time-varying environmental
-
QCDCL with cube learning or pure literal elimination – What is best? Artif. Intell. (IF 5.1) Pub Date : 2024-08-08 Benjamin Böhm, Tomáš Peitl, Olaf Beyersdorff
Quantified conflict-driven clause learning (QCDCL) is one of the main approaches for solving quantified Boolean formulas (QBF). We formalise and investigate several versions of QCDCL that include cube learning and/or pure-literal elimination, and formally compare the resulting solving variants via proof complexity techniques. Our results show that almost all of the QCDCL variants are exponentially
-
Representing states in iterated belief revision Artif. Intell. (IF 5.1) Pub Date : 2024-08-05 Paolo Liberatore
Iterated belief revision requires information about the current beliefs. This information is represented by mathematical structures called doxastic states. Most literature concentrates on how to revise a doxastic state and neglects that it may exponentially grow. This problem is studied for the most common ways of storing a doxastic state. All four of them are able to store every doxastic state, but
-
Identifying roles of formulas in inconsistency under Priest's minimally inconsistent logic of paradox Artif. Intell. (IF 5.1) Pub Date : 2024-08-05 Kedian Mu
It has been increasingly recognized that identifying roles of formulas of a knowledge base in the inconsistency of that base can help us better look inside the inconsistency. However, there are few approaches to identifying such roles of formulas from a perspective of models in some paraconsistent logic, one of typical tools used to characterize inconsistency in semantics. In this paper, we characterize
-
NovPhy: A physical reasoning benchmark for open-world AI systems Artif. Intell. (IF 5.1) Pub Date : 2024-08-02 Vimukthini Pinto, Chathura Gamage, Cheng Xue, Peng Zhang, Ekaterina Nikonova, Matthew Stephenson, Jochen Renz
Due to the emergence of AI systems that interact with the physical environment, there is an increased interest in incorporating physical reasoning capabilities into those AI systems. But is it enough to only have physical reasoning capabilities to operate in a real physical environment? In the real world, we constantly face novel situations we have not encountered before. As humans, we are competent
-
Sample-based bounds for coherent risk measures: Applications to policy synthesis and verification Artif. Intell. (IF 5.1) Pub Date : 2024-08-02 Prithvi Akella, Anushri Dixit, Mohamadreza Ahmadi, Joel W. Burdick, Aaron D. Ames
Autonomous systems are increasingly used in highly variable and uncertain environments giving rise to the pressing need to consider risk in both the synthesis and verification of policies for these systems. This paper first develops a sample-based method to upper bound the risk measure evaluation of a random variable whose distribution is unknown. These bounds permit us to generate high-confidence
-
Manipulation and peer mechanisms: A survey Artif. Intell. (IF 5.1) Pub Date : 2024-08-02 Matthew Olckers, Toby Walsh
In peer mechanisms, the competitors for a prize also determine who wins. Each competitor may be asked to rank, grade, or nominate peers for the prize. Since the prize can be valuable, such as financial aid, course grades, or an award at a conference, competitors may be tempted to manipulate the mechanism. We survey approaches to prevent or discourage the manipulation of peer mechanisms. We conclude
-
On measuring inconsistency in graph databases with regular path constraints Artif. Intell. (IF 5.1) Pub Date : 2024-08-02 John Grant, Francesco Parisi
Real-world data are often inconsistent. Although a substantial amount of research has been done on measuring inconsistency, this research concentrated on knowledge bases formalized in propositional logic. Recently, inconsistency measures have been introduced for relational databases. However, nowadays, real-world information is always more frequently represented by graph-based structures which offer
-
An abstract and structured account of dialectical argument strength Artif. Intell. (IF 5.1) Pub Date : 2024-07-30 Henry Prakken
This paper presents a formal model of dialectical argument strength in terms of the number of ways in which an argument can be successfully attacked in expansions of an abstract argumentation framework. First a model is proposed that is abstract but designed to avoid overly limiting assumptions on instantiations or dialogue contexts. It is then shown that most principles for argument strength proposed
-
