AAAI Conference Research Articles

Frontmatter

The 20th AAAI conference on Artificial Intelligence and Interactive Digital Entertainment was held at the University of Kentucky, in Lexington, Kentucky, USA.

Observation impact explanation in atmospheric state estimation using hierarchical message-passing graph neural networks**This paper is significantly revised from an earlier version [] presented at the Explainable Machine Learning for Sciences Workshop (XAI4Sci) in conjunction with the 38th AAAI Conference on Artificial Intelligence (AAAI 2024) held in Vancouver, Canada, in February 2024.

Abstract The impact of meteorological observations on weather forecasting varies with the sensor type, location, time, and other environmental factors. Thus, the quantitative analysis of observation impacts is crucial for the effective and efficient development of weather forecasting systems. However, existing impact analysis methods are dependent on specific forecast systems, because system-specific adjoint models are used and the sensitivity of the observation to the forecast is measured. This study investigates the impact of observations on atmospheric state estimation in weather forecasting systems by developing a novel graph neural network (GNN) model specialized for analyzing the heterogeneous relations between observations and atmospheric states. The observation impact can then be assessed by applying explainable methods to the proposed GNN model, which is independent of forecasting systems. Further, we develop a novel application called ‘CloudNine,’ a system that provides impact analysis for individual observations with visualization. Our GNN model comprises hierarchical message-passing modules that separately analyze spatial correlations between observations at close locations and atmospheric states at close locations and then examine correlations between observations and atmospheric states. To consider the different factors influencing these correlations, we utilized geo-coordinates and types of observations in the attention mechanism of the modules with their feature vectors. We then applied gradient-based explainability methods to quantify the significance of the different observations in the estimation. Evaluated using data from 11 satellites and land-based observations, the results highlight the effectiveness of the proposed model and the visualization of observation impacts, enhancing the understanding and optimization of observational data in weather forecasting.

Learning representations for robust human–robot interaction

AbstractThis article summarizes the author's presentation in the New Faculty Highlight at the Thirty‐Eighth AAAI Conference on Artificial Intelligence. It discusses the desired properties of representations for enabling robust human–robot interaction. Examples from the author's work are presented to show how to build these properties into models for performing tasks with natural language guidance and engaging in social interactions with other agents.

Editors' Introduction to Special Issue of JQD:DM in Collaboration with ICWSM

This special issue aims to build bridges between scholarly communities engaging in the study of digital media. The result of a partnership between the International AAAI Conference on the Web and Social Media (ICWSM) and the Journal of Quantitative Description: Digital Media (JQD:DM), this effort provides both journal space and physical space for strengthening our interdisciplinary community. The eight articles in this volume showcase the diversity of data, methods, and contributions being made in the study of digital media. As editors, we are pleased at this collaborative forum for such interdisciplinary conversation, and it is our privilege to present the first set of articles — of many more to come.

Matching papers and reviewers at large conferences

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

RETRACTED: McOmet: Multimodal Fusion Transformer for Physical Audiovisual Commonsense Reasoning

This article, which was published in Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023), has been retracted by agreement between the authors and the journal. This statement refers to RETRACTED: McOmet: Multimodal Fusion Transformer for Physical Audiovisual Commonsense Reasoning.

Preface

The 19th AAAI conference on Artificial Intelligence and Interactive Digital Entertainment was held at the University of Utah, in Salt Lake City, Utah, USA.

