DiffOR reformulates ordinal regression as continuous generative modeling using diffusion models with dual-decoupling to capture soft semantic transitions.
arXiv preprint arXiv:1912.07753 (2019)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
VALOR improves uplift modeling for B2B sales revenue by using a treatment-gated sparse network and cost-sensitive focal loss, achieving 20% better rankability on benchmarks and 2.7x incremental revenue in a production A/B test.
citing papers explorer
-
DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
DiffOR reformulates ordinal regression as continuous generative modeling using diffusion models with dual-decoupling to capture soft semantic transitions.
-
VALOR: Value-Aware Revenue Uplift Modeling with Treatment-Gated Representation for B2B Sales
VALOR improves uplift modeling for B2B sales revenue by using a treatment-gated sparse network and cost-sensitive focal loss, achieving 20% better rankability on benchmarks and 2.7x incremental revenue in a production A/B test.