Bayesian method combines expert and user rankings using copulas.
problem Combining expert and user rankings for accurate predictions.
method Bayesian inference with copula modeling latent variables.
result Predictive distribution of user rankings can be approximated accurately.
AIPS improves ranking policy evaluation by adapting to diverse user behavior.
problem Inaccurate Off-Policy Evaluation of ranking policies due to high variance under diverse user behavior.
method Developed Adaptive IPS (AIPS) that adapts to different user behaviors and minimizes MSE.
result AIPS achieves minimum variance among unbiased estimators and provides significant empirical accuracy improvement.
New algorithm improves ad targeting for personalized online services.
problem Personalizing online services for improved user experience and revenue.
method Label ranking approach for non-linear, large-scale prediction of user interests.
result The proposed algorithm outperforms existing solutions in rank loss and top-K retrieval.
Paper proposes a two-stage ranking for personalized TV recommendations.
problem Improving TV recommendation accuracy and efficiency.
method First, identifies potential candidates using user viewing patterns. Then, ranks them based on user preferences and program textual information.
result The proposed model outperforms in recommendation accuracy and efficiency.
Study tackles ranking fraud in online platforms by learning robust rankings.
problem Fraudulent fake users manipulate product rankings.
method Developed algorithms for robust ranking in two informational environments.
result Our algorithms converge to optimal rankings, robust to fake users.
Paper tackles real-world e-commerce search efficiency and user experience.
problem Efficiently rank large-scale e-commerce search results with multiple factors.
method Design and deploy a novel Cascade ranking model in a large-scale operational e-commerce search application.
result Demonstrates the advantage of the proposed model in addressing multiple factors of effectiveness, efficiency, and user experience.
Proposes HTM for aggregating ranked data considering user accuracy.
problem Aggregating ranked data from heterogeneous users with varying accuracy levels.
method Heterogeneous Thurstone Model (HTM) with alternating gradient descent algorithm.
result Algorithm converges linearly and outperforms existing methods.
New method for online low-rank matrix completion with improved regret.
problem Designing an efficient algorithm for online recommendation systems with low regret.
method Explore-then-commit (ETC) approach and iterative user clustering (OCTAL) for rank-1 setting.
result Nearly optimal regret bounds for online low-rank matrix completion.
Proposes a method for ranking items across multiple aspects based on user feedback.
problem No principled solution exists for generating multiple item rankings over different aspects.
method Developed a directional multi-aspect ranking criterion using probabilistic multivariate tensor factorization.
result Demonstrated effectiveness of the proposed method through comprehensive experiments on real datasets.
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.
A new method models user-specific parameters as a low-rank plus sparse component for efficient personalization.
problem Efficient personalization of machine learning models for individual users.
method Meta-learning approach that models network weights as a sum of low-rank and sparse components.
result The proposed method, AMHT-LRS, achieves nearly optimal sample complexity for estimating the low-rank and sparse components.
A method for cold-start playlist recommendation using multitask learning.
problem Playlist recommendation for new users and songs.
method Flexible multitask learning method that minimizes a bipartite ranking loss and a classification loss.
result The method performs well in cold-start scenarios on real datasets.
Framework for optimizing search engine rankings using observational data.
problem Optimizing ranking policies for search engines using limited observational data.
method Formulated expected reward optimization problem, estimated context value distribution, trained ranking policy via Bayesian inference.
result Demonstrated trade-offs in ranking policies trained on empirical reward estimates.
Choppy optimizes ranked list truncation using Transformer architecture.
problem Optimal truncation of ranked search results to balance relevance and user cost.
method Assumption-free Transformer model optimizing user-defined IR metrics.
result Choppy improves upon recent state-of-the-art methods.
The paper improves recommendation systems by ensuring their outputs are reliable.
problem Recommendation systems often lack reliability guarantees for their outputs.
method The method uses a pre-trained ranking model to create a set of items with rigorous FDR control.
result The approach provides a way to guarantee the reliability of recommendation outputs.
Nonparametric method predicts user rankings from incomplete ratings.
problem Predict user rankings from incomplete item-user rating data.
method Nonparametric model with nearest neighbors-like algorithm.
result Algorithm is consistent and performs well on real datasets.
