Voting is used widely to identify a collective decision for a group of agents, based on their preferences. In this paper, we focus on evaluating and designing voting rules that support both the privacy of the voting agents and a notion of fairness over such agents. To do this, we introduce a novel notion of group fairness and adopt the existing notion of local differential privacy. We then evaluate the level of group fairness in several existing voting rules, as well as the trade-offs between fairness and privacy, showing that it is not possible to always obtain maximal economic efficiency with high fairness or high privacy levels. Then, we present both a machine learning and a constrained optimization approach to design new voting rules that are fair while maintaining a high level of economic efficiency. Finally, we empirically examine the effect of adding noise to create local differentially private voting rules and discuss the three-way trade-off between economic efficiency, fairness, and privacy. This paper appears in the special track on AI & Society.

James A. Hendler was recognized with the AAAI Distinguished Service Award at AAAI-17 for his contributions to the field of artificial intelligence through sustained service to AAAI, other professional societies and government activities promoting the importance of artificial intelligence research. This article presents his recipe for success advice, with advice directed at newer AI researchers (with some notes for experienced ones as well).

We consider ordinal approximation algorithms for a broad class of utility maximization problems for multi-agent systems. In these problems, agents have utilities for connecting to each other, and the goal is to compute a maximum-utility solution subject to a set of constraints. We represent these as a class of graph optimization problems, including matching, spanning tree problems, TSP, maximum weight planar subgraph, and many others. We study these problems in the ordinal setting: latent numerical utilities exist, but we only have access to ordinal preference information, i.e., every agent specifies an ordering over the other agents by preference. We prove that for the large class of graph problems we identify, ordinal information is enough to compute solutions which are close to optimal, thus demonstrating there is no need to know the underlying numerical utilities. For example, for problems in this class with bounded degree b a simple ordinal greedy algorithm always produces a (b + 1)-approximation; we also quantify how the quality of ordinal approximation depends on the sparsity of the resulting graphs. In particular, our results imply that ordinal information is enough to obtain a 2-approximation for Maximum Spanning Tree; a 4-approximation for Max Weight Planar Subgraph; a 2-approximation for Max-TSP; and a 2- approximation for various Matching problems.

Driven by successes in deep learning, computer vision research has begun to move beyond object detection and image classification to more sophisticated tasks like image captioning or visual question answering. Motivating such endeavors is the desire for models to capture not only objects present in an image, but more fine-grained aspects of a scene such as relationships between objects and their attributes. Scene graphs provide a formal construct for capturing these aspects of an image. Despite this, there have been only a few recent efforts to generate scene graphs from imagery. Previous works limit themselves to settings where bounding box information is available at train time and do not attempt to generate scene graphs with attributes. In this paper we propose a method, based on recent advancements in Generative Adversarial Networks, to overcome these deficiencies. We take the approach of first generating small subgraphs, each describing a single statement about a scene from a specific region of the input image chosen using an attention mechanism. By doing so, our method is able to produce portions of the scene graphs with attribute information without the need for bounding box labels. Then, the complete scene graph is constructed from these subgraphs. We show that our model improves upon prior work in scene graph generation on state-of-the-art data sets and accepted metrics. Further, we demonstrate that our model is capable of handling a larger vocabulary size than prior work has attempted.

We propose a hierarchical extension to hidden Markov model (HMM) under the Bayesian framework to overcome its limited model capacity. The model parameters are treated as random variables whose distributions are governed by hyperparameters. Therefore the variation in data can be modeled at both instance level and distribution level. We derive a novel learning method for estimating the parameters and hyperparameters of our model based on adversarial learning framework, which has shown promising results in generating photorealistic images and videos. We demonstrate the benefit of the proposed method on human motion capture data through comparison with both state-of-the-art methods and the same model that is learned by maximizing likelihood. The first experiment on reconstruction shows the model's capability of generalizing to novel testing data. The second experiment on synthesis shows the model's capability of generating realistic and diverse data.

The "democratization" of AI has been taken up as a primary goal by several major tech companies. However, these efforts resemble earlier "freeware" and "open access" initiatives, and it is unclear how or whether they are informed by political conceptions of democratic governance. A political formulation of the democratization of AI is thus necessary. This paper presents a framework for the democratic governance of technology through intelligent trial and error (ITE) that can be utilized to evaluate barriers to the democratization of AI and suggest strategies for overcoming them.

Natural Language Understanding (NLU, not NLP) in Cognitive Systems

This is an area where statistics-and MLbased that cognitive system developers currently address systems can be symbiotic with cognitive systems: the and methodological preferences that they, by and former can provide advanced computation frameworks large, share. For some of the issues, the consensus is while the latter can provide content-related not entirely universal, which is to be expected for a insights into the choice of the inventory of features to group of active developers. Still, the general points of consensus should help to characterize the overall be used in making decisions.

Developing cognitive agents with human-level natural language understanding (NLU) capabilities requires modeling human cognition because natural, unedited utterances regularly contain ambiguities, ellipses, production errors, implicatures, and many other types of complexities. Moreover, cognitive agents must be nimble in the face of incomplete interpretations since even people do not perfectly understand every aspect of every utterance they hear. So, once an agent has reached the best interpretation it can, it must determine how to proceed – be that acting upon the new information directly, remembering an incomplete interpretation and waiting to see what happens next, seeking out information to fill in the blanks, or asking its interlocutor for clarification. The reasoning needed to support NLU extends far beyond language itself, including, non-exhaustively, the agent’s understanding of its own plans and goals; its dynamic modeling of its interlocutor’s knowledge, plans, and goals, all guided by a theory of mind; its recognition of diverse aspects human behavior, such as affect, cooperative behavior, and the effects of cognitive biases; and its integration of linguistic interpretations with its interpretations of other perceptive inputs, such as simulated vision and non-linguistic audition. Considering all of these needs, it seems hardly possible that fundamental NLU will ever be achieved through the kinds of knowledge-lean text-string manipulation being pursued by the mainstream natural language processing (NLP) community. Instead, it requires a holistic approach to cognitive modeling of the type we are pursuing in a paradigm called OntoAgent.

He noted the shared interest of the members of this community in studying high-level cognition, structured representations, comprehensive system development, heuristics, and openness to insights into human cognition. The developments of the last five years warrant a new look at the issues. The five thematic articles in this issue offers such a look. The contributions are diverse and cover a representative -- though by no means a complete -- set of issues and opinions. Sergei Nirenburg's introductory essay offers a bird's eye view of the current directions of research in the field and suggests some aspirational issues that need attention for the cognitive systems community to make a lasting impact.