Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Chapter

Download BibTeX

Title

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

Authors

[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee

Scientific discipline (Law 2.0)

[2.3] Information and communication technology

Year of publication

2023

Chapter type

chapter in monograph / paper

Publication language

english

Keywords
EN
  • extreme multi-label classification
  • complex performance metrics
  • long-tail phenomenon
  • expected test utility
Abstract

EN Extreme multi-label classification (XMLC) is the task of selecting a small subset of relevant labels from a very large set of possible labels. As such, it is characterized by long-tail labels, i.e., most labels have very few positive instances. With standard performance measures such as precision@k, a classifier can ignore tail labels and still report good performance. However, it is often argued that correct predictions in the tail are more “interesting” or “rewarding,” but the community has not yet settled on a metric capturing this intuitive concept. The existing propensity-scored metrics fall short on this goal by confounding the problems of long-tail and missing labels. In this paper, we analyze generalized metrics budgeted “at k” as an alternative solution. To tackle the challenging problem of optimizing these metrics, we formulate it in the expected test utility (ETU) framework, which aims at optimizing the expected performance on a fixed test set. We derive optimal prediction rules and construct computationally efficient approximations with provable regret guarantees and robustness against model misspecification. Our algorithm, based on block coordinate ascent, scales effortlessly to XMLC problems and obtains promising results in terms of long-tail performance.

URL

https://papers.nips.cc/paper_files/paper/2023/hash/46994b3d6dd0fd5fca5f780af6259db5-Abstract-Conference.html

Book

Advances in Neural Information Processing Systems 36 : Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10-16, 2023

Presented on

37th Conference on Neural Information Processing Systems (NeurIPS 2023), 10-16.12.2023, New Orleans, United States

Open Access Mode

publisher's website

Open Access Text Version

final published version

Ministry points / chapter

5

Ministry points / conference (CORE)

200

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.