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

Showing 125 of 75 papers

TitleStatusHype
Semantic Operators: A Declarative Model for Rich, AI-based Data ProcessingCode5
In-Context Learning for Extreme Multi-Label ClassificationCode3
DECAF: Deep Extreme Classification with Label FeaturesCode1
Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification FrameworkCode1
Propensity-scored Probabilistic Label TreesCode1
Probabilistic Label Trees for Extreme Multi-label ClassificationCode1
ELIAS: End-to-End Learning to Index and Search in Large Output SpacesCode1
Cluster-Guided Label Generation in Extreme Multi-Label ClassificationCode1
ECLARE: Extreme Classification with Label Graph CorrelationsCode1
Adversarial Extreme Multi-label ClassificationCode0
MDACE: MIMIC Documents Annotated with Code EvidenceCode0
Multi-label Learning with Random Circular VectorsCode0
Deep Extreme Multi-label LearningCode0
Dense Retrieval as Indirect Supervision for Large-space Decision MakingCode0
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood PredictionCode0
ICXML: An In-Context Learning Framework for Zero-Shot Extreme Multi-Label ClassificationCode0
CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label ClassificationCode0
Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU ServersCode0
Bonsai -- Diverse and Shallow Trees for Extreme Multi-label ClassificationCode0
Dual-Encoders for Extreme Multi-Label ClassificationCode0
Extreme Multi-label Learning for Semantic Matching in Product SearchCode0
HFT-CNN: Learning Hierarchical Category Structure for Multi-label Short Text CategorizationCode0
A no-regret generalization of hierarchical softmax to extreme multi-label classificationCode0
DiSMEC - Distributed Sparse Machines for Extreme Multi-label ClassificationCode0
Taming Pretrained Transformers for Extreme Multi-label Text ClassificationCode0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.