AI Paper Atlas

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

Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems

Dor Arviv, Yehonatan Elisha, Oren Barkan, Noam Koenigstein

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 0 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 prediction-level loss (increase beta from 0) (ablation)SAE on MF and NCF (ML1M) · ML1M top-30 list fidelityRBO and Kendall TauImproved
increase prediction-loss weight beta to large values (ablation)SAE on MF and NCF (ML1M) · ML1Mmonosemanticity score and sparsityHurt
add Matryoshka nested dictionaries (ablation)SAE · ML1Minterpretability of neuronsNo clear effect
add Matryoshka nested dictionaries (ablation)SAE · Last.FMneuron hierarchy (qualitative)Improved
increase top-K from 10 to 50SAE concept neurons · ML1M and Last.FM puritysemantic purity: e.g. MF Country 1.00 -> 0.56Hurt
edit neuron activation in item latent vector (Bob Dylan)MF on Last.FM · Last.FM top-30 recommendationspromotion to non-fan usersImproved

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