A graph neural network detects beneficial feature interactions for recommender systems.
problem Feature interactions are crucial but not all are beneficial for recommendation accuracy.
method Graph neural network with L0 activation regularization for edge prediction.
result The model outperforms baselines and automatically identifies beneficial feature interactions.
New feature mapping approach improves recommendation accuracy and explainability.
problem Balancing recommendation accuracy and explainability using metadata.
method Maps uninterpretable features to interpretable aspect features, minimizing both prediction and interpretation losses.
result Strong performance in recommendation and explainability, eliminating metadata need.
DFM binarizes feature embeddings for fast, accurate recommendation.
problem Expensive storage and computational cost due to large feature dimensions.
method DFM binarizes real-valued model parameters into binary codes for efficient storage and computation.
result DFM outperforms state-of-the-art binarized recommendation models and shows competitive performance compared to its real-valued version.
Automated feature recommendation for signal analytics with interpretability.
problem Signal data analytics problems requiring feature interpretation.
method Wide Learning architecture for feature recommendation with interpretability.
result Effective feature recommendation and interpretation techniques for signal analytics.
BoostJet combines statistical aggregates and neural embeddings for better recommendations.
problem Combining diverse user and offer features for improved recommendation quality.
method Integrates statistical aggregates and neural embeddings using MatrixNet.
result Significantly improved recommendation quality on Yandex's dataset.
Interprets feature interactions in ad-click prediction models.
problem Improving interpretability of black-box recommender systems.
method Interprets feature interactions from a source model and encodes them in a target model.
result Interpretations significantly outperform existing recommender models.
DeepUnHide uses deep learning to reveal hidden demographic features in recommender systems.
problem Extracting hidden demographic features from recommender systems factors.
method Gradient-based localization in deep learning for feature extraction.
result DeepUnHide outperforms state-of-the-art feature selection methods.
Aesthetic-based clothing recommendation improves user satisfaction.
problem Lack of aesthetic features in existing clothing recommendation methods.
method Introduce aesthetic features extracted by a neural network and incorporate them into a personalized tensor factorization model.
result Our approach significantly outperforms state-of-the-art recommendation methods.
FBSM improves item recommendation for cold-start users by modeling feature interactions.
problem Cold-start item recommendation for new users.
method Factorized bilinear similarity model learning interactions among item features.
result Improves TOP-n recommendation performance compared to traditional methods.
Confounding biases recommender systems, even when data seems fully observed.
problem Unmeasured features influencing both treatment and outcome in recommender systems.
method Illustrations and simulation studies showing how common practices introduce confounding.
result Standard recommender system practices can introduce confounding, reducing performance.
MKR uses knowledge graphs to enhance recommendation, improving performance across various categories.
problem Collaborative filtering's sparsity and cold start issues in real-world recommendation scenarios.
method MKR is a deep end-to-end framework that leverages knowledge graph embedding for recommendation, associating two tasks through cross&compress units.
result MKR achieves substantial gains in movie, book, music, and news recommendation, outperforming state-of-the-art baselines.
Proposes HBGNN for better recommendation systems using graph neural networks.
problem Sparse structured data in recommendation systems lacking feature richness.
method Hierarchical BiGraph Neural Network (HBGNN) using bigraph framework.
result Competitive performance compared to current methods.
Proposes a new graph-based model for cold-start recommendations.
problem Cold-start problem in Recommender Systems, especially for items with no interaction history.
method Graph-based feature weighting model using probabilities from item-based collaborative filtering.
result Shows improved recommendation quality compared to existing methods.
SAIN integrates user-item feedback with content attributes for better recommendation.
problem Cold start problems in recommendation models due to sparse user-item interactions.
method SAIN uses a self-attention mechanism to capture feature interactions and an information integration layer to combine feedback and content information.
result SAIN outperforms state-of-the-art models by 2.13% on public datasets.
Wide & Deep combines linear and deep learning for better app recommendations.
problem Sparse user-item interactions lead to less relevant recommendations.
method Jointly trains wide linear models and deep neural networks.
result Wide & Deep significantly increases app acquisitions compared to wide-only and deep-only models.
