Paper reduces recommender system model size by 90%.
problem Large model size in recommender systems.
method Hybrid frequency and double hashing for model size reduction.
result 90% reduction in model size with no performance loss.
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.
168,786 papers · 148 categories
Trend · papers per month
48 results for “size recommendation”
Bayesian model predicts fashion size recommendations and returns.
problem Predicting optimal fashion sizes and handling returns efficiently.
method Hierarchical Bayesian model for size and return events.
result Model incorporates domain expertise and article characteristics.
Paper introduces RTT2Vec for real-time grocery recommendations, achieving 9.4% uplift over baselines.
problem Personalized grocery recommendations to improve user experience and sales.
method RTT2Vec deep architecture for real-time recommendations, approximate inference technique.
result 9.4% uplift in prediction metrics over baseline models.
Deep learning predicts fit for fashion e-commerce.
problem Predicting correct fit for customer satisfaction and cost reduction.
method Deep learning content-collaborative approach using customer and article embeddings.
result Significant improvement over state-of-the-art methods.
Recommendation problems with large numbers of discrete items, such as products, webpages, or videos, are ubiquitous in the technology industry. Deep neural networks are being increasingly used for these recommendation problems. These models use embeddings to represent discrete items as continuous vectors, and the vocab…
This work reduces model size by 86.11% for recommender systems using 4-bit quantization.
problem Large memory consumption in embedding vectors for recommender systems.
method Post-training 4-bit quantization on embedding tables, including row-wise uniform quantization and codebook-based quantization.
result Consistently reduces accuracy degradation while significantly reducing model size.
In this work, we study recommendation systems modelled as contextual multi-armed bandit (MAB) problems. We propose a graph-based recommendation system that learns and exploits the geometry of the user space to create meaningful clusters in the user domain. This reduces the dimensionality of the recommendation problem w…
In this paper, we investigate the common scenario where every candidate item for recommendation is characterized by a maximum capacity, i.e., number of seats in a Point-of-Interest (POI) or size of an item's inventory. Despite the prevalence of the task of recommending items under capacity constraints in a variety of s…
Large-scale industrial recommender systems are usually confronted with computational problems due to the enormous corpus size. To retrieve and recommend the most relevant items to users under response time limits, resorting to an efficient index structure is an effective and practical solution. The previous work Tree-b…
Paper speeds up policy optimization for large recommendation systems.
problem Offline optimization of large-scale recommendation systems is computationally expensive.
method Derives an approximation of policy learning algorithms that scales logarithmically with the catalogue size.
result Our algorithm is an order of magnitude faster than naive approaches while producing equally good policies.
Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systemscs.LG
A new method reduces embedding size for efficient recommendation systems.
problem Memory bottleneck in embedding tables for diverse categorical features.
method Complementary partitions to produce unique embeddings without explicit definition.
result Our approach reduces embedding size and maintains similar accuracy.
Skip-gram with negative sampling, a popular variant of Word2vec originally designed and tuned to create word embeddings for Natural Language Processing, has been used to create item embeddings with successful applications in recommendation. While these fields do not share the same type of data, neither evaluate on the …
Automates investor/company matching with AI, explaining decisions.
problem Matching companies and investors is hard due to limited data and need for explanations.
method Representation learning for small datasets + parameterized explanation generation.
result System performs well on matching task and explains decisions.
Improved recommendation systems using multi-layer embeddings reduce model size while maintaining accuracy.
problem Improving model accuracy in recommendation systems while minimizing model size.
method Introducing a multi-layer embedding training (MLET) architecture that trains embeddings via a sequence of linear layers.
result Substantial advantages in model accuracy and memory footprint are achieved with reduced embedding dimensions.
Two methods estimate effect size for online experiments, improving accuracy and efficiency.
problem Determining the correct effect size for online experiment duration.
method Two approaches: hierarchical models and utility theory.
result Proposed methods outperform baseline approaches in accuracy and efficiency.
Automates size normalization for fashion items.
problem Reduce merchandise returns in e-commerce.
method Uses sales data to automate size mapping.
result Automated size mappings comparable to human-generated ones.
GraphSW reduces training cost for GNN-based recommender models by selectively accessing graph features.
problem Training GNN-based recommender models on full KG is computationally expensive and impractical.
method GraphSW uses stage-wise training to access a subset of entities in the KG, gradually learning from higher-order features.
result GraphSW improves recommendation performance and helps models converge effectively in high-order features.
