The task of annotating a data point with labels most relevant to it from a large universe of
labels is referred to as Extreme Classification (XC). State-of-the-art XC methods have …

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 …

Abstract In recent years, Dynamic Sparse Training (DST) has emerged as an alternative to
post-training pruning for generating efficient models. In principle, DST allows for a much …

This paper develops the MUFIN technique for extreme classification (XC) tasks with millions
of labels where datapoints and labels are endowed with visual and textual descriptors …

Negative sampling is a common approach for making the training of deep models in
classification problems with very large output spaces, known as extreme multilabel …

The objective in eXtreme Classification (XC) is to find relevant labels for a document from an
exceptionally large label space. Most XC application scenarios have rich auxiliary data …

Taxonomy completion, a self-supervised task, aims to add new concepts to an existing
taxonomy by attaching them to appropriate hypernym and hyponym pairs. Researchers …

This paper focuses on the task of Extreme Multi-Label Classification (XMC) whose goal is to
predict multiple labels for each instance from an extremely large label space. While existing …