Mengyang Ma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mengyang Ma has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jingtong Gao
City University of Hong Kong, Hong Kong, China
1 shared publication - Pengyue Jia
City University of Hong Kong, Hong Kong, China
1 shared publication - Wanyu Wang
City University of Hong Kong, Hong Kong, Hong Kong
1 shared publication - Weihong Luo
Tencent, Shenzhen, China
1 shared publication - Xiangyu Zhao
City University of Hong Kong, Kowloon Tong, Hong Kong
1 shared publication - Xiao Han
Zhejiang University of Technology, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6389-6399
BlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations
Transformer structures have been widely used in sequential recommender systems (SRS). However, as user interaction histories increase, computational time and memory requirements also grow. This is mainly caused by the standard attention mechanism. Although there exist many methods employing efficient attention and SSM-based models, these approaches struggle to effectively model long sequences and may exhibit unstable performance on short sequences. To address these challenges, we design a sparse attention mechanism, BlossomRec, which models both long-term and short-term user interests through attention computation to achieve stable performance across sequences of varying lengths. Specifically, we categorize user interests in recommendation systems into long-term and short-term interests, and compute them using two distinct sparse attention patterns, with the results combined through a learnable gated output. Theoretically, it significantly reduces the number of interactions participating in attention computation. Extensive experiments on four public datasets demonstrate that BlossomRec, when integrated with state-of-the-art Transformer-based models, achieves comparable or even superior performance while significantly reducing memory usage, providing strong evidence of BlossomRec's efficiency and effectiveness. The code is available at https://github.com/Applied-Machine-Learning-Lab/WWW2026_BlossomRec.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6389-6399
Open AccessBlossomRec: Block-level Fused Sparse Attention Mechanism for Sequential Recommendations
Transformer structures have been widely used in sequential recommender systems (SRS). However, as user interaction histories increase, computational time and memory requirements also grow. This is mainly caused by the standard attention mechanism. Although there exist many methods employing efficient attention and SSM-based models, these approaches struggle to effectively model long sequences and may exhibit unstable performance on short sequences. To address these challenges, we design a sparse attention mechanism, BlossomRec, which models both long-term and short-term user interests through attention computation to achieve stable performance across sequences of varying lengths. Specifically, we categorize user interests in recommendation systems into long-term and short-term interests, and compute them using two distinct sparse attention patterns, with the results combined through a learnable gated output. Theoretically, it significantly reduces the number of interactions participating in attention computation. Extensive experiments on four public datasets demonstrate that BlossomRec, when integrated with state-of-the-art Transformer-based models, achieves comparable or even superior performance while significantly reducing memory usage, providing strong evidence of BlossomRec's efficiency and effectiveness. The code is available at https://github.com/Applied-Machine-Learning-Lab/WWW2026_BlossomRec.