Many policies in the US are determined locally, eg, at the county-level. Local policy regimes
provide flexibility between regions, but may become less effective in the presence of …

In this paper we address the problem of building user models that can predict the rate at
which individuals consume items from a finite set, including items they have consumed in …

Variational Graph Autoencoders (VGAEs) are powerful models for unsupervised learning of
node representations from graph data. In this work, we systematically analyze modeling …

The self-attention mechanism is the backbone of the transformer neural network underlying
most large language models. It can capture complex word patterns and long-range …

Recommender systems learn users' preferences from their explicit feedback, such as
ratings, and implicit feedback, such as purchases. Learning a user's preference from implicit …

Abstract The IRI Marketing Data Set was introduced in 2008 (Bronnenberg, Kruger and
Mela, 2008) with five years of data. The data set was expanded to include more than twice …

Word embeddings refer to vector representations of words that can capture their meanings.
Those vectors can be applied in diverse NLP tasks [1]. Recently, several studies present the …

In an interconnected world, effective policymaking increasingly relies on understanding
complex human networks, such as contact networks for pandemic response, supply chain …

Recommender systems have been utilized in various online services. Recommendations
help users of these services to find interesting items. Recommender systems are also …

Analyzing crime data is a challenging task, especially homicide data due to the low-
frequency and spatial sparsity of the occurrences. In this work, we use Zero Inflated …