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 …

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 …

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 …

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 …

Industrial recommender systems usually hold data from multiple business scenarios and are
expected to provide recommendation services for these scenarios simultaneously. In the …

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 …

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 …

Recently, a new paradigm, meta learning, has been widely applied to Deep Learning
Recommendation Models (DLRM) and significantly improves statistical performance …

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 …

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 …