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 31–40 of 75 papers

TitleStatusHype
On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification—0
Augmenting Training Data for Massive Semantic Matching Models in Low-Traffic E-commerce Stores—0
Investigating Active Learning Sampling Strategies for Extreme Multi Label Text Classification—0
Open Vocabulary Extreme Classification Using Generative Models—0
Extreme Multi-Label Classification with Label Masking for Product Attribute Value Extraction—0
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood PredictionCode0
Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU ServersCode0
On Riemannian Approach for Constrained Optimization Model in Extreme Classification Problems—0
TailMix: Overcoming the Label Sparsity for Extreme Multi-label Classification—0
Speeding-up One-vs-All Training for Extreme Classification via Smart Initialization—0
Show:102550
← PrevPage 4 of 8Next →

No leaderboard results yet.