BAHSD applies adaptive hierarchical distillation with dynamic-temperature KL divergence, ranking consistency, and InfoNCE contrastive learning to improve black-box sequential recommendation extraction on long-tail sequences.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation
BAHSD applies adaptive hierarchical distillation with dynamic-temperature KL divergence, ranking consistency, and InfoNCE contrastive learning to improve black-box sequential recommendation extraction on long-tail sequences.