Truthful aggregation of budget proposals with proportionality guarantees Artif. Intell. (IF 5.1) Pub Date : 2024-07-30 Ioannis Caragiannis, George Christodoulou, Nicos Protopapas
We study a participatory budgeting problem, where a set of strategic agents wish to split a divisible budget among different projects, by aggregating their proposals on a single division. Unfortunately, the straightforward rule that divides the budget proportionally is susceptible to manipulation. Recently, a class of truthful mechanisms has been proposed, namely the moving phantom mechanisms. One
-
A crossword solving system based on Monte Carlo tree search Artif. Intell. (IF 5.1) Pub Date : 2024-07-25 Jingping Liu, Lihan Chen, Sihang Jiang, Chao Wang, Sheng Zhang, Jiaqing Liang, Yanghua Xiao, Rui Song
Although the development of AI in games is remarkable, intelligent machines still lag behind humans in games that require the ability of language understanding. In this paper, we focus on the crossword puzzle resolution task. Solving crossword puzzles is a challenging task since it requires the ability to answer natural language questions with knowledge and the ability to execute a search over possible
-
Multi-objective meta-learning Artif. Intell. (IF 5.1) Pub Date : 2024-07-25 Feiyang Ye, Baijiong Lin, Zhixiong Yue, Yu Zhang, Ivor W. Tsang
Meta-learning has arisen as a powerful tool for many machine learning problems. With multiple factors to be considered when designing learning models for real-world applications, meta-learning with multiple objectives has attracted much attention recently. However, existing works either linearly combine multiple objectives into one objective or adopt evolutionary algorithms to handle it, where the
-
ASQ-IT: Interactive explanations for reinforcement-learning agents Artif. Intell. (IF 5.1) Pub Date : 2024-07-22 Yotam Amitai, Ofra Amir, Guy Avni
As reinforcement learning methods increasingly amass accomplishments, the need for comprehending their solutions becomes more crucial. Most explainable reinforcement learning (XRL) methods generate a static explanation depicting their developers' intuition of what should be explained and how. In contrast, literature from the social sciences proposes that meaningful explanations are structured as a
-
Planning with mental models – Balancing explanations and explicability Artif. Intell. (IF 5.1) Pub Date : 2024-07-18 Sarath Sreedharan, Tathagata Chakraborti, Christian Muise, Subbarao Kambhampati
Human-aware planning involves generating plans that are explicable, i.e. conform to user expectations, as well as providing explanations when such plans cannot be found. In this paper, we bring these two concepts together and show how an agent can achieve a trade-off between these two competing characteristics of a plan. To achieve this, we conceive a first-of-its-kind planner that can reason about
-
A note on incorrect inferences in non-binary qualitative probabilistic networks Artif. Intell. (IF 5.1) Pub Date : 2024-07-14 Jack Storror Carter
Qualitative probabilistic networks (QPNs) combine the conditional independence assumptions of Bayesian networks with the qualitative properties of positive and negative dependence. They formalise various intuitive properties of positive dependence to allow inferences over a large network of variables. However, we will demonstrate in this paper that, due to an incorrect symmetry property, many inferences
-
Assessing fidelity in XAI post-hoc techniques: A comparative study with ground truth explanations datasets Artif. Intell. (IF 5.1) Pub Date : 2024-07-11 Miquel Miró-Nicolau, Antoni Jaume-i-Capó, Gabriel Moyà-Alcover
The evaluation of the fidelity of eXplainable Artificial Intelligence (XAI) methods to their underlying models is a challenging task, primarily due to the absence of a ground truth for explanations. However, assessing fidelity is a necessary step for ensuring a correct XAI methodology. In this study, we conduct a fair and objective comparison of the current state-of-the-art XAI methods by introducing
-
Class fairness in online matching Artif. Intell. (IF 5.1) Pub Date : 2024-07-09 Hadi Hosseini, Zhiyi Huang, Ayumi Igarashi, Nisarg Shah
We initiate the study of fairness among of agents in online bipartite matching where there is a given set of offline vertices (aka agents) and another set of vertices (aka items) that arrive online and must be matched irrevocably upon arrival. In this setting, agents are partitioned into classes and the matching is required to be fair with respect to the classes. We adapt popular fairness notions (e