Proposes a new query autocompletion method that maximizes retrieval performance.
problem Users often select suboptimal queries due to unknown best retrieval performance.
method Formulates query autocompletion as ranking item rankings, uses counterfactual learning.
result Empirical results show improved query suggestions for better retrieval performance.
Paper tackles online ranking and diversification in recommender systems.
problem Maximizing relevance and diversity in ranked lists for online recommendation.
method CascadeHybrid approach that combines contextual bandits for relevance and topical diversity.
result CascadeHybrid outperforms baselines in real-world datasets.
New estimator GMIPS reduces variance in ranking policy evaluation.
problem High variance in off-policy evaluation for ranking policies.
method GMIPS estimator with user behavior model on ranking embedding spaces.
result GMIPS achieves lowest MSE and balances bias-variance trade-off.
A new algorithm improves top-k recommendation accuracy by considering item payoffs uncertainty.
problem Suboptimal performance in top-k 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-k recommendations. Proposes a new ranking framework for implicit feedback recommendation systems.
problem Learning user preferences over items from implicit feedback data.
method Minimizes a pairwise ranking loss to learn user preferences and item representations.
result Consistent empirical risk minimization proved for worst-case user behavior.
New ranking system balances fairness and user utility.
problem Achieving group fairness in ranking systems.
method Formulated a minimax game between a ranking player and an adversary.
result Better utility for highly fair rankings.
FPL allows users to control their data in federated top-N recommendation.
problem Data privacy in recommendation services.
method Federated Learning with learning to rank optimization.
result Users can control the amount of sensitive data shared with a central server.
SQL-Rank improves recommendation systems by modeling user rankings as permutations.
problem Improving recommendation systems by better modeling user rankings.
method SQL-Rank uses a listwise approach based on a permutation model to construct user-specific rankings.
result SQL-Rank outperforms current state-of-the-art algorithms for implicit feedback and explicit feedback.
We study the problem of collaborative filtering where ranking information is available. Focusing on the core of the collaborative ranking process, the user and their community, we propose new models for representation of the underlying permutations and prediction of ranks. The first approach is based on the assumption …
Algorithm learns diverse rankings for search engines.
problem Designing algorithms for search engines to rank diverse items.
method LDR (Learning Diverse Rankings) algorithm, efficient learning based on users' feedback.
result Algorithm achieves optimal ranking performance with O((N−L)log(T)) regret. In recent years rank aggregation has received significant attention from the machine learning community. The goal of such a problem is to combine the (partially revealed) preferences over objects of a large population into a single, relatively consistent ordering of those objects. However, in many cases, we might not w…
Proposes a deep learning model for timely and accurate recommendations.
problem Inability to provide timely recommendations and ranking issues with implicit feedback.
method Unified cross-network solution using listwise ranking for implicit data.
result Superior performance in accuracy, novelty, and diversity compared to baselines.
PGRec improves recommendation by modeling user-item preferences as a graph and embedding it for better predictions.
problem Sparse user-item data in recommender systems.
method PGRec models user-item preferences as a PrefGraph, then uses deep learning and factorization to embed and predict user preferences.
result PGRec outperforms state-of-the-art methods by up to 3.2% in NDCG@10.
TopRank algorithm improves online ranking with better performance and insights.
problem Sequential decision-making in online learning to rank with user feedback.
method Generalized click model and topological sort-based algorithm.
result TopRank outperforms existing algorithms in terms of performance and proof insight.
A new learning-to-rank approach ensures fairness for item providers in dynamic ranking systems.
problem Myopically optimizing user utility can be unfair to item providers in two-sided markets.
method A controller that integrates unbiased estimators for fairness and utility, dynamically adapting as more data becomes available.
result Empirically, the algorithm is highly practical and robust, ensuring amortized group fairness.
Designs ranking models to consider long-term consequences, improving online discourse.
problem Ranking models fail to foresee long-term negative impacts.
method Introduces Markov decision processes and weighted sampling for optimal consequential rankings; develops gradient-based algorithm for practical implementation.
result Optimal consequential rankings can be approximated efficiently using parameterized models.
Personalized Transformer improves temporal collaborative ranking performance.
problem Temporal collaborative ranking in recommendation systems.
method Personalized Transformer model using attention mechanisms.
result Personalized Transformer outperforms SASRec by almost 5% in NDCG@10.
