Abstract We present the Open Graph Benchmark (OGB), a diverse set of challenging and
realistic benchmark datasets to facilitate scalable, robust, and reproducible graph machine …

Neural ranking models for information retrieval (IR) use shallow or deep neural networks to
rank search results in response to a query. Traditional learning to rank models employ …

As the number of AI systems keeps growing, it is fundamental to implement and develop
efficient control mechanisms to ensure the safe and proper functioning of machine learning …

We study off-policy evaluation (OPE) of contextual bandit policies for large discrete action
spaces where conventional importance-weighting approaches suffer from excessive …

A central problem in sequential decision making is to develop algorithms that are practical
and computationally efficient, yet support the use of flexible, general-purpose models …

Recent advances by practitioners in the deep learning community have breathed new life
into Locality Sensitive Hashing (LSH), using it to reduce memory and time bottlenecks in …

Deep extreme multi-label learning (XML) requires training deep architectures that can tag a
data point with its most relevant subset of labels from an extremely large label set. XML …

Abstract The goal of Extreme Multi-label Classification (XC) is to learn representations that
enable map** input texts to the most relevant subset of labels selected from an extremely …

Existing Graph Neural Networks (GNNs) compute the message exchange between nodes
by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by …

Dual-encoder (DE) models are widely used in retrieval tasks, most commonly studied on
open QA benchmarks that are often characterized by multi-class and limited training data. In …