-
Controlled query evaluation in description logics through consistent query answering Artif. Intell. (IF 5.1) Pub Date : 2024-07-02 Gianluca Cima, Domenico Lembo, Riccardo Rosati, Domenico Fabio Savo
Controlled Query Evaluation (CQE) is a framework for the protection of confidential data, where a given in terms of logic formulae indicates which information must be kept private. Functions called filter query answering so that no answers are returned that may lead a user to infer data protected by the policy. The preferred censors, called censors, are the ones that conceal only what is necessary
-
Incremental measurement of structural entropy for dynamic graphs Artif. Intell. (IF 5.1) Pub Date : 2024-07-02 Runze Yang, Hao Peng, Chunyang Liu, Angsheng Li
Structural entropy is a metric that measures the amount of information embedded in graph structure data under a strategy of hierarchical abstracting. To measure the structural entropy of a dynamic graph, we need to decode the optimal encoding tree corresponding to the best community partitioning for each snapshot. However, the current methods do not support dynamic encoding tree updating and incremental
-
Adversarial analysis of similarity-based sign prediction Artif. Intell. (IF 5.1) Pub Date : 2024-06-27 Michał T. Godziszewski, Marcin Waniek, Yulin Zhu, Kai Zhou, Talal Rahwan, Tomasz P. Michalak
Adversarial social network analysis explores how social links can be altered or otherwise manipulated to hinder unwanted information collection. To date, however, problems of this kind have not been studied in the context of signed networks in which links have positive and negative labels. Such formalism is often used to model social networks with positive links indicating friendship or support and
-
Hyper-heuristics for personnel scheduling domains Artif. Intell. (IF 5.1) Pub Date : 2024-06-25 Lucas Kletzander, Nysret Musliu
In real-life applications problems can frequently change or require small adaptations. Manually creating and tuning algorithms for different problem domains or different versions of a problem can be cumbersome and time-consuming. In this paper we consider several important problems with high practical relevance, which are Rotating Workforce Scheduling, Minimum Shift Design, and Bus Driver Scheduling
-
Boosting optimal symbolic planning: Operator-potential heuristics Artif. Intell. (IF 5.1) Pub Date : 2024-06-21 Daniel Fišer, Álvaro Torralba, Jörg Hoffmann
Heuristic search guides the exploration of states via heuristic functions estimating remaining cost. Symbolic search instead replaces the exploration of individual states with that of state sets, compactly represented using binary decision diagrams (BDDs). In cost-optimal planning, heuristic explicit search performs best overall, but symbolic search performs best in many individual domains, so both
-
Delegated online search Artif. Intell. (IF 5.1) Pub Date : 2024-06-20 Pirmin Braun, Niklas Hahn, Martin Hoefer, Conrad Schecker
In a delegation problem, a with commitment power tries to pick one out of options. Each option is drawn independently from a known distribution. Instead of inspecting the options herself, delegates the information acquisition to a rational and self-interested . After inspection, proposes one of the options, and can accept or reject.
-
An extensive study of security games with strategic informants Artif. Intell. (IF 5.1) Pub Date : 2024-06-12 Weiran Shen, Minbiao Han, Weizhe Chen, Taoan Huang, Rohit Singh, Haifeng Xu, Fei Fang
Over the past years, game-theoretic modeling for security and public safety issues (also known as ) have attracted intensive research attention and have been successfully deployed in many real-world applications for fighting, e.g., illegal poaching, fishing and urban crimes. However, few existing works consider how information from local communities would affect the structure of these games. In this
-
A domain-independent agent architecture for adaptive operation in evolving open worlds Artif. Intell. (IF 5.1) Pub Date : 2024-06-06 Shiwali Mohan, Wiktor Piotrowski, Roni Stern, Sachin Grover, Sookyung Kim, Jacob Le, Yoni Sher, Johan de Kleer
Model-based reasoning agents are ill-equipped to act in novel situations in which their model of the environment no longer sufficiently represents the world. We propose HYDRA, a framework for designing model-based agents operating in mixed discrete-continuous worlds that can autonomously detect when the environment has evolved from its canonical setup, understand how it has evolved, and adapt the agents'
