Yifan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yifan Wang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Ming Zhang
State Key Laboratory for Multimedia Information Processing, School of Computer Science, PKU-Anker LLM Lab, Peking University, Beijing, China
2 shared publications - Bing Cheng
Beijing China
1 shared publication Chong Chen
Alibaba Group DAMO Academy China
1 shared publication- Hongxia Yang
DAMO Academy, Alibaba Group
1 shared publication - Jiangke Fan
Meituan
1 shared publication - Jingren Zhou
Alibaba Group, Seattle, USA
1 shared publication
Latest Publications
- Open Access
TGNN: A Joint Semi-supervised Framework for Graph-level Classification
This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing to explicitly leverage features derived from graph topology (e.g., paths). Moreover, when labeled data is scarce, these methods are far from satisfactory due to their insufficient topology exploration of unlabeled data. We address the challenge by proposing a novel semi-supervised framework called Twin Graph Neural Network (TGNN). To explore graph structural information from complementary views, our TGNN has a message passing module and a graph kernel module. To fully utilize unlabeled data, for each module, we calculate the similarity of each unlabeled graph to other labeled graphs in the memory bank and our consistency loss encourages consistency between two similarity distributions in different embedding spaces. The two twin modules collaborate with each other by exchanging instance similarity knowledge to fully explore the structure information of both labeled and unlabeled data. We evaluate our TGNN on various public datasets and show that it achieves strong performance.
Open AccessTGNN: A Joint Semi-supervised Framework for Graph-level Classification
This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing to explicitly leverage features derived from graph topology (e.g., paths). Moreover, when labeled data is scarce, these methods are far from satisfactory due to their insufficient topology exploration of unlabeled data. We address the challenge by proposing a novel semi-supervised framework called Twin Graph Neural Network (TGNN). To explore graph structural information from complementary views, our TGNN has a message passing module and a graph kernel module. To fully utilize unlabeled data, for each module, we calculate the similarity of each unlabeled graph to other labeled graphs in the memory bank and our consistency loss encourages consistency between two similarity distributions in different embedding spaces. The two twin modules collaborate with each other by exchanging instance similarity knowledge to fully explore the structure information of both labeled and unlabeled data. We evaluate our TGNN on various public datasets and show that it achieves strong performance.
- 17 March 2023
- Published by Springer Nature
- p. 474-490
AD-AUG: Adversarial Data Augmentation for Counterfactual Recommendation
- 17 March 2023
- Published by Springer Nature
- p. 474-490
AD-AUG: Adversarial Data Augmentation for Counterfactual Recommendation
- 8 April 2022
- Published by Springer Nature
- p. 298-305
Deep Graph Mutual Learning for Cross-domain Recommendation
- 8 April 2022
- Published by Springer Nature
- p. 298-305
Deep Graph Mutual Learning for Cross-domain Recommendation