Hongxiang Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hongxiang Lin has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Huiying Hu
Kuaishou Technology, Beijing, China
3 shared publications - Lei Wang
Meituan, Beijing, China
2 shared publications - Xiaoqing Lyu
Peking University
2 shared publications - Xiaoqing Lyu
Wangxuan Institute of Computer Technology, Peking University, Beijing, China and State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, China
2 shared publications - Yixiao Zhou
Wangxuan Institute of Computer Technology, Peking University, Beijing, China
2 shared publications - Bei Hua
School of Computer Science and Technology, University of Science and Technology of China, Hefei, China
1 shared publication
Latest Publications
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1809-1818
ConGM: Contrastive Graph Matching for Graph Self-Supervised Learning
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1809-1818
Open AccessConGM: Contrastive Graph Matching for Graph Self-Supervised Learning
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3957-3967
SMA-GNN: A Symbol-Aware Graph Neural Network for Signed Link Prediction in Recommender Systems
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3957-3967
Open AccessSMA-GNN: A Symbol-Aware Graph Neural Network for Signed Link Prediction in Recommender Systems
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2607-2611
Improving Link Sign Prediction in Signed Bipartite Graphs via Balanced Line Graphs
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2607-2611
Open AccessImproving Link Sign Prediction in Signed Bipartite Graphs via Balanced Line Graphs
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2612-2616
Multi-Interest Matching for Personalized News Recommendation with Large Language Models
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2612-2616
Open AccessMulti-Interest Matching for Personalized News Recommendation with Large Language Models
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4105-4109
Boosting Meta-Learning Cold-Start Recommendation with Graph Neural Network
Meta-learning methods have shown to be effective in dealing with cold-start recommendation. However, most previous methods rely on an ideal assumption that there exists a similar data distribution between source and target tasks, which are unsuitable for the scenario that only extremely limited number of new user or item interactions are available. In this paper, we propose to boost meta-learning cold-start recommendation with graph neural network (MeGNN). First, it utilizes the global neighborhood translation learning to obtain consistent potential interactions for all new user and item nodes, which can refine their representations. Second, it employs the local neighborhood translation learning to predict specific potential interactions for each node, thus guaranteeing the personalized requirement. In experiments, we combine MeGNN with two representative meta-learning models MeLU and TaNP. Extensive results on two widely-used datasets show the superiority of MeGNN in four different scenarios.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4105-4109
Open AccessBoosting Meta-Learning Cold-Start Recommendation with Graph Neural Network
Meta-learning methods have shown to be effective in dealing with cold-start recommendation. However, most previous methods rely on an ideal assumption that there exists a similar data distribution between source and target tasks, which are unsuitable for the scenario that only extremely limited number of new user or item interactions are available. In this paper, we propose to boost meta-learning cold-start recommendation with graph neural network (MeGNN). First, it utilizes the global neighborhood translation learning to obtain consistent potential interactions for all new user and item nodes, which can refine their representations. Second, it employs the local neighborhood translation learning to predict specific potential interactions for each node, thus guaranteeing the personalized requirement. In experiments, we combine MeGNN with two representative meta-learning models MeLU and TaNP. Extensive results on two widely-used datasets show the superiority of MeGNN in four different scenarios.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2021-2025
Gated Attention with Asymmetric Regularization for Transformer-based Continual Graph Learning
Continual graph learning (CGL) aims to mitigate the topological-feature-induced catastrophic forgetting problem (TCF) in graph neural networks, which plays an essential role in the field of information retrieval. The TCF is mainly caused by the forgetting of node features of old tasks and the forgetting of topological features shared by old and new tasks. Existing CGL methods do not pay enough attention to the forgetting of topological features shared between different tasks. In this paper, we propose a transformer-based CGL method (Trans-CGL), thereby taking full advantage of the transformer's properties to mitigate the TCF problem. Specifically, to alleviate forgetting of node features, we introduce a gated attention mechanism for Trans-CGL based on parameter isolation that allows the model to be independent of each other when learning old and new tasks. Furthermore, to address the forgetting of shared parameters that store topological information between different tasks, we propose an asymmetric mask attention regularization module to constrain the shared attention parameters ensuring that the shared topological information is preserved. Comparative experiments show that the method achieves competitive performance on four real-world datasets.
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2021-2025
Open AccessGated Attention with Asymmetric Regularization for Transformer-based Continual Graph Learning
Continual graph learning (CGL) aims to mitigate the topological-feature-induced catastrophic forgetting problem (TCF) in graph neural networks, which plays an essential role in the field of information retrieval. The TCF is mainly caused by the forgetting of node features of old tasks and the forgetting of topological features shared by old and new tasks. Existing CGL methods do not pay enough attention to the forgetting of topological features shared between different tasks. In this paper, we propose a transformer-based CGL method (Trans-CGL), thereby taking full advantage of the transformer's properties to mitigate the TCF problem. Specifically, to alleviate forgetting of node features, we introduce a gated attention mechanism for Trans-CGL based on parameter isolation that allows the model to be independent of each other when learning old and new tasks. Furthermore, to address the forgetting of shared parameters that store topological information between different tasks, we propose an asymmetric mask attention regularization module to constrain the shared attention parameters ensuring that the shared topological information is preserved. Comparative experiments show that the method achieves competitive performance on four real-world datasets.