-
Functional Relation Field: A Model-Agnostic Framework for Multivariate Time Series Forecasting Artif. Intell. (IF 5.1) Pub Date : 2024-06-05 Ting Li, Bing Yu, Jianguo Li, Zhanxing Zhu
In multivariate time series forecasting, the most popular strategy for modeling the relationship between multiple time series is the construction of graph, where each time series is represented as a node and related nodes are connected by edges. However, the relationship between multiple time series is typically complicated, e.g. the sum of outflows from upstream nodes may be equal to the inflows of
-
Stability based on single-agent deviations in additively separable hedonic games Artif. Intell. (IF 5.1) Pub Date : 2024-05-31 Felix Brandt, Martin Bullinger, Leo Tappe
Coalition formation is a central concern in multiagent systems. A common desideratum for coalition structures is stability, defined by the absence of beneficial deviations of single agents. Such deviations require an agent to improve her utility by joining another coalition. On top of that, the feasibility of deviations may also be restricted by demanding consent of agents in the welcoming and/or the
-
Joint learning of reward machines and policies in environments with partially known semantics Artif. Intell. (IF 5.1) Pub Date : 2024-05-23 Christos K. Verginis, Cevahir Koprulu, Sandeep Chinchali, Ufuk Topcu
We study the problem of reinforcement learning for a task encoded by a reward machine. The task is defined over a set of properties in the environment, called atomic propositions, and represented by Boolean variables. One unrealistic assumption commonly used in the literature is that the truth values of these propositions are accurately known. In real situations, however, these truth values are uncertain
-
Credulous acceptance in high-order argumentation frameworks with necessities: An incremental approach Artif. Intell. (IF 5.1) Pub Date : 2024-05-22 Gianvincenzo Alfano, Andrea Cohen, Sebastian Gottifredi, Sergio Greco, Francesco Parisi, Guillermo R. Simari
Argumentation is an important research area in the field of AI. There is a substantial amount of work on different aspects of Dung's abstract Argumentation Framework (AF). Two relevant aspects considered separately so far are: ) extending the framework to account for recursive attacks and supports, and considering dynamics, , AFs evolving over time. In this paper, we jointly deal with these two aspects
-
Optimizing pathfinding for goal legibility and recognition in cooperative partially observable environments Artif. Intell. (IF 5.1) Pub Date : 2024-05-21 Sara Bernardini, Fabio Fagnani, Alexandra Neacsu, Santiago Franco
In this paper, we perform a joint design of goal legibility and recognition in a cooperative, multi-agent pathfinding setting with partial observability. More specifically, we consider a set of identical agents (the actors) that move in an environment only partially observable to an observer in the loop. The actors are tasked with reaching a set of locations that need to be serviced in a timely fashion
-
Acquiring and modeling abstract commonsense knowledge via conceptualization Artif. Intell. (IF 5.1) Pub Date : 2024-05-17 Mutian He, Tianqing Fang, Weiqi Wang, Yangqiu Song
Conceptualization, or viewing entities and situations as instances of abstract concepts in mind and making inferences based on that, is a vital component in human intelligence for commonsense reasoning. Despite recent progress in artificial intelligence to acquire and model commonsense attributed to neural language models and commonsense knowledge graphs (CKGs), conceptualization is yet to be introduced
-
Knowledge is power: Open-world knowledge representation learning for knowledge-based visual reasoning Artif. Intell. (IF 5.1) Pub Date : 2024-05-13 Wenbo Zheng, Lan Yan, Fei-Yue Wang
Knowledge-based visual reasoning requires the ability to associate outside knowledge that is not present in a given image for cross-modal visual understanding. Two deficiencies of the existing approaches are that (1) they only employ or construct elementary and but superficial knowledge graphs while lacking complex and but indispensable cross-modal knowledge for visual reasoning, and (2) they also
-
Learning spatio-temporal dynamics on mobility networks for adaptation to open-world events Artif. Intell. (IF 5.1) Pub Date : 2024-05-08 Zhaonan Wang, Renhe Jiang, Hao Xue, Flora D. Salim, Xuan Song, Ryosuke Shibasaki, Wei Hu, Shaowen Wang