Intelligent recommender system tracks user activity and intent for better recommendations.
problem Recommender systems often lack user intent awareness, leading to suboptimal recommendations.
method Encoded user activity, reduced to lower dimensions using tensor factorization, and scored for intent. Combined with contextual information for ranking recommendations.
result Better recommendations compared to baselines, with intent-aware scoring.
Algorithm learns diverse recommendations from partial clicks.
problem Learning diverse recommendations from partial user feedback.
method Online learning algorithm for cascade model.
result Gap-free upper bound on n-step regret proved.
Paper reviews ranking systems in multi-layered architectures.
problem Ranking systems for effective machine learning models and real-time user responses.
method Examines data processing, representation learning, candidate selection, and online inference layers.
result Ranking systems are complex systems of multiple architectures.
Efficiently evaluates new ranking policies using click models.
problem Evaluate new ranking policies offline and optimize them before deployment.
method Proposes evaluation algorithms using click models to estimate expected clicks from logged data.
result Our estimators are more statistically efficient than those that do not use click models.
The paper introduces algorithms for efficient low-rank matrix approximation.
problem Efficiently approximating large matrices while preserving their properties.
method Random linear images (sketches) of the matrix, with error bounds for quality control.
result Simple, accurate, numerically stable methods for low-rank approximation.
FAIRY explains user actions and social media feeds.
problem Users struggle to understand why certain items appear in their social feeds.
method FAIRY uses an interaction graph to model user behavior and ranks feed items, scoring paths connecting user actions and feed items.
result FAIRY provides clear explanations for user actions and feed items, enhancing transparency and user understanding.
New methods improve recommendation accuracy for users and items with few ratings.
problem Skewed distribution and low ratings affect recommendation accuracy.
method Four matrix completion-based approaches: FARP, TMF, TMF + Dropout, IFWMF.
result Improved prediction accuracy for users and items with few ratings.
This paper protects rankings from differential privacy breaches.
problem Leakage of personal information in rankings.
method Develops ε-ranking differential privacy and a multistage ranking algorithm.
result Establishes the connection between Mallows model and ε-ranking differential privacy.
New model improves website ranking by considering user choices as a whole.
problem Optimizing content ordering for user clicks in website design.
method Introduced multinomial logit (MNL) choice model to LTR framework, proposing UCB algorithms.
result Proved theoretical bounds on regret for UCB algorithms in both known and unknown position parameter settings.
Proposes a new IPW-based ranking metric for two-sided markets.
problem Addressing bias in implicit user feedback in two-sided markets.
method Extends IPW estimator to two-sided markets, addressing position bias.
result Proposed estimator is unbiased for ground-truth ranking metric.
This paper studies the problem of inferring a global preference based on the partial rankings provided by many users over different subsets of items according to the Plackett-Luce model. A question of particular interest is how to optimally assign items to users for ranking and how many item assignments are needed to a…
iSplit LBI predicts individualized partial rankings from ties, outperforming state-of-the-art methods.
problem Predicting partial rankings from pairwise comparisons with ties, considering individual preferences.
method Variable splitting-based algorithm (iSplit LBI) that generates a sequence of estimations with a regularization path, decomposing parameters into abnormal signals, personalized signals, and random noise.
result iSplit LBI significantly outperforms state-of-the-art alternatives in predicting individualized partial rankings.
BubbleRank improves online search results using safe exploration.
problem Learning user preferences from scratch in online ranking is costly and risky.
method BubbleRank combines offline and online learning, starting with an initial base list and improving it online by exchanging items.
result BubbleRank achieves a graceful degradation of n-step regret with a good initial base list.
New method to rank metrics on non-shuffled traffic.
problem Position bias in ranking metrics due to item display order.
method Leverage stochasticity of recommendation policy to mitigate position bias.
result Improved ranking metrics without shuffling recommendations.
Paper introduces individual fairness for machine learning tasks.
problem Fairness in algorithmic decision making for machine learning tasks.
method Probabilistic mapping of user records into a low-rank representation that reconciles individual fairness and classifier utility.
result Substantial improvements over prior work for individual fairness in machine learning tasks.