Rationalizable behavior in the Hotelling–Downs model of spatial competition

We consider two scenarios of the Hotelling–Downs model of spatial competition. This setting has typically been explored using pure Nash equilibrium, but this paper uses point rationalizability (Bernheim, Econometrica J Economet Soc 52(4):1007–1028, 1984) instead. Pure Nash equilibrium imposes a correct beliefs assumption, which may rule out perfectly reasonable choices in a game. Point rationalizability does not have this correct beliefs assumption, which makes this solution concept more natural and permissive. The first scenario is the original Hotelling–Downs model with an arbitrary number of agents. Eaton and Lipsey (Rev Econ Stud 42(1):27–49, 1975) used pure Nash equilibrium as their solution concept for this setting. They showed that with three agents, there does not exist a pure Nash equilibrium. We characterize the set of point rationalizable choices for any number of agents and show that as the number of agents increases, the set of point rationalizable choices increases as well. In the second scenario, agents have limited attraction intervals (Feldman et al. Variations on the Hotelling–Downs model. In: Thirtieth AAAI Conference on Artificial Intelligence, pp 496–501, 2016). We show that the set of point rationalizable choices does not depend on the number of agents, apart from this number being odd or even. Furthermore, the set of point rationalizable choices shrinks as the attraction interval increases.

Preface

Proceedings of the Eighteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2022) preface by Stephen G. Ware and Markus Eger

The Third AI Summer: AAAI Robert S. Engelmore Memorial Lecture

This article summarizes the author's Robert S. Englemore Memorial Lecture presented at the Thirty-Fourth AAAI Conference on Artificial Intelligence on February 10, 2020. It explores recurring themes in the history of AI, real and imagined dangers from AI, and the future of the field.

The third AI summer: AAAI Robert S. Engelmore Memorial Lecture

The third AI summer: AAAI Robert S. Engelmore Memorial Lecture

Consistency of anchor-based spectral clustering

Abstract Anchor-based techniques reduce the computational complexity of spectral clustering algorithms. Although empirical tests have shown promising results, there is currently a lack of theoretical support for the anchoring approach. We define a specific anchor-based algorithm and show that it is amenable to rigorous analysis, as well as being effective in practice. We establish the theoretical consistency of the method in an asymptotic setting where data is sampled from an underlying continuous probability distribution. In particular, we provide sharp asymptotic conditions for the number of nearest neighbors in the algorithm, which ensure that the anchor-based method can recover with high probability disjoint clusters that are mutually separated by a positive distance. We illustrate the performance of the algorithm on synthetic data and explain how the theoretical convergence analysis can be used to inform the practical choice of parameter scalings. We also test the accuracy and efficiency of the algorithm on two large scale real data sets. We find that the algorithm offers clear advantages over standard spectral clustering. We also find that it is competitive with the state-of-the-art LSC method of Chen and Cai (Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011), while having the added benefit of a consistency guarantee.

Preface

This volume contains the papers accepted for presentation at SoCS 2013, the Sixth Annual Symposium on Combinatorial Search, held in Leavenworth, WA, USA on July 11–13, 2013. SoCS 2013 was held in cooperation with AAAI and collocated with the Twenty-Seventh AAAI Conference (AAAI 2013) and the 10th Symposium on Abstraction, Reformulation, and Approximation (SARA 2013).

Preface

The seventh meeting of the International AAAI Conference on Weblogs and Social Media (ICWSM-13) was held in Cambridge, Massachusetts. The year 2013 promises to be a benchmark year for ICWSM. Thanks to the enthusiastic participation of our community, we received a record number of submissions, with a growth of 50 percent over the previous year. More than the quantity, however, the high quality of the submitted papers is the truest evidence that ICWSM is maturing in its role as a premier venue for social media research.

Organizers

List of organizers of the Musical Metacreation workshop held at the Ninth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

Preface

Welcome to the Eighth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE’12). Computer games are a staple of today’s popular culture, and have been called the preemi- nent form of entertainment of the 21st century. The computer game industry has become a multibillion- dollar commercial enterprise. Game system require- ments are an important driver of hardware and soft- ware innovation in the computer industry.

Organizers

List of organizers of the AI in the Game Design Process workshop held at the Ninth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

Organizers

List of organizers of the Intelligent Narrative Technologies workshop held at the Ninth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

AIIDE-12 Organization

Organizers of the 2012 AIIDE AAAI Conference.

Sponsors

List of sponsors of Tenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.