As a decisive part in the success of Mobility-as-a-Service (MaaS), spatio-temporal dynamics modeling on mobility networks is a challenging task particularly considering scenarios where open-world events drive mobility behavior deviated from the routines. While tremendous progress has been made to model high-level spatio-temporal regularities with deep learning, most, if not all of the existing methods
-
Exploring the psychology of LLMs’ moral and legal reasoning Artif. Intell. (IF 5.1) Pub Date : 2024-05-03 Guilherme F.C.F. Almeida, José Luiz Nunes, Neele Engelmann, Alex Wiegmann, Marcelo de Araújo
Large language models (LLMs) exhibit expert-level performance in tasks across a wide range of different domains. Ethical issues raised by LLMs and the need to align future versions makes it important to know how state of the art models reason about moral and legal issues. In this paper, we employ the methods of experimental psychology to probe into this question. We replicate eight studies from the
-
A multi-graph representation for event extraction Artif. Intell. (IF 5.1) Pub Date : 2024-05-03 Hui Huang, Yanping Chen, Chuan Lin, Ruizhang Huang, Qinghua Zheng, Yongbin Qin
Event extraction has a trend in identifying event triggers and arguments in a unified framework, which has the advantage of avoiding the cascading failure in pipeline methods. The main problem is that joint models usually assume a one-to-one relationship between event triggers and arguments. It leads to the argument multiplexing problem, in which an argument mention can serve different roles in an
-
Mitigating social biases of pre-trained language models via contrastive self-debiasing with double data augmentation Artif. Intell. (IF 5.1) Pub Date : 2024-04-26 Yingji Li, Mengnan Du, Rui Song, Xin Wang, Mingchen Sun, Ying Wang
Pre-trained Language Models (PLMs) have been shown to inherit and even amplify the social biases contained in the training corpus, leading to undesired stereotype in real-world applications. Existing techniques for mitigating the social biases of PLMs mainly rely on data augmentation with manually designed prior knowledge or fine-tuning with abundant external corpora to debias. However, these methods
-
Iterative voting with partial preferences Artif. Intell. (IF 5.1) Pub Date : 2024-04-21 Zoi Terzopoulou, Panagiotis Terzopoulos, Ulle Endriss
Voting platforms can offer participants the option to sequentially modify their preferences, whenever they have a reason to do so. But such iterative voting may never converge, meaning that a state where all agents are happy with their submitted preferences may never be reached. This problem has received increasing attention within the area of computational social choice. Yet, the relevant literature
-
Probabilistic reach-avoid for Bayesian neural networks Artif. Intell. (IF 5.1) Pub Date : 2024-04-17 Matthew Wicker, Luca Laurenti, Andrea Patane, Nicola Paoletti, Alessandro Abate, Marta Kwiatkowska
Model-based reinforcement learning seeks to simultaneously learn the dynamics of an unknown stochastic environment and synthesise an optimal policy for acting in it. Ensuring the safety and robustness of sequential decisions made through a policy in such an environment is a key challenge for policies intended for safety-critical scenarios. In this work, we investigate two complementary problems: first
-
A unified momentum-based paradigm of decentralized SGD for non-convex models and heterogeneous data Artif. Intell. (IF 5.1) Pub Date : 2024-04-17 Haizhou Du, Chaoqian Cheng, Chengdong Ni
Emerging distributed applications recently boosted the development of decentralized machine learning, especially in IoT and edge computing fields. In real-world scenarios, the common problems of non-convexity and data heterogeneity result in inefficiency, performance degradation, and development stagnation. The bulk of studies concentrate on one of the issues mentioned above without having a more general
-
Discrete preference games with logic-based agents: Formal framework, complexity, and islands of tractability Artif. Intell. (IF 5.1) Pub Date : 2024-04-08 Gianluigi Greco, Marco Manna
Analyzing and predicting the dynamics of opinion formation in the context of social environments are problems that attracted much attention in literature. While grounded in social psychology, these problems are nowadays popular within the artificial intelligence community, where opinion dynamics are often studied via models in which individuals/agents hold opinions taken from a fixed set of alternatives
