Graph Regularized Encoder Training for Extreme Classification

arXiv:2402.18434v1 Announce Type: new
Abstract: Deep extreme classification (XC) aims to train an encoder architecture and an accompanying classifier architecture to tag a data point with the most relevant subset of labels from a very large universe of labels. XC applications in ranking, recommendation and tagging routinely encounter tail labels for which the amount of training data is exceedingly small. Graph convolutional networks (GCN) present a convenient but computationally expensive way to leverage task metadata and enhance model accuracies in …

abstract applications architecture arxiv classification classifier cs.ir cs.lg data encoder graph labels ranking recommendation tag tagging train training type universe