Recommendation or Discrimination?: Quantifying Distribution Parity in Information Retrieval Systemsstat.ML
Test for fairness in IR systems based on protected variables.
problem Unfairness in IR systems due to correlation with protected variables.
method Statistical test for 'distribution parity' in top-K IR results.
result Ensures fairness in IR systems for all users.
Recommender systems have recently attracted many researchers in the deep learning community. The state-of-the-art deep neural network models used in recommender systems are typically multilayer perceptron and deep Autoencoder (DAE), among which DAE usually shows better performance due to its superior capability to reco…
PoDiRe learns long-term rewards in multi-task recommendations.
problem Long-term rewards in multiple recommendation tasks.
method Policy Distilled Reinforcement Learning (PoDiRe) combining deep reinforcement learning and knowledge distillation.
result PoDiRe outperforms state-of-the-art methods in real-world data.
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.
EMDE efficiently estimates manifold densities for diverse recommendation systems.
problem Efficiently estimating manifold densities for multi-modal recommendation systems.
method EMDE (Efficient Manifold Density Estimator) framework for arbitrary vector representations.
result Established new state-of-the-art results in top-k and session-based recommendation settings.
Production recommendation systems rely on embedding methods to represent various features. An impeding challenge in practice is that the large embedding matrix incurs substantial memory footprint in serving as the number of features grows over time. We propose a similarity-aware embedding matrix compression method call…
Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender Systemcs.LG
We propose a novel way to train ranking models, such as recommender systems, that are both effective and efficient. Knowledge distillation (KD) was shown to be successful in image recognition to achieve both effectiveness and efficiency. We propose a KD technique for learning to rank problems, called \emph{ranking dist…
Paper tackles exposure bias in recommender systems using contrastive learning.
problem Exposure bias in large-scale recommender systems.
method Contrastive learning to reduce exposure bias via inverse propensity weighting.
result Contrastive learning effectively reduces exposure bias in recommender systems.
Classical collaborative filtering, and content-based filtering methods try to learn a static recommendation model given training data. These approaches are far from ideal in highly dynamic recommendation domains such as news recommendation and computational advertisement, where the set of items and users is very fluid.…
In sponsored search, keyword recommendations help advertisers to achieve much better performance within limited budget. Many works have been done to mine numerous candidate keywords from search logs or landing pages. However, the strategy to select from given candidates remains to be improved. The existing relevance-ba…
New TVBO algorithm optimizes time-varying functions with varying sampling frequencies.
problem Optimizing time-varying, expensive, noisy functions with constant frequency assumption.
method Formulated practical recommendations and derived upper regret bound for varying sampling frequencies.
result BOLT algorithm outperforms state-of-the-art TVBO algorithms in experiments.
On the effectiveness of convolutional autoencoders on image-based personalized recommender systemscs.LG
Convolutional autoencoders improve personalized recommendations from image-based data.
problem Lack of personalized recommendations in gastronomic platforms using image data.
method Used convolutional autoencoders to extract features from images and improve personalized recommendations.
result Convolutional autoencoders outperform standard deep features in image-based personalized recommendation systems.
Presentation of a Recommender System with Ensemble Learning and Graph Embedding: A Case on MovieLenscs.IR
Enhanced recommender system using ensemble learning and graph embedding.
problem Challenges in selecting relevant data for users from large datasets.
method Group classification, ensemble learning, fuzzy rules, decision tree, graph embedding.
result High efficiency of the presented method on MovieLens datasets.
We consider a particular instance of a common problem in recommender systems: using a database of book reviews to inform user-targeted recommendations. In our dataset, books are categorized into genres and sub-genres. To exploit this nested taxonomy, we use a hierarchical model that enables information pooling across a…
The paper develops a method to evaluate recommendation systems without A/B testing.
problem Evaluating new recommendation algorithms efficiently and accurately.
method An estimator that predicts algorithm performance using historical data.
result The estimator converges to true performance at a rate of .
Many-to-one RNN predicts user hotel clicks from browsing history.
problem Predicting user hotel clicks from browsing history.
method Combines rule-based algorithm with Gated RNN to sort accommodations.
result Promising results but computationally demanding.