-
Critical observations in model-based diagnosis Artif. Intell. (IF 5.1) Pub Date : 2024-03-29 Cody James Christopher, Alban Grastien
In this paper, we address the problem of finding the part of the observations that is useful for the diagnosis. We define a as an abstraction of the observations. We then argue that a sub-observation is if it allows a diagnoser to derive the same minimal diagnosis as the original observations; and we define as a maximally abstracted sufficient sub-observation. We show how to compute a critical observation
-
Polarized message-passing in graph neural networks Artif. Intell. (IF 5.1) Pub Date : 2024-03-27 Tiantian He, Yang Liu, Yew-Soon Ong, Xiaohu Wu, Xin Luo
In this paper, we present Polarized message-passing (PMP), a novel paradigm to revolutionize the design of message-passing graph neural networks (GNNs). In contrast to existing methods, PMP captures the power of node-node similarity and dissimilarity to acquire dual sources of messages from neighbors. The messages are then coalesced to enable GNNs to learn expressive representations from sparse but
-
Matching papers and reviewers at large conferences Artif. Intell. (IF 5.1) Pub Date : 2024-03-25 Kevin Leyton-Brown, Mausam, Yatin Nandwani, Hedayat Zarkoob, Chris Cameron, Neil Newman, Dinesh Raghu
Peer-reviewed conferences, the main publication venues in CS, rely critically on matching highly qualified reviewers for each paper. Because of the growing scale of these conferences, the tight timelines on which they operate, and a recent surge in explicitly dishonest behavior, there is now no alternative to performing this matching in an automated way. This paper introduces , a novel reviewer–paper
-
Almost proportional allocations of indivisible chores: Computation, approximation and efficiency Artif. Intell. (IF 5.1) Pub Date : 2024-03-24 Haris Aziz, Bo Li, Hervé Moulin, Xiaowei Wu, Xinran Zhu
Proportionality (PROP) is one of the simplest and most intuitive fairness criteria used for allocating items among agents with additive utilities. However, when the items are indivisible, ensuring PROP becomes unattainable, leading to increased focus on its relaxations. In this paper, we focus on the relaxation of proportionality up to any item (PROPX), where proportionality is satisfied if an arbitrary
-
Knowledge-driven profile dynamics Artif. Intell. (IF 5.1) Pub Date : 2024-03-21 Eduardo Fermé, Marco Garapa, Maurício D.L. Reis, Yuri Almeida, Teresa Paulino, Mariana Rodrigues
In the last decades, user profiles have been used in several areas of information technology. In the literature, most research works, and systems focus on the creation of profiles (using Data Mining techniques based on user's navigation or interaction history). In general, the dynamics of profiles are made by means of a systematic recreation of the profiles, without using the previous profiles. In
-
Regular decision processes Artif. Intell. (IF 5.1) Pub Date : 2024-03-21 Ronen I. Brafman, Giuseppe De Giacomo
We introduce and study Regular Decision Processes (RDPs), a new, compact model for domains with non-Markovian dynamics and rewards, in which the dependence on the past is regular, in the language theoretic sense. RDPs are an intermediate model between MDPs and POMDPs. They generalize -order MDPs and can be viewed as a POMDP in which the hidden state is a regular function of the entire history. In factored
-
Lifted algorithms for symmetric weighted first-order model sampling Artif. Intell. (IF 5.1) Pub Date : 2024-03-19 Yuanhong Wang, Juhua Pu, Yuyi Wang, Ondřej Kuželka
Weighted model counting (WMC) is the task of computing the weighted sum of all satisfying assignments (i.e., models) of a propositional formula. Similarly, weighted model sampling (WMS) aims to randomly generate models with probability proportional to their respective weights. Both WMC and WMS are hard to solve exactly, falling under the #-hard complexity class. However, it is known that the counting
-
Embedding justification theory in approximation fixpoint theory Artif. Intell. (IF 5.1) Pub Date : 2024-03-16 Simon Marynissen, Bart Bogaerts, Marc Denecker
Approximation Fixpoint Theory (AFT) and Justification Theory (JT) are two frameworks to unify logical formalisms. AFT studies semantics in terms of fixpoints of lattice operators, and JT in terms of so-called justifications, which are explanations of why certain facts do or do not hold in a model. While the approaches differ, the frameworks were designed with similar goals in mind, namely to study