Artificial Intelligence最新文献

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 game-theoretic models in which individuals/agents hold opinions taken from a fixed set of discrete alternatives, and where the goal is to find those configurations where the opinions expressed by the agents emerge as a kind of compromise between their innate opinions and the social pressure they receive from the environments. As a matter of facts, however, these studies are based on very high-level and sometimes simplistic formalizations of the social environments, where the mental state of each individual is typically encoded as a variable taking values from a Boolean domain. To overcome these limitations, the paper proposes a framework generalizing such discrete preference games by modeling the reasoning capabilities of agents in terms of weighted propositional logics. It is shown that the framework easily encodes different kinds of earlier approaches and fits more expressive scenarios populated by conformist and dissenter agents. Problems related to the existence and computation of stable configurations are studied, under different theoretical assumptions on the structural shape of the social interactions and on the class of logic formulas that are allowed. Remarkably, during its trip to identify some relevant tractability islands, the paper devises a novel technical machinery whose significance goes beyond the specific application to analyzing opinion formation and diffusion, since it significantly enlarges the class of Integer Linear Programs that were known to be tractable so far.

In this paper, we address the problem of finding the part of the observations that is useful for the diagnosis. We define a sub-observation as an abstraction of the observations. We then argue that a sub-observation is sufficient if it allows a diagnoser to derive the same minimal diagnosis as the original observations; and we define critical observations as a maximally abstracted sufficient sub-observation. We show how to compute a critical observation, and discuss a number of algorithmic improvements that also shed light on the theory of critical observations. Finally, we illustrate this framework on both state-based and event-based observations.

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 strongly correlated neighbors. Three novel GNNs based on the PMP paradigm, namely PMP graph convolutional network (PMP-GCN), PMP graph attention network (PMP-GAT), and PMP graph PageRank network (PMP-GPN) are proposed to perform various downstream tasks. Theoretical analysis is also conducted to verify the high expressiveness of the proposed PMP-based GNNs. In addition, an empirical study of five learning tasks based on 12 real-world datasets is conducted to validate the performances of PMP-GCN, PMP-GAT, and PMP-GPN. The proposed PMP-GCN, PMP-GAT, and PMP-GPN outperform numerous strong message-passing GNNs across all five learning tasks, demonstrating the effectiveness of the proposed PMP paradigm.

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 Large Conference Matching (LCM), a novel reviewer–paper matching approach that was recently deployed in the 35th AAAI Conference on Artificial Intelligence (AAAI 2021), and has since been adopted (wholly or partially) by other conferences including ICML 2022, AAAI 2022-2024, and IJCAI 2022-2024. LCM has three main elements: (1) collecting and processing input data to identify problematic matches and generate reviewer–paper scores; (2) formulating and solving an optimization problem to find good reviewer–paper matchings; and (3) a two-phase reviewing process that shifts reviewing resources away from papers likely to be rejected and towards papers closer to the decision boundary. This paper also describes an evaluation of these innovations based on an extensive post-hoc analysis on real data—including a comparison with the matching algorithm used in AAAI's previous (2020) iteration—and supplements this with additional numerical experimentation.²

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 item is removed from every agent's allocation. We show that PROPX is an appealing fairness notion for the allocation of indivisible chores, which approximately implies some share-based notions, such as maximin share (MMS) and AnyPrice share (APS). We further provide a comprehensive understanding of PROPX allocations, regarding the computation, approximation, and compatibility with efficiency. On top of these, we extend the study to scenarios where agents do not share equal liability towards the chores, and approximate PROPX allocations using partial information about agents' utilities.

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 this paper we propose to formalize the creation, representation, and dynamics of profiles from a Knowledge-Driven perspective. We introduce and axiomatically characterize four operators for changing profiles using a belief change inspired approach.

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 k-order MDPs and can be viewed as a POMDP in which the hidden state is a regular function of the entire history. In factored RDPs, transition and reward functions are specified using formulas in linear temporal logics over finite traces, or using regular expressions. This allows specifying complex dependence on the past using intuitive and compact formulas, and building models of partially observable domains without specifying an underlying state space.