Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

70139209278 · Jun 202019922001200920182026
48 results for item ratings

The paper explores using set-level ratings for better user-item preference prediction in recommender systems.

problem Capturing user preferences on individual items using set-level ratings.
method Developed collaborative filtering-based methods to model user behaviors in set-level ratings.
result Collaborative filtering-based models can recover and predict user preferences on individual items using set-level ratings.

A new multi-task framework for recommender systems improves ranking and rating predictions.

problem Improving ranking and rating predictions in recommender systems.
method Exploits a two-phase decision process: first deciding to interact with an item (ranking task) and then rating it (rating prediction task).
result Superior performance compared to state-of-the-art methods on two benchmark datasets.

Eigenvalue analogy explains item-based recommender system accuracy.

problem Lack of theoretical explanation for item-based recommender system success.
method Formalized as an eigenvalue problem, estimating ratings as true ratings multiplied by user-specific eigenvalues.
result Eigenvalue magnitude correlates with user's recommendation accuracy and can measure confidence.

Collaborative filtering is used to recommend items to a user without requiring a knowledge of the item itself and tends to outperform other techniques. However, collaborative filtering suffers from the cold-start problem, which occurs when an item has not yet been rated or a user has not rated any items. Incorporating …

2014-06-09abs ↗pdf ↗

Paper proposes a combined model for better recommendation by integrating explicit and implicit feedbacks.

problem Improve recommendation accuracy by considering both explicit and implicit feedbacks.
method Developed three models (RHC-PMF, RV-PMF, RHCV-PMF) that incorporate users' explicit and implicit feedbacks for better rating prediction.
result RHCV-PMF model outperforms other models in cold start scenarios for both users and items.

A new method for multi-criteria recommender systems using graph attention networks.

problem Lack of nuanced relationships between users and items based on specific criteria.
method MDGAT, a multi-edge bipartite graph with dual attention networks and contrastive learning.
result MDGAT achieves higher accuracy in predicting item ratings compared to baseline methods.

New model corrects bias in crowdsourced ratings for diverse items.

problem Bias and noise in crowdsourced ratings for training data.
method Bayesian rating model with item-level effects for difficulty, discriminativeness, and guessability.
result New model avoids bias in training data, improving model goodness of fit.

Proposes a multilayer nonlinear semi-nonnegative matrix factorization for better recommendation.

problem Inaccurate user-item interaction modeling with classical matrix factorization.
method Multilayer nonlinear Semi-NMF approach for latent user and item representations.
result Proposed method achieves better generalization in prediction and comparable representation in clustering.

Debias recommender systems by accounting for hidden confounders using network information.

problem Debiased recommender systems to reduce bias caused by hidden confounders.
method Leverage network information to disentangle user conformity and item popularity, modeling exposure and ratings while controlling hidden confounders.
result The proposed method effectively debiases recommender systems, improving recommendation accuracy.

Recommending items to users is a challenging task due to the large amount of missing information. In many cases, the data solely consist of ratings or tags voluntarily contributed by each user on a very limited subset of the available items, so that most of the data of potential interest is actually missing. Current ap…

2015-09-30abs ↗pdf ↗

Advanced and effective collaborative filtering methods based on explicit feedback assume that unknown ratings do not follow the same model as the observed ones (\emph{not missing at random}). In this work, we build on this assumption, and introduce a novel dynamic matrix factorization framework that allows to set an ex…

2015-07-23abs ↗pdf ↗

Improved item recommendation using VAEs with user-dependent priors and text feedback.

problem Improving recommendation quality by integrating user ratings and text feedback.
method Extended VAEs to incorporate user-dependent priors in a multimodal latent space.
result Model outperforms existing VAE models for collaborative filtering (up to 29.41% relative improvement).

The paper proposes a new recommender system combining ratings and textual reviews.

problem Lack of using textual reviews in recommender systems.
method Combines Latent Factor Model with Latent Dirichlet Allocation for textual reviews.
result Combining textual reviews with ratings improves recommendation quality.

Proposes a method to infer ranking properties and top-K rankings with uncertainty quantification.

problem General uncertainty quantification in ranking problems.
method Combinatorial inference framework for the Bradley-Terry-Luce model, generalized to multiple testing.
result Minimax optimal method for inferring top-K rankings with FDR control.

The paper ranks items based on top choices in multiway comparisons.

problem Ranking items based on top choices in multiway comparisons.
method Uniform sampling scheme, statistical rates of convergence, asymptotic normality, maximum likelihood estimator, Gaussian multiplier bootstrap.
result Proposed inference framework for ranking items through maximum pairwise difference statistic.

Bandit problem on graphs aims to recommend items with high expected ratings.

problem Online learning problems involving graphs, such as content-based recommendation.
method Study of a bandit problem on graphs, introducing effective dimension and proposing algorithms.
result Proposed algorithms scale linearly and sublinearly in the effective dimension, improving cumulative regret.

