Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction
Accurate watch-time (WT) prediction is an important requirement for short-video recommendations. Yet WT distributions are near-zero-inflated, long-tailed and multimodal. The recent Exponential-Gaussian Mixture Network (EGMN) models the full conditional WT distribution rather than a single point estimate and achieves state-of-the-art performance. Our large-scale reproduction study reveals that EGMN is vulnerable to variance collapse, component redundancy, and inactive components. We propose a Hierarchical Exponential-Gaussian Mixture (HEGM) model that addresses these failure modes through a hie
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Sofia Gulevskaia →
“Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction”
- LinkedLinked via arxiv author · 85%Mikhail Trapeznikov →
“Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction”
- LinkedLinked via arxiv author · 85%Aleksandr Poslavsky →
“Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction”
- LinkedLinked via arxiv author · 85%Alexander D'yakonov →
“Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction”