Zihan Liu

Zihan Liu

Auto-generated profile, based on publicly available information

Zihan Liu

University of California, San Diego, San Diego, CA, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 October 2024
Verified
Conference Paper
Open access
ZLZihan Liu
Zihan Liu
YHYupeng Hou
Yupeng Hou
JMJulian J. McAuley
Julian J. McAuley
The task of multi-behavioral sequential recommendation (MBSR) has grown in importance in personalized recommender systems, aiming to incorporate behavior types of interactions for better recommendations. Existing approaches focus on the next-item prediction objective, neglecting the value of integrating the target behavior type into the learning objective. In this paper, we propose MBGen, a novel Multi-Behavioral sequential Generative recommendation framework. We model the MBSR task into a consecutive two-step process: (1) given item sequences, MBGen first predicts the next behavior type to frame the user intention, (2) given item sequences and a target behavior type, MBGen then predicts the next items. To model such a two-step process, we tokenize both behaviors and items into tokens and construct one single token sequence with both behaviors and items placed interleaved. Furthermore, we design a unified generative recommendation paradigm that learns to autoregressive generate next behavior and item tokens, naturally enabling a multi-task capability. Additionally, we exploit the heterogeneous nature of token sequences in the generative recommendation and propose a position-routed sparse architecture to efficiently scale up models under the generative recommendation paradigm. Extensive experiments on real-world public datasets demonstrate that MBGen significantly outperforms existing MBSR models across multiple tasks.

12 November 2021
Verified
Conference Paper
Closed access
ZLZihan Liu
Zihan Liu
GSGuoyou Shi
Guoyou Shi
WLWeifeng Li
Weifeng Li
In the case of signal masking, the accuracy of global positioning system (GPS) receiver output drops sharply, or even no output. At this time, inertial navigation (INS)/GPS navigation works in pure inertial mode, and the accuracy is relatively low. In order to enable INS/GPS integrated navigation to obtain high-precision navigation information even when the GPS receiver is not working, an improved radia basis function(RBF)neural network optimized by the particle swarm algorithm is proposed to assist Kalman filter(KF), which is combined with back-propagation(BP) neural network, the convergence of RBF neural network is simulated and compared, and the experimental results show that this method can effectively suppress the filter divergence when the GPS is out of lock, and improve the accuracy of navigation and positioning.