PR-entmax loss curbs popularity bias in sequential recommenders without architecture changes
_reachsumit · x · 2026-10-14
A paper introduces PR-entmax, a sparse prior-regularized objective that makes popularity correction context-dependent in sequential recommender systems.
- Derived from a generalized variational principle embedding item-popularity priors into a sparse probability mapping
- Non-zero gradients go only to items selected jointly by contextual relevance and popularity
- Plug-in via loss modification only; the prior term is dropped at inference
- Consistently reduces popularity bias while preserving or improving relevance across benchmarks and architectures
More from Research
- AIPOCH's Open-Science ships portable .science packages that share full research context, not just outputs — ahuja_priyank · 2026-10-14
- Video-Arena: Game-Based Video Benchmark Shows Native Models Score Just 13.2 F1 — Kuan Zhang · 2026-10-14
- LSCBench: Vibe Coding Agents Write Functional Code, But Only 25% Is Also Secure — Qwen · 2026-10-14
- Omni-LLMs Know More Than They Say: NAVER's OmniCatalyst Adds 7.29% via Self-Generated Text — naver-ai · 2026-10-14
- Repeated-Data Pretraining Study: Smaller Batches Act as Regularizers and Beat More GPUs — Sewon Min · 2026-10-14
- NAVER's WATCH: Cross-Video Human-Video Pretraining Lifts Robot Success Rate to 77.7% — naver-ai · 2026-10-14