Dongmei Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Dongmei Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Xiaolong Qu
School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
4 shared publications - Yu Yang
School of Information Science and Technology, Beijing Forestry University, Beijing, China
3 shared publications - Chao Song
School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
2 shared publications - Haipeng Zhang
School of Information Science and Technology, Beijing Forestry University, Beijing, Beijing, China
2 shared publications - Xiaoping Zhang
China National Data Center of Tradition Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing, Beijing, China
2 shared publications - Chao Song
Beijing Botanical Garden, Beijing 100093, China
1 shared publication
Latest Publications
- Open Access
- 21 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 652-659
AutoEncoder-based Weighted Multi-modal Knowledge Graph Representation Learning
- 21 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 652-659
Open AccessAutoEncoder-based Weighted Multi-modal Knowledge Graph Representation Learning
- Open Access
- 21 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 710-715
Temporal Knowledge Graph Reasoning with Reinforcement Learning for Clinical Gastritis Prediction
- 21 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 710-715
Open AccessTemporal Knowledge Graph Reasoning with Reinforcement Learning for Clinical Gastritis Prediction
- Open Access
- 14 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 631-637
TCM Intelligent Recommendation Based on Multimodal Knowledge Graph Attention Network
In recent years, with the inheritance, innovation, and development of traditional Chinese medicine (TCM), an increasing number of individuals have shown interest in the field of TCM. However, TCM, as a complex and rich medical system, has posed challenges in terms of information retrieval and dissemination. Traditional search engine methods suffer from issues such as low retrieval efficiency and information overload, which significantly hinder the informatization process of TCM. To address this problem, we propose a Multimodal Knowledge Graph Attention Networks (MKGAN) to enhance TCM intelligent recommendation by leveraging the multimodal knowledge of TCM and their high-order side information. Specially, we construct a multimodal knowledge graph (MKG) for TCM by integrating data from various heterogeneous sources into a unified knowledge representation. Building upon this MKG, we employ graph attention networks to enhance both item and user feature representations. Ultimately, we utilize these enhanced feature representations to achieve personalized recommendations. Extensive experiments and performance comparisons with baseline models demonstrate the superior performance of MKGAN in TCM intelligent scientific recommendation, which promises substantial support for TCM informatization process.
- 14 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 631-637
Open AccessTCM Intelligent Recommendation Based on Multimodal Knowledge Graph Attention Network
In recent years, with the inheritance, innovation, and development of traditional Chinese medicine (TCM), an increasing number of individuals have shown interest in the field of TCM. However, TCM, as a complex and rich medical system, has posed challenges in terms of information retrieval and dissemination. Traditional search engine methods suffer from issues such as low retrieval efficiency and information overload, which significantly hinder the informatization process of TCM. To address this problem, we propose a Multimodal Knowledge Graph Attention Networks (MKGAN) to enhance TCM intelligent recommendation by leveraging the multimodal knowledge of TCM and their high-order side information. Specially, we construct a multimodal knowledge graph (MKG) for TCM by integrating data from various heterogeneous sources into a unified knowledge representation. Building upon this MKG, we employ graph attention networks to enhance both item and user feature representations. Ultimately, we utilize these enhanced feature representations to achieve personalized recommendations. Extensive experiments and performance comparisons with baseline models demonstrate the superior performance of MKGAN in TCM intelligent scientific recommendation, which promises substantial support for TCM informatization process.
- Open Access
- 15 June 2023
- Published by MDPI AG in Electronics
- Vol. 12 (12) , 2688
MKGCN: Multi-Modal Knowledge Graph Convolutional Network for Music Recommender Systems
With the emergence of online music platforms, music recommender systems are becoming increasingly crucial in music information retrieval. Knowledge graphs (KGs) are a rich source of semantic information for entities and relations, allowing for improved modeling and analysis of entity relations to enhance recommendations. Existing research has primarily focused on the modeling and analysis of structural triples, while largely ignoring the representation and information processing capabilities of multi-modal data such as music videos and lyrics, which has hindered the improvement and user experience of music recommender systems. To address these issues, we propose a Multi-modal Knowledge Graph Convolutional Network (MKGCN) to enhance music recommendation by leveraging the multi-modal knowledge of music items and their high-order structural and semantic information. Specifically, there are three aggregators in MKGCN: the multi-modal aggregator aggregates the text, image, audio, and sentiment features of each music item in a multi-modal knowledge graph (MMKG); the user aggregator and item aggregator use graph convolutional networks to aggregate multi-hop neighboring nodes on MMKGs to model high-order representations of user preferences and music items, respectively. Finally, we utilize the aggregated embedding representations for recommendation. In training MKGCN, we adopt the ratio negative sampling strategy to generate high-quality negative samples. We construct four different-sized music MMKGs using the public dataset Last-FM and conduct extensive experiments on them. The experimental results demonstrate that MKGCN achieves significant improvements and outperforms several state-of-the-art baselines.
- 15 June 2023
- Published by MDPI AG in Electronics
- Vol. 12 (12) , 2688
Open AccessMKGCN: Multi-Modal Knowledge Graph Convolutional Network for Music Recommender Systems
With the emergence of online music platforms, music recommender systems are becoming increasingly crucial in music information retrieval. Knowledge graphs (KGs) are a rich source of semantic information for entities and relations, allowing for improved modeling and analysis of entity relations to enhance recommendations. Existing research has primarily focused on the modeling and analysis of structural triples, while largely ignoring the representation and information processing capabilities of multi-modal data such as music videos and lyrics, which has hindered the improvement and user experience of music recommender systems. To address these issues, we propose a Multi-modal Knowledge Graph Convolutional Network (MKGCN) to enhance music recommendation by leveraging the multi-modal knowledge of music items and their high-order structural and semantic information. Specifically, there are three aggregators in MKGCN: the multi-modal aggregator aggregates the text, image, audio, and sentiment features of each music item in a multi-modal knowledge graph (MMKG); the user aggregator and item aggregator use graph convolutional networks to aggregate multi-hop neighboring nodes on MMKGs to model high-order representations of user preferences and music items, respectively. Finally, we utilize the aggregated embedding representations for recommendation. In training MKGCN, we adopt the ratio negative sampling strategy to generate high-quality negative samples. We construct four different-sized music MMKGs using the public dataset Last-FM and conduct extensive experiments on them. The experimental results demonstrate that MKGCN achieves significant improvements and outperforms several state-of-the-art baselines.