activity
20182023
most citedContrastive Learning with Positive-Negative Frame Mask for Music Representation

17 citations · 36 across the 15 of their papers we have counts for

collaborators
Showing cs.IRShow all

16 papers · 1 filter

cs.IR2023

Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendation

Liangcai Su, Fan Yan, Jieming Zhu +5

Two-tower models are a prevalent matching framework for recommendation, which have been widely deployed in industrial applications. The success of two-tower matching attributes to…

cs.IR2023

Only Encode Once: Making Content-based News Recommender Greener

Qijiong Liu, Jieming Zhu, Quanyu Dai +1

Large pretrained language models (PLM) have become de facto news encoders in modern news recommender systems, due to their strong ability in comprehending textual content. These hu…

cs.IR2023

Time-aligned Exposure-enhanced Model for Click-Through Rate Prediction

Hengyu Zhang, Chang Meng, Wei Guo +5

Click-Through Rate (CTR) prediction, crucial in applications like recommender systems and online advertising, involves ranking items based on the likelihood of user clicks. User be…

cs.IR2023

Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector Quantization

Qijiong Liu, Lu Fan, Jiaren Xiao +2

Category information plays a crucial role in enhancing the quality and personalization of recommender systems. Nevertheless, the availability of item category information is not co…

cs.IR2023

DisCover: Disentangled Music Representation Learning for Cover Song Identification

Jiahao Xun, Shengyu Zhang, Yanting Yang +7

In the field of music information retrieval (MIR), cover song identification (CSI) is a challenging task that aims to identify cover versions of a query song from a massive collect…

cs.IR2023

Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models

Yunjia Xi, Weiwen Liu, Jianghao Lin +8

Recommender systems play a vital role in various online services. However, the insulated nature of training and deploying separately within a specific domain limits their access to…