@inproceedings{dahiya2021siamesexml,
author = {Dahiya, Kunal and Agarwal, Ananye and Saini, Deepak and K, Gururaj and Jiao, Jian and Singh, Amit and Agarwal, Sumeet and Kar, Purushottam and Varma, Manik},
title = {SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels},
booktitle = {International Conference on Machine Learning},
year = {2021},
month = {July},
abstract = {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
applications such as ad and product recommendation involve labels rarely seen during training
but which nevertheless hold the key to recommendations that delight users. Effective utilization of label metadata and high quality predictions for rare labels at the scale of millions of
labels are thus key challenges in contemporary
XML research. To address these, this paper develops the SiameseXML framework based on a
novel probabilistic model that naturally motivates
a modular approach melding Siamese architectures with high-capacity extreme classifiers, and
a training pipeline that effortlessly scales to tasks
with 100 million labels. SiameseXML offers predictions 2–13% more accurate than leading XML
methods on public benchmark datasets, as well
as in live A/B tests on the Bing search engine,
it offers significant gains in click-through-rates,
coverage, revenue and other online metrics over
state-of-the-art techniques currently in production. Code for SiameseXML is available at https:
//github.com/Extreme-classification/siamesexml},
url = {http://approjects.co.za/?big=en-us/research/publication/siamesexml-siamese-networks-meet-extreme-classifiers-with-100m-labels/},
}