Extreme Multi-Label Classification

Extreme Multi-Label Classification is a supervised learning problem where an instance may be associated with multiple labels. The two main problems are the unbalanced labels in the dataset and the amount of different labels.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 75 papers

Title	Date	Tasks	Status	Score
A no-regret generalization of hierarchical softmax to extreme multi-label classification	Oct 27, 2018	Extreme Multi-Label ClassificationGeneral Classification	CodeCode Available	5
ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label Classification	Nov 16, 2023	Extreme Multi-Label ClassificationIn-Context Learning	CodeCode Available	5
Deep Extreme Multi-label Learning	Apr 12, 2017	ClassificationExtreme Multi-Label Classification	CodeCode Available	5
Dense Retrieval as Indirect Supervision for Large-space Decision Making	Oct 28, 2023	Decision MakingEntity Typing	CodeCode Available	5
Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers	Oct 13, 2021	Extreme Multi-Label ClassificationGPU	CodeCode Available	5
Generalized test utilities for long-tail performance in extreme multi-label classification	Nov 9, 2023	Extreme Multi-Label ClassificationMissing Labels	CodeCode Available	5
Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification	Apr 17, 2019	ClassificationExtreme Multi-Label Classification	CodeCode Available	5
Dual-Encoders for Extreme Multi-Label Classification	Oct 16, 2023	ClassificationExtreme Multi-Label Classification	CodeCode Available	5
CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification	Oct 29, 2022	Extreme Multi-Label ClassificationMulti-Label Classification	CodeCode Available	5
DiSMEC - Distributed Sparse Machines for Extreme Multi-label Classification	Sep 8, 2016	ClassificationExtreme Multi-Label Classification	CodeCode Available	5

Show:10 25 50

← PrevPage 2 of 8Next →

No leaderboard results yet.