Zhuofeng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhuofeng Li has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Haoxiang Zhang
Shanghai University, Shanghai, China
2 shared publications - Chenglei Wu
Kuaishou Technology, Hangzhou, China
1 shared publication - Enyun Yu
Independent, Beijing, China
1 shared publication - Liang Zhao
Emory University
1 shared publication - Qiannan Zhang
Cornell University, New York, USA
1 shared publication - Shichao Pei
University of Massachusetts Boston, Boston, Massachusetts, USA
1 shared publication
Latest Publications
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5879-5887
GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 5879-5887
Open AccessGReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1326-1335
Learning from Novel Knowledge: Continual Few-shot Knowledge Graph Completion
Knowledge graph (KG) completion has been increasingly recognized as a vital approach for uncovering missing knowledge and addressing the incompleteness issue in KGs. To enhance inference on rare relations and mitigate the impact of the long-tail distribution, the dominant strategy designs few-shot models following the meta-learning paradigm. However, these approaches typically operate under the assumption that KGs are available instantly, disregarding the newly emerging relations during KG enrichment. Thus, the emergence of these novel relations presents a need for few-shot models to continually learn from emerging knowledge. Although promising, two significant obstacles, i.e., catastrophic forgetting and the scarcity of novel relations, prevent effective learning from newly emerging relations. In this paper, we propose a novel framework designed to equip the few-shot model with the ability to learn sequentially from novel relations. Specifically, we introduce innovative strategies at both data and model levels: data-level rehearsal and model-level modulation to address catastrophic forgetting, alongside multi-view relation augmentation aimed at resolving the issue of insufficient novel relations. Extensive experiments conducted on real-world KGs validate the effectiveness of our proposed method.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1326-1335
Open AccessLearning from Novel Knowledge: Continual Few-shot Knowledge Graph Completion
Knowledge graph (KG) completion has been increasingly recognized as a vital approach for uncovering missing knowledge and addressing the incompleteness issue in KGs. To enhance inference on rare relations and mitigate the impact of the long-tail distribution, the dominant strategy designs few-shot models following the meta-learning paradigm. However, these approaches typically operate under the assumption that KGs are available instantly, disregarding the newly emerging relations during KG enrichment. Thus, the emergence of these novel relations presents a need for few-shot models to continually learn from emerging knowledge. Although promising, two significant obstacles, i.e., catastrophic forgetting and the scarcity of novel relations, prevent effective learning from newly emerging relations. In this paper, we propose a novel framework designed to equip the few-shot model with the ability to learn sequentially from novel relations. Specifically, we introduce innovative strategies at both data and model levels: data-level rehearsal and model-level modulation to address catastrophic forgetting, alongside multi-view relation augmentation aimed at resolving the issue of insufficient novel relations. Extensive experiments conducted on real-world KGs validate the effectiveness of our proposed method.