PDQUBO is a new performance-driven QUBO method for feature selection in recommender systems that incorporates counterfactual performance impacts of features and pairs, is model-agnostic, and outperforms prior quantum and some classical baselines on CTR tasks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2verdicts
UNVERDICTED 2representative citing papers
An LLM judge uses semantic matching on user text to deliver reliable, explainable top-K recommendation scores instead of biased ID-based holdout metrics.
citing papers explorer
-
Performance-Driven QUBO for Recommender Systems on Quantum Annealers
PDQUBO is a new performance-driven QUBO method for feature selection in recommender systems that incorporates counterfactual performance impacts of features and pairs, is model-agnostic, and outperforms prior quantum and some classical baselines on CTR tasks.
-
LLM-as-a-Judge for Reliable and Explainable Offline Evaluation in Top-K Recommendation
An LLM judge uses semantic matching on user text to deliver reliable, explainable top-K recommendation scores instead of biased ID-based holdout metrics.