SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 75 papers

TitleStatusHype
A no-regret generalization of hierarchical softmax to extreme multi-label classificationCode0
Learning a Compressed Sensing Measurement Matrix via Gradient UnrollingCode0
Deep Extreme Multi-label LearningCode0
Dense Retrieval as Indirect Supervision for Large-space Decision MakingCode0
Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU ServersCode0
HFT-CNN: Learning Hierarchical Category Structure for Multi-label Short Text CategorizationCode0
Bonsai -- Diverse and Shallow Trees for Extreme Multi-label ClassificationCode0
Dual-Encoders for Extreme Multi-Label ClassificationCode0
CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label ClassificationCode0
DiSMEC - Distributed Sparse Machines for Extreme Multi-label ClassificationCode0
Show:102550
← PrevPage 2 of 8Next →

No leaderboard results yet.