Saec compresses recommendation system embeddings by clustering similar features.
problem Large embedding matrix in recommendation systems consumes excessive memory.
method Saec clusters similar features within a field to reduce embedding matrix size.
result Saec reduces embedding size by ~27x with no performance loss.
Paper introduces a new job recommendation method using candidate job selection progression.
problem Traditional job recommendation methods are either filter-based or feature-based, limiting serendipitous and cold-start recommendations.
method Uses machine learning to analyze candidate job selection progression and derive latent competencies.
result Achieved best click-through rate in a real-world job recommender system.
This study compares feature extraction methods using Neural Networks and Latent Dirichlet Allocation for movie synopses.
problem Extracting meaningful features from movie synopses for pattern detection and recommendation.
method Employed Latent Dirichlet Allocation for topic modeling and Neural Networks for distributed paragraph representations.
result Latent Dirichlet Allocation can provide meaningful features for movie synopses, comparable to Neural Networks.
New private learning algorithms improve utility in tasks with public features.
problem Private learning with public features in recommendation and ad prediction.
method Developed algorithms that protect only certain sufficient statistics, improving utility for linear regression and private recommendation benchmarks.
result Achieved state-of-the-art performance on private recommendation benchmarks.
The paper explains deep learning models for recommendations using layer-wise relevance propagation.
problem Explainable recommendations in deep learning models.
method Layer-wise relevance propagation applied to a Deep Convolutional Neural Network.
result Demonstrates the effectiveness of the method on an Amazon products dataset.
Proposes a deep hybrid model for better recommendation systems.
problem Limited studies on hybrid recommender systems and the need for more advanced approaches.
method Integrates deep learning with ID embeddings and auxiliary features for improved recommendation.
result Improves recommendation results over deep learning models using ID embeddings.
NIS learns optimal embedding sizes for recommendation models.
problem Finding optimal embedding sizes for large-scale recommendation models.
method Neural Input Search (NIS) uses reinforcement learning to automatically find optimal vocabulary sizes and embedding dimensions.
result NIS improves prediction accuracy by 6.8% on Recall@1 and 1.8% on ROC-AUC.
GEM improves recommendation by capturing complex feature interactions.
problem Capturing complex high-order interaction signals in feature-based recommendation models.
method Integrates graph convolution networks to generate high-order embeddings and combines with FM-based models.
result Significant improvement in recommendation performance over baselines.
DES training speeds up large-scale recommender systems convergence.
problem Training large-scale recommender systems with dynamic sparse features.
method Distributed Equivalent Substitution (DES) framework for fully synchronous training.
result DES achieves higher AUC and up to 68.7% communication savings.
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.
A new method for decision tree selection in recommendation systems.
problem Feature-based selection of a single tree from an ensemble for dynamic interpretation.
method A multi-armed contextual bandit recommendation framework that trains a system on top of Random Forests to identify the most relevant tree.
result The dynamic method outperforms an independent CART tree and is comparable to Random Forest in predictive performance.
CSA improves recommender systems by learning context-aware feature representations.
problem Limited expressiveness of traditional IMC methods for feature representations.
method Generalizes self-attention mechanism to IMC, learning context-aware feature representations.
result Extensive experiments show CSA's effectiveness on real RS datasets.
A new method selects the best feature selection technique for datasets.
problem Selecting the best feature selection method for unseen datasets.
method Data synthesis, meta features, fuzzy similarity, classification model training.
result Successfully recommended the best feature selection method for five out of eight datasets.
A framework combines multiple types of data for better item recommendations.
problem Limited performance of top-N recommendation systems using only one or two types of information.
method Design and implement GraFC2T2, a graph-based framework that encodes and combines content, temporal, and trust information.
result Combining different types of information improves recommendation performance.
Two novel methods identify influential features in CMABs for better reward distribution.
problem Suboptimal features degrade rewards, interpretability, and efficiency in CMABs.
method Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD) methods.
result Consistent ability to identify influential HTE features, enhancing CMAB performance.
Proposes SSL framework for improving item recommendations in large-scale systems.
problem Sparse feedback data for long-tail items in recommender systems.
method Multi-task self-supervised learning framework with data augmentation.
result Significant improvements in model performance, especially on slices lacking supervision.
