Yuxiao Duan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuxiao Duan has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Hao Guo
National university of defense technology, Changsha, China
3 shared publications - Xiang Zhao
National Key Laboratory of Big Data and Decision, National University of Defense Technology, Changsha, China
3 shared publications - Yuzhuo Dang
National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha, China
3 shared publications - Fei Cai
National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha, China
2 shared publications - Honghui Chen
National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha, China
2 shared publications - Wanyu Chen
College of Electronic countermeasures, National University of Defense Technology, Hefei, China
2 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 257-267
MLLMRec: A Preference Reasoning Paradigm with Graph Refinement for Multimodal Recommendation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 257-267
Open AccessMLLMRec: A Preference Reasoning Paradigm with Graph Refinement for Multimodal Recommendation
- 27 February 2026
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 72
Dual-space feature representation learning network for multimodal recommender systems
- 27 February 2026
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 72
Dual-space feature representation learning network for multimodal recommender systems
- 25 July 2025
- Published by Elsevier in Decision Support Systems
- Vol. 196
Sentiment-aware cross-modal semantic interaction model for harmful meme detection
- 25 July 2025
- Published by Elsevier in Decision Support Systems
- Vol. 196
Sentiment-aware cross-modal semantic interaction model for harmful meme detection
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1904-1907
OSPC: OCR-Assisted VLM for Zero-Shot Harmful Meme Detection
Harmful memes refer to the memes which contain social bias towards a certain group, such as gender, race, disabilities and so on. Detecting these harmful memes requires the model to have both visual and linguistic understanding of memes and some external knowledge about the culture and morality. This technical report summarises the fourth place solution of the Online Safety Prize Challenge, which enhances a visual language model (VLM) by integrating external Optical Character Recognition (OCR) tools, employs prompt engineering and manual resource management to optimize performance within limited resource constraints. This strategy achieved a score of 0.723/0.643(AUROC/ACC) in this challenge with one single submission
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1904-1907
Open AccessOSPC: OCR-Assisted VLM for Zero-Shot Harmful Meme Detection
Harmful memes refer to the memes which contain social bias towards a certain group, such as gender, race, disabilities and so on. Detecting these harmful memes requires the model to have both visual and linguistic understanding of memes and some external knowledge about the culture and morality. This technical report summarises the fourth place solution of the Online Safety Prize Challenge, which enhances a visual language model (VLM) by integrating external Optical Character Recognition (OCR) tools, employs prompt engineering and manual resource management to optimize performance within limited resource constraints. This strategy achieved a score of 0.723/0.643(AUROC/ACC) in this challenge with one single submission
- Open Access
- 29 February 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (5) , 2044
Commonsense-Guided Inductive Relation Prediction with Dual Attention Mechanism
The inductive relation prediction of knowledge graphs, as an important research topic, aims at predicting the missing relation between unknown entities with many real-world applications. Existing approaches toward this problem mostly use enclosing subgraphs to extract the features of target nodes to make predictions; however, there is a tendency to ignore the neighboring relations outside the enclosing subgraph, thus leading to inaccurate predictions. In addition, they also neglect the rich commonsense information that can help filter out less convincing results. In order to address the above issues, this paper proposes a commonsense-guided inductive relation prediction method with a dual attention mechanism called CNIA. Specifically, in addition to the enclosing subgraph, we added the multi-hop neighboring relations of target nodes, thereby forming a neighbor-enriched subgraph where the initial embeddings are generated. Next, we obtained the subgraph representations with a dual attention (i.e., edge-aware and relation-aware) mechanism, as well as the neighboring relational path embeddings. Then, we concatenated the two embeddings before feeding them into the supervised learning model. A commonsense re-ranking mechanism was introduced to filter the results that conformed to commonsense. Extensive experiments on WN18RR, FB15k-237, and NELL995 showed that CNIA achieves better prediction results when compared to the state-of-the-art models. The results suggested that our proposed model can be considered as an effective and state-of-the-art solution for inductive relation prediction.
- 29 February 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (5) , 2044
Open AccessCommonsense-Guided Inductive Relation Prediction with Dual Attention Mechanism
The inductive relation prediction of knowledge graphs, as an important research topic, aims at predicting the missing relation between unknown entities with many real-world applications. Existing approaches toward this problem mostly use enclosing subgraphs to extract the features of target nodes to make predictions; however, there is a tendency to ignore the neighboring relations outside the enclosing subgraph, thus leading to inaccurate predictions. In addition, they also neglect the rich commonsense information that can help filter out less convincing results. In order to address the above issues, this paper proposes a commonsense-guided inductive relation prediction method with a dual attention mechanism called CNIA. Specifically, in addition to the enclosing subgraph, we added the multi-hop neighboring relations of target nodes, thereby forming a neighbor-enriched subgraph where the initial embeddings are generated. Next, we obtained the subgraph representations with a dual attention (i.e., edge-aware and relation-aware) mechanism, as well as the neighboring relational path embeddings. Then, we concatenated the two embeddings before feeding them into the supervised learning model. A commonsense re-ranking mechanism was introduced to filter the results that conformed to commonsense. Extensive experiments on WN18RR, FB15k-237, and NELL995 showed that CNIA achieves better prediction results when compared to the state-of-the-art models. The results suggested that our proposed model can be considered as an effective and state-of-the-art solution for inductive relation prediction.