Active learning improves ordering of items with contextual attributes.

problem Learning accurate item orderings from pairwise comparisons, especially when exhaustive comparisons are impractical.
method Proposes an active learning strategy that samples items to minimize expected ordering error, accounting for uncertainty in comparisons.
result Superior sample efficiency and generalization compared to non-contextual ranking approaches and active preference learning baselines.

Proposes a multi-perspective neural model for better user preference analysis in recommendation systems.

problem Complex user preferences not well captured by existing recommendation models.
method Uses multiple perspectives to encode user and item features, then combines these representations to predict ratings.
result Significant improvements over baseline models in predicting user ratings.

Normalized nonnegative models assign probability distributions to users and random variables to items; see [Stark, 2015]. Rating an item is regarded as sampling the random variable assigned to the item with respect to the distribution assigned to the user who rates the item. Models of that kind are highly expressive. F…

2015-11-20abs ↗pdf ↗

This paper models continuous user experience evolution for better item recommendations.

problem Dynamic user experience in online review communities.
method Combines Geometric Brownian Motion, Brownian Motion, and Latent Dirichlet Allocation to model continuous user experience and language evolution.
result The model outperforms discrete models and state-of-the-art methods in predicting item ratings.

The paper tackles a bandit problem on graphs with smooth functions, aiming to recommend items with high expected ratings.

problem Online learning problems involving graphs, such as content-based recommendation.
method Introduced the notion of effective dimension and proposed two algorithms for solving the problem.
result The algorithms can learn good estimators of user preferences from just tens of nodes evaluations.

A new algorithm improves top-kk recommendation accuracy by considering item payoffs uncertainty.

problem Suboptimal performance in top-kk recommendation rankings due to varying item payoffs.
method Proposes a risk-seeking utility function for ranking items based on estimated preference scores.
result Risk-seeking ranking yields the best performance in top-kk recommendations.

User preferences for items can be inferred from either explicit feedback, such as item ratings, or implicit feedback, such as rental histories. Research in collaborative filtering has concentrated on explicit feedback, resulting in the development of accurate and scalable models. However, since explicit feedback is oft…

2011-09-27abs ↗pdf ↗

The paper models and predicts co-occurrence counts using Gamma regression.

problem Predicting relevance between items or users from high-dimensional sparse co-occurrence count data.
method Shared parameter alternating zero-inflated Gamma regression models (SA-ZIG) with Fisher scoring and learning rate adjustment.
result SA-ZIG with learning rate adjustment performs satisfactorily in predicting relevance.

New algorithm for online collaborative filtering using linear bandits and alternating least squares.

problem Online collaborative filtering with item recommendations over time.
method Combines linear bandits and alternating least squares for matrix factorization.
result Superior performance in cumulative regret and average cumulative NDCG over state-of-the-art algorithms.

Model analyzes cooccurrence data for recommender systems and item relevance.

problem High-dimensional cooccurrence data from online platforms.
method Shared parameter Alternating Tweedie (SA-Tweedie) model with Fisher scoring and learning rate adjustment.
result SA-Tweedie model outperforms other methods in optimizing parameters.

We address the cold start problem in recommendation systems assuming no contextual information is available neither about users, nor items. We consider the case in which we only have access to a set of ratings of items by users. Most of the existing works consider a batch setting, and use cross-validation to tune param…

2014-07-10abs ↗pdf ↗

We develop a Bayesian Poisson matrix factorization model for forming recommendations from sparse user behavior data. These data are large user/item matrices where each user has provided feedback on only a small subset of items, either explicitly (e.g., through star ratings) or implicitly (e.g., through views or purchas…

2013-11-07abs ↗pdf ↗

Data poisoning attacks can manipulate recommender systems to recommend target items.

problem Attacks on recommender systems to influence top-N item recommendations.
method Formulated as an optimization problem, solved using influence function to select influential users.
result Effective data poisoning attacks that outperform existing methods.

Paper anonymizes user ratings to protect privacy while improving recommendation accuracy.

problem Protecting user privacy while maintaining recommendation accuracy with anonymized ratings.
method Exhaustively lists recommender models using anonymized ratings and presents item-based collaborative filtering algorithms.
result Item-based collaborative filtering based on anonymized ratings outperforms non-anonymized ratings in some settings.

Proposes a method to improve recommendation systems by considering negative feedback.

problem Insensitivity to negative feedback in top-N recommendation tasks.
method Model user feedback as a ternary variable and use third-order tensor factorization.
result Achieves state-of-the-art quality and significantly outperforms other methods in cold-start scenarios.

Unified model for evolving user and item preferences with social influence.

problem Understanding and inferring evolving user preferences and item ratings.
method Dynamic matrix factorization with social influence, combining opinion dynamics and trust-based recommendation.
result Consistent reduction in root mean squared error by considering both user and item dynamics.