A new model improves click-through rate prediction for recommendation systems.
problem Improving accuracy of click-through rate prediction in recommendation systems.
method Combines traditional feature engineering with deep neural networks to automate feature combinations.
result The model (FNFM) outperforms current deep learning feature combination models.
DeepSurv uses deep learning to personalize treatment recommendations based on patient features.
problem Lack of effective personalized treatment recommender systems for medical practitioners.
method Cox proportional hazards deep neural network.
result DeepSurv outperforms other survival models in personalized treatment recommendations.
PriRec preserves privacy in POI recommendation by keeping data and models on users' devices.
problem Privacy concerns in centralized POI recommendation models.
method Local differential privacy for sensitive data, secure decentralized gradient descent for linear models, secure aggregation for feature interactions.
result PriRec achieves comparable or better recommendation accuracy than FM while protecting user privacy.
Deep neural networks improve recommendation accuracy in marketplaces.
problem Measuring and optimizing recommender performance in marketplaces.
method Hybrid item representation models, sequence-based models, and multi-armed bandit models.
result Promising deep neural network recommenders are currently in production at FINN.no.
ONN learns different representations for different operations to improve user response prediction.
problem Improving user response prediction in online advertising and recommendation systems.
method Proposes Operation-aware Neural Networks (ONN) to learn different representations for different operations.
result ONN consistently outperforms state-of-the-art models in both offline and online environments.
Memory-Augmented Meta-Optimization improves cold-start recommendation.
problem Cold-start problem in recommender systems for new users or items.
method Memory-Augmented Meta-Optimization approach with personalized and task-specific memories.
result Significant improvement in cold-start recommendation performance on multiple datasets.
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.
A deep learning architecture for news session-based recommendations.
problem Challenges in news recommendation systems, including sparse user profiling and dynamic user preferences.
method Hybrid approach combining text and metadata features, session-based recommendations with Recurrent Neural Networks, and temporal offline evaluation.
result Significant improvement in top-n accuracy and ranking metrics (10% Hit Rate and 13% MRR) over best benchmark methods.
The system recommends hotels based on user preferences.
problem Overwhelm of hotel choices during trip planning.
method Used Expedia's hotel dataset to predict user preferences.
result Predicted and recommended hotels with high accuracy.
EB-SeqGANs use energy-based models for better recommendation.
problem Creating accurate and efficient mappings for new item recommendations.
method EB-SeqGANs learn a generative model for user-preferred item sequences, interpreting the energy function as a feature function.
result EB-SeqGANs can be seen as a form of maximum-entropy imitation learning.
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.
Study predicts email triage actions using content-based approach.
problem Predicting user triage actions on incoming emails.
method Formulated as a recommendation problem, uses content-based approach with additional similarity features.
result Proposed framework achieves better performance than state-of-the-art deep recommendation methods.
Proposes a graph-based system for personalized news recommendation considering multiple user behaviors.
problem Lack of considering multiple user behaviors in news recommendation systems.
method Builds an interaction behavior graph, applies DeepWalk and G-CNN for news and behavior sequence representations, introduces core and coritivity features.
result Achieves personalized news recommendation considering user's concentration degree of interests.
Transforms data for interpretable recommender systems.
problem Building an interpretable recommender system for personalized content and promotions.
method Loss-preserving transformation to standard interpretable multi-class classification algorithms.
result Minimizing standard misclassification penalty in the new space is equivalent to minimizing custom cost function.
IFM improves recommender systems by learning flexible feature interactions.
problem Dealing with feature interactions in recommender systems can degrade performance.
method Introduces Interaction-Aware Mechanism (IAM) to learn feature and field interactions.
result Improves performance on two well-known datasets compared to state-of-the-art methods.
DVE models dynamic changes in feature embeddings for better sequence-aware applications.
problem Dynamic characterization of feature variations in time-varying data.
method Dynamic Variational Embedding (DVE) using recurrent neural networks.
result DVE models intrinsic nature and temporal variation of nodes effectively.
Hybrid system combines NMF and TV graph for song recommendations.
problem Improving song recommendation systems.
method Formulates a matrix completion problem using NMF and TV on graphs.
result Outperforms models using only low-rank or graph-based information.