Publications

2026

1. Comp. & Edu.

   Assessing mindset states of Hong Kong secondary students using machine learning in real-world online learning environment

   Elly Cheng Wang, Xin Guan, Xiaolong Chen, and 1 more author

   Computers & Education, 2026

   Abs DOI Bib

   This study investigates the use of machine learning to detect mindset states — concentration, motivation, perseverance, engagement, and self-initiative among secondary school students in Hong Kong during two real-life online courses. Prior research has explored AI for mindset detection in controlled settings. Addressing real-life challenges such as low data quality, lighting variability, movement, and privacy concerns, this study explores the feasibility of detecting mindset states in a real-life environment with a combination of inputs, including quiz scores, facial expression, and categorized learning behavior logs. Using a Recurrent Neural Network (RNN), we achieved a modest yet significant prediction accuracy, even with a small dataset of approximately one hundred students. In particular, our results demonstrate the potential of logging data as a scalable and privacy-preserving approach for understanding students’ psychological states. We caution that while our results are encouraging, the modest accuracy highlights the need for further optimization before the approach can be reliably applied in real-world educational settings. From a pedagogical perspective, our findings suggest that real-time feedback from well-trained AI tool may provide useful information about students’ mindset states which educators can use to create better student-centered adaptive teaching practices that promote personalized learning while addressing ethical considerations such as data privacy and accessibility.

   @article{WANG2026105554,
     title = {Assessing mindset states of Hong Kong secondary students using machine learning in real-world online learning environment},
     journal = {Computers & Education},
     volume = {245},
     pages = {105554},
     year = {2026},
     issn = {0360-1315},
     doi = {https://doi.org/10.1016/j.compedu.2025.105554},
     url = {https://www.sciencedirect.com/science/article/pii/S0360131525003239},
     author = {Wang, Elly Cheng and Guan, Xin and Chen, Xiaolong and Ng, Tai Kai},
     keywords = {Individualized instruction, Logging behavior, Mindset states, Artificial intelligence (AI), Online course},
   }

2025

1. VLDB 2026

   Augmenting Social Influence of Uncertain Seeds via Probabilistic Link Insertion

   Xiaolong Chen and Jing Tang

   Proc. VLDB Endow., Dec 2025

   DOI
2. KDD 2025

   Scalable Link Recommendation for Influence Maximization

   Xiaolong Chen and Jing Tang

   In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1, Toronto ON, Canada, 2025

   DOI Bib

   @inproceedings{chen2025scalable,
     author = {Chen, Xiaolong and Tang, Jing},
     title = {Scalable Link Recommendation for Influence Maximization},
     year = {2025},
     isbn = {9798400712456},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3690624.3709190},
     doi = {10.1145/3690624.3709190},
     booktitle = {Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1},
     pages = {130-141},
     numpages = {12},
     keywords = {influence maximization, social networks},
     location = {Toronto ON, Canada},
     series = {KDD '25},
   }

3. ICLR 2025

   You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs

   Yihong Luo, Xiaolong Chen, Xinghua Qu, and 2 more authors

   In The Thirteenth International Conference on Learning Representations, 2025

   Bib

   @inproceedings{luoyou,
     title = {You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs},
     author = {Luo, Yihong and Chen, Xiaolong and Qu, Xinghua and Hu, