Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distribution

Ashutosh Agarwal
11/7/2025
cs.LGcs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

This paper presents a novel solution, LEVER, designed to address the challenges posed by underperforming infrequent categories in Extreme Classification (XC) tasks. Infrequent categories, often characterized by sparse samples, suffer from high label inconsistency, which undermines classification performance. LEVER mitigates this problem by adopting a robust Siamese-style architecture, leveraging knowledge transfer to reduce label inconsistency and enhance the performance of One-vs-All classifiers. Comprehensive testing across multiple XC datasets reveals substantial improvements in the handling of infrequent categories, setting a new benchmark for the field. Additionally, the paper introduces two newly created multi-intent datasets, offering essential resources for future XC research.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Multi-Head Encoding for Extreme Label Classification

81% match1 repo472024

Labels in Extremes: How Well Calibrated are Extreme Multi-label Classifiers?

80% match2024

PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation

80% match1 repo5542023

Generalized test utilities for long-tail performance in extreme multi-label classification

79% match2026

Graph Regularized Encoder Training for Extreme Classification

79% match2024

Navigating Extremes: Dynamic Sparsity in Large Output Spaces

77% match1 repo32024

Cite this paper

@article{agarwal2025optimizing,
  title  = {Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distribution},
  author = {Ashutosh Agarwal},
  year   = {2025},
  eprint = {2511.07459},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.07459v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.07459.svg)](https://codeofpaper.com/paper/2511.07459)

Discussion