SOTAVerified

Transductive Learning

In this setting, both a labeled training sample and an (unlabeled) test sample are provided at training time. The goal is to predict only the labels of the given test instances as accurately as possible.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 71–80 of 135 papers

TitleStatusHype
BertGCN: Transductive Text Classification by Combining GCN and BERTCode1
Transductive Learning for Abstractive News Summarization—0
Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning—0
DINE: Domain Adaptation from Single and Multiple Black-box PredictorsCode1
Learning Graph Neural Networks with Positive and Unlabeled Nodes—0
Fast Few-Shot Classification by Few-Iteration Meta-LearningCode0
Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time—0
Robust Collective Classification against Structural Attacks—0
Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples—0
Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural NetworksCode1
Show:102550
← PrevPage 8 of 14Next →

No leaderboard results yet.