SEHP generates hard negative hyperedges with a conditional, score-guided iterative denoiser and accelerates training by sampling sub-hypergraphs and classifying latent representations directly.
Bhuiyan, Mahmudur Rahman, Mahmuda Rahman, and Mohammad Al Hasan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scalable and Effective Negative Sample Generation for Hyperedge Prediction
SEHP generates hard negative hyperedges with a conditional, score-guided iterative denoiser and accelerates training by sampling sub-hypergraphs and classifying latent representations directly.