Multi-stage ranking pipelines have been a practical solution in modern search systems,
where the first-stage retrieval is to return a subset of candidate documents and latter stages …

Collaborative filtering (CF) is a widely studied research topic in recommender systems. The
learning of a CF model generally depends on three major components, namely interaction …

The past two decades have witnessed the rapid development of personalized
recommendation techniques. Despite the significant progress made in both research and …

Large-scale recommendation systems are characterized by their reliance on high
cardinality, heterogeneous features and the need to handle tens of billions of user actions …

In the era of online business, many e-commerce sites have evolved which recommend items
according to one's needs and interests. Plenty of data is available to be processed to make …

Large language models (LLMs) have achieved remarkable success across various
domains, but effectively incorporating complex and potentially noisy user timeline data into …

The learning objective plays a fundamental role to build a recommender system. Most
methods routinely adopt either pointwise (eg, binary cross-entropy) or pairwise (eg, BPR) …

Large Language Models (LLMs) have demonstrated remarkable capabilities and have been
extensively deployed across various domains, including recommender systems. Prior …

Highly skewed long-tail item distribution is very common in recommendation systems. It
significantly hurts model performance on tail items. To improve tail-item recommendation …

Recommender system usually faces popularity bias. From the popularity distribution shift
perspective, the normal paradigm trained on exposed items (most are hot items) identifies …