Towards understanding the overfitting phenomenon of deep click-through rate models
Deep learning techniques have been applied widely in industrial recommendation systems.
However, far less attention has been paid on the overfitting problem of models in …
However, far less attention has been paid on the overfitting problem of models in …
KEEP: An industrial pre-training framework for online recommendation via knowledge extraction and plugging
An industrial recommender system generally presents a hybrid list that contains results from
multiple subsystems. In practice, each subsystem is optimized with its own feedback data to …
multiple subsystems. In practice, each subsystem is optimized with its own feedback data to …
Deep task-specific bottom representation network for multi-task recommendation
Neural-based multi-task learning (MTL) has gained significant improvement, and it has been
successfully applied to recommendation system (RS). Recent deep MTL methods for RS (eg …
successfully applied to recommendation system (RS). Recent deep MTL methods for RS (eg …
UGACHE: A Unified GPU Cache for Embedding-based Deep Learning
This paper presents UGache, a unified multi-GPU cache system for embedding-based deep
learning (EmbDL). UGache is primarily motivated by the unique characteristics of EmbDL …
learning (EmbDL). UGache is primarily motivated by the unique characteristics of EmbDL …
Adaptive domain interest network for multi-domain recommendation
Industrial recommender systems usually hold data from multiple business scenarios and are
expected to provide recommendation services for these scenarios simultaneously. In the …
expected to provide recommendation services for these scenarios simultaneously. In the …
Joint optimization of ranking and calibration with contextualized hybrid model
Despite the development of ranking optimization techniques, pointwise loss remains the
dominating approach for click-through rate prediction. It can be attributed to the calibration …
dominating approach for click-through rate prediction. It can be attributed to the calibration …
Experimental analysis of large-scale learnable vector storage compression
Learnable embedding vector is one of the most important applications in machine learning,
and is widely used in various database-related domains. However, the high dimensionality …
and is widely used in various database-related domains. However, the high dimensionality …
G-meta: Distributed meta learning in gpu clusters for large-scale recommender systems
Recently, a new paradigm, meta learning, has been widely applied to Deep Learning
Recommendation Models (DLRM) and significantly improves statistical performance …
Recommendation Models (DLRM) and significantly improves statistical performance …
Capturing conversion rate fluctuation during sales promotions: A novel historical data reuse approach
Conversion rate (CVR) prediction is one of the core components in online recommender
systems, and various approaches have been proposed to obtain accurate and well …
systems, and various approaches have been proposed to obtain accurate and well …
Extr: click-through rate prediction with externalities in e-commerce sponsored search
Click-Through Rate (CTR) prediction, estimating the probability of a user clicking on items,
plays a key fundamental role in sponsored search. E-commerce platforms display organic …
plays a key fundamental role in sponsored search. E-commerce platforms display organic …