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 41–50 of 75 papers

TitleStatusHype
Unbiased Loss Functions for Extreme Classification With Missing Labels—0
Unbiased Loss Functions for Multilabel Classification with Missing Labels—0
Uncertainty in Extreme Multi-label Classification—0
UniDEC : Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification—0
Adopting the Multi-answer Questioning Task with an Auxiliary Metric for Extreme Multi-label Text Classification Utilizing the Label Hierarchy—0
On-the-fly Global Embeddings Using Random Projections for Extreme Multi-label Classification—0
Augmenting Training Data for Massive Semantic Matching Models in Low-Traffic E-commerce Stores—0
Block-wise Partitioning for Extreme Multi-label Classification—0
Content Explorer: Recommending Novel Entities for a Document Writer—0
Efficient Text Encoders for Labor Market Analysis—0
Show:102550
← PrevPage 5 of 8Next →

No leaderboard results yet.