AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Fidelity-Aware Recommendation Explanations via Stochastic Path Integration

Oren Barkan, Yahlly Schein, Yehonatan Elisha, Veronika Bogina, Mikhail Baklanov, Noam Koenigstein

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add stochastic baseline sampling to path integration (ablation)PI · ML1M, VAEPOS@5: 0.236 -> 0.189Improved
add stochastic baseline sampling to path integration (ablation)PI · ML1M, NCFPOS@5: 0.211 -> 0.185Improved
add stochastic baseline sampling to path integration (ablation)PI · ML1M, MFPOS@5: 0.418 -> 0.410Improved
add stochastic baseline sampling to path integration (ablation)PI · Yahoo! Music, VAECDCG: 0.380 -> 0.358Improved
add stochastic baseline sampling to path integration (ablation)PI · ML1M, MFINS: 0.939 -> 0.939No clear effect
add stochastic baseline sampling to path integration (ablation)PI · Yahoo! Music, MFDEL: 0.591 -> 0.591No clear effect
add stochastic baseline sampling to path integration (ablation)PI · ML1M, VAE, Ke=2INS@Ke: 1.987 -> 3.626Improved
replace learned explainer LXR with SPINRecLXR · ML1M, VAEPOS@5: 0.348 -> 0.189Improved
use SPINRec instead of FIAFIA · Yahoo! Music, VAEPOS@5: 0.315 -> 0.280Improved
increase number of sampled baselines kappa beyond 10 (ablation)SPINRec · ML1M, NCFINSNo clear effect
use SPINRec instead of PI at fixed length Ke=2 (MF, ML1M) (ablation)PI · ML1M, MF, Ke=2INS@Ke: 0.798 -> 0.799No clear effect
add stochastic sampling to PI at ML1M VAE (ablation)PI · ML1M, VAEINS: 0.029 -> 0.031Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy