Ge Teng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ge Teng has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Xiang Tian
Zhejiang Provincial Key Laboratory of Internet Multimedia Technology, College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310027, China
2 shared publications Chen Shen
1 shared publication- Chen Shen
Tongyi Lab, Alibaba Group, Hangzhou, China
1 shared publication Jieping Ye
1 shared publication- Jieping Ye
Qwen-Character Team, Alibaba Group, China
1 shared publication - Liang Xie
Zhejiang University of Technology
1 shared publication
Latest Publications
- 19 June 2026
- Published by Elsevier in Neurocomputing
- Vol. 698
DDPT: Enhancing complex reasoning in large language models via distillation and dynamic prompt tuning
- 19 June 2026
- Published by Elsevier in Neurocomputing
- Vol. 698
DDPT: Enhancing complex reasoning in large language models via distillation and dynamic prompt tuning
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 2888-2899
URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering
Incomplete multi-view clustering (IMVC) aims to cluster multi-view data that are only partially available. This poses two main challenges: effectively leveraging multi-view information and mitigating the impact of missing views. Prevailing solutions employ cross-view contrastive learning and missing view recovery techniques. However, they either neglect valuable complementary information by focusing only on consensus between views or provide unreliable recovered views due to the absence of supervision. To address these limitations, we propose a novel Unified and Robust Representation Learning for Incomplete Multi-View Clustering (URRL-IMVC). URRL-IMVC directly learns a unified embedding that is robust to view missing conditions by integrating information from multiple views and neighboring samples. Firstly, to overcome the limitations of cross-view contrastive learning, URRL-IMVC incorporates an attention-based auto-encoder framework to fuse multi-view information and generate unified embeddings. Secondly, URRL-IMVC directly enhances the robustness of the unified embedding against view-missing conditions through KNN imputation and data augmentation techniques, eliminating the need for explicit missing view recovery. Finally, incremental improvements are introduced to further enhance the overall performance, such as the Clustering Module and the customization of the Encoder. We extensively evaluate the proposed URRL-IMVC framework on various benchmark datasets, demonstrating its state-of-the-art performance. Furthermore, comprehensive ablation studies are performed to validate the effectiveness of our design.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 2888-2899
Open AccessURRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering
Incomplete multi-view clustering (IMVC) aims to cluster multi-view data that are only partially available. This poses two main challenges: effectively leveraging multi-view information and mitigating the impact of missing views. Prevailing solutions employ cross-view contrastive learning and missing view recovery techniques. However, they either neglect valuable complementary information by focusing only on consensus between views or provide unreliable recovered views due to the absence of supervision. To address these limitations, we propose a novel Unified and Robust Representation Learning for Incomplete Multi-View Clustering (URRL-IMVC). URRL-IMVC directly learns a unified embedding that is robust to view missing conditions by integrating information from multiple views and neighboring samples. Firstly, to overcome the limitations of cross-view contrastive learning, URRL-IMVC incorporates an attention-based auto-encoder framework to fuse multi-view information and generate unified embeddings. Secondly, URRL-IMVC directly enhances the robustness of the unified embedding against view-missing conditions through KNN imputation and data augmentation techniques, eliminating the need for explicit missing view recovery. Finally, incremental improvements are introduced to further enhance the overall performance, such as the Clustering Module and the customization of the Encoder. We extensively evaluate the proposed URRL-IMVC framework on various benchmark datasets, demonstrating its state-of-the-art performance. Furthermore, comprehensive ablation studies are performed to validate the effectiveness of our design.