Shicheng Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shicheng Wang has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Zhiguo Liu
Communication and Network Laboratory, Dalian University, Dalian, China
2 shared publications - Chunwei Yang
College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, China
1 shared publication Dacheng Luo
Xi’an Research Institute of High-Tech
1 shared publication- Dawei Sun
High-Tech Institute of Xi'an, Xi'an, Shaanxi 710025, PR China
1 shared publication Guo Yang
301 Staff Room of the Second Artillery Engineering Institute, The Chinese University of Xi'an, Baqiao, Xi'an
1 shared publication- Haojie Liu
Institute of Photonics Technology, Jinan University, Guangzhou, Guangdong, China
1 shared publication
Latest Publications
- Open Access
- 22 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 3 (3) , 1-23
GIIE: A Graph-based News Recommendation Model with Intrinsic Interest Enhancement
News recommendation aims to offer potentially interesting news items to a specific user, guided by his historical browsing behaviors. Existing methods failed to effectively address the knowledge sparsity issue that the user may have sparse behaviors and the news may own sparse features. To address the problem, we propose a graph-based news recommendation model with intrinsic interest enhancement, named GIIE , leveraging intrinsic interests and neighbor information to enhance the representation of sparse users and news. Concretely, to fully take advantage of the intrinsic interests, we design an interest encoder based on an interest-type graph with a learnable structure and explore the interest embeddings from news types. Then, we inject the obtained interest embeddings into news and represent the user by aggregating the clicked news under the same interest and across different interests sequentially. These interests can build a bridge between users so users with sparse behaviors can implicitly share knowledge with other users, thereby enhancing their representation. To properly introduce the neighbor knowledge, we propose a graph-based neighbor enhancing mechanism. First, we design a news relation graph and a user relation graph in encoders. Then, based on these graphs, we take the attention module to aggregate additional knowledge from neighbors, enhancing sparse news and user representations. To avoid feature ambiguity, we adopt a way to represent the current item (user and news) and its neighbors separately and then do adaptive aggregation. We evaluate GIIE on the public news recommendation datasets MIND-Large and MIND-Small. Experimental results show that our model can solve the knowledge-sparse problem and outperforms current state-of-the-art models in four indicators.
- 22 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 3 (3) , 1-23
Open AccessGIIE: A Graph-based News Recommendation Model with Intrinsic Interest Enhancement
News recommendation aims to offer potentially interesting news items to a specific user, guided by his historical browsing behaviors. Existing methods failed to effectively address the knowledge sparsity issue that the user may have sparse behaviors and the news may own sparse features. To address the problem, we propose a graph-based news recommendation model with intrinsic interest enhancement, named GIIE , leveraging intrinsic interests and neighbor information to enhance the representation of sparse users and news. Concretely, to fully take advantage of the intrinsic interests, we design an interest encoder based on an interest-type graph with a learnable structure and explore the interest embeddings from news types. Then, we inject the obtained interest embeddings into news and represent the user by aggregating the clicked news under the same interest and across different interests sequentially. These interests can build a bridge between users so users with sparse behaviors can implicitly share knowledge with other users, thereby enhancing their representation. To properly introduce the neighbor knowledge, we propose a graph-based neighbor enhancing mechanism. First, we design a news relation graph and a user relation graph in encoders. Then, based on these graphs, we take the attention module to aggregate additional knowledge from neighbors, enhancing sparse news and user representations. To avoid feature ambiguity, we adopt a way to represent the current item (user and news) and its neighbors separately and then do adaptive aggregation. We evaluate GIIE on the public news recommendation datasets MIND-Large and MIND-Small. Experimental results show that our model can solve the knowledge-sparse problem and outperforms current state-of-the-art models in four indicators.
- 1 December 2017
- Published by Elsevier in Aerospace Science and Technology
- Vol. 71, 136-146
Dual-filter transfer alignment for airborne distributed POS based on PVAM
- 1 December 2017
- Published by Elsevier in Aerospace Science and Technology
- Vol. 71, 136-146
Dual-filter transfer alignment for airborne distributed POS based on PVAM
- 1 May 2016
- Published by Elsevier in Infrared Physics & Technology
- Vol. 76, 740-747
Kernel sparse coding method for automatic target recognition in infrared imagery using covariance descriptor
- 1 May 2016
- Published by Elsevier in Infrared Physics & Technology
- Vol. 76, 740-747
Kernel sparse coding method for automatic target recognition in infrared imagery using covariance descriptor
- 22 September 2013
- Published by Springer Nature
- p. 763-771
A Novel Acquisition Scheme for a GPS Software Receiver Based on Two Stand-Alone One-Dimensional Search Processes
- 22 September 2013
- Published by Springer Nature
- p. 763-771
A Novel Acquisition Scheme for a GPS Software Receiver Based on Two Stand-Alone One-Dimensional Search Processes
- 1 July 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 754-759
SINS/SAR/GPS navigation system intelligent fault diagnosis method
Residual chi-square test is not sensitive to soft faults and also can't detect suddenly changing faults well in inaccurate observation noise, therefore, an intelligent fault diagnosis method of residual chi-square test assisted by fuzzy adaptive filter is proposed to slove the problem. To deal with the soft fault, a fuzzy adaptive filtering algorithm is proposed. By monitoring the residual and the residual rate, the observation quality gene is obtained by the fuzzy logic control system. The local filter is adaptively adjusted on-line, and the filtering divergence arising from the gradual changing fault is prevented, and then the residual chi-square test is assisted to detect faults. Simulation results show that the proposed method can effectively diagnose suddenly changing faults and soft faults online, and ensure system precision during failure phase, and the system reliability is improved.
- 1 July 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 754-759
SINS/SAR/GPS navigation system intelligent fault diagnosis method
Residual chi-square test is not sensitive to soft faults and also can't detect suddenly changing faults well in inaccurate observation noise, therefore, an intelligent fault diagnosis method of residual chi-square test assisted by fuzzy adaptive filter is proposed to slove the problem. To deal with the soft fault, a fuzzy adaptive filtering algorithm is proposed. By monitoring the residual and the residual rate, the observation quality gene is obtained by the fuzzy logic control system. The local filter is adaptively adjusted on-line, and the filtering divergence arising from the gradual changing fault is prevented, and then the residual chi-square test is assisted to detect faults. Simulation results show that the proposed method can effectively diagnose suddenly changing faults and soft faults online, and ensure system precision during failure phase, and the system reliability is improved.