We design a predictive layer for structured-output prediction (SOP) that can be plugged into
any neural network guaranteeing its predictions are consistent with a set of predefined …

This paper develops a novel methodology for using symbolic knowledge in deep learning.
From first principles, we derive a semantic loss function that bridges between neural output …

Challenges, experiments, and computational solutions in peer review Page 1 76
COMMUNICATIONS OF THE ACM | JUNE 2022 | VOL. 65 | NO. 6 review articles IMA GER YB Y …

From fundamental concepts and results to recent advances in computational social choice,
this open access book provides a thorough and in-depth look at multi-winner voting based …

We consider the following problem: There is a set of items (eg, movies) and a group of
agents (eg, passengers on a plane); each agent has some intrinsic utility for each of the …

We consider three important challenges in conference peer review:(i) reviewers maliciously
attempting to get assigned to certain papers to provide positive reviews, possibly as part of …

Social choice becomes easier on restricted preference domains such as single-peaked,
single-crossing, and Euclidean preferences. Many impossibility theorems disappear, the …

We study computational aspects of three prominent voting rules that use approval ballots to
elect multiple winners. These rules are satisfaction approval voting, proportional approval …

A survey of papers on practically significant restrictions on the preference profile of a
collective is carried out, including single-peaked preferences, group-separable preferences …

The more AI agents are deployed in scenarios with possibly unexpected situations, the more
they need to be flexible, adaptive, and creative in achieving the goal we have given them …