New recommendations improve Gaussian process accuracy and stability.
problem Numerical instabilities and poor test likelihoods in iterative Gaussian process learning.
method Investigated CG tolerance, preconditioner rank, and Lanczos decomposition rank. Recommended small CG tolerance and large root decomposition size.
result L-BFGS-B optimizer achieves convergence with fewer gradient updates, improving Gaussian process accuracy.
Proposes a max-utility arm selection strategy for reducing cumulative regret in sequential query recommendations.
problem Reduces cumulative regret in sequential query recommendations for closed loop interactive learning settings.
method Proposes a max-utility arm selection strategy based on the maximum utility of arms.
result Improves cumulative regret substantially compared to baseline algorithms and random selection.
MACRo-mIcro VAE learns disentangled user behavior representations.
problem Complex user behavior data in recommender systems are entangled; disentangling them enhances robustness and interpretability.
method MACRo-mIcro Disentangled Variational Auto-Encoder (MacridVAE) infers high-level user intentions and micro-disentangles preferences.
result Our approach achieves substantial improvement over state-of-the-art baselines and demonstrates interpretable and controllable learned representations.
This paper reviews methods for constructing confidence intervals for error rates in 1:1 matching tasks.
problem Challenges in assessing uncertainty of error rates in matching algorithms, especially when data are dependent and error rates are low.
method Derives and examines statistical properties of methods for constructing confidence intervals for error rates in 1:1 matching tasks.
result Coverage and interval width vary with sample size, error rates, and data dependence.
RGCF improves collaborative filtering by refining graph convolution embeddings.
problem GCN-based recommendation models introduce noise and redundancy, limiting high-order connectivity capture.
method Developed RGCF, a new GCN-based Collaborative Filtering model with redesigned embeddings.
result RGCF significantly outperforms state-of-the-art models on public datasets.
Recommendation is the task of improving customer experience through personalized recommendation based on users' past feedback. In this paper, we investigate the most common scenario: the user-item (U-I) matrix of implicit feedback. Even though many recommendation approaches are designed based on implicit feedback, they…
Estimates sample size for subgroup analysis in randomized experiments.
problem Determining sample size for accurate subgroup analysis.
method Turns inference problem into simultaneous inference, calculates sample size based on confidence level and margin of error.
result Allows inversion of sample size to feasible number of treatment arms or partition complexity.
Efficiently classifies binary labels with XOR queries, even under noisy conditions.
problem Binary classification with unknown labels using XOR queries.
method Effective query type and an efficient inference algorithm for noisy conditions.
result Achieves information-theoretic limit on optimal number of queries.
FAB-COST improves cold-start recommendation accuracy with less data.
problem Cold-start problem in recommendation systems.
method Contextual bandit algorithm using Expectation Propagation and Assumed Density Filtering.
result FAB-COST outperforms Laplace approximation on real data.
DaConA improves recommendation accuracy with auxiliary data by adapting to different data contexts.
problem Improving recommendation accuracy with auxiliary data considering different data contexts.
method Data context adaptation layer, latent interaction vector, latent independence vector, non-linear function.
result DaConA achieves state-of-the-art accuracy on real-world datasets.
Deviation-based learning improves recommender systems by abstaining from recommending choices users might follow.
problem Recommender systems learn from user choices but can stall if users blindly follow recommendations.
method The recommender learns user knowledge by observing choices, abstaining from recommending a choice when multiple alternatives produce similar payoffs.
result Learning rate and social welfare improve when the recommender abstains from recommending certain choices.
CAFL breaks feedback loops in recommender systems using causal inference.
problem Feedback loops in recommender systems compromise recommendation quality and homogenize user behavior.
method Causal Adjustment for Feedback Loops (CAFL) algorithm that breaks feedback loops using causal inference.
result CAFL improves recommendation quality compared to prior correction methods.
The paper is devoted to modeling optimal exercise strategies of the behavior of investors and issuers working with convertible bonds. This implies solution of the problems of stock price modeling, payoff computation and min-max optimization. Stock prices (underlying asset) were modeled under the assumption of the geome…
Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systemscs.LG
Knowledge graphs capture structured information and relations between a set of entities or items. As such knowledge graphs represent an attractive source of information that could help improve recommender systems. However, existing approaches in this domain rely on manual feature engineering and do not allow for an end…
We study the transfer of adversarial robustness of deep neural networks between different perturbation types. While most work on adversarial examples has focused on and -bounded perturbations, these do not capture all types of perturbations available to an adversary. The present work evaluates 32 attack…