← Search

Deepak Saini

3 accepted papers

2025

MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification

ICML 2025poster

Retrieval-augmented classification and generation models benefit from *early-stage fusion* of high-quality text-based metadata, often called memory, but face high latency and noise sensitivity. In extreme classification (XC), where low latency is crucial, existing methods use *late-stage fusion* for…

2024

OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification

ICML 2024poster

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 associated with the input documents, e.g., frequently clicked webpages for search queries in sponsored search. Unfort…

Cited by 2SourcePDFScholar
2021

SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels

ICML 2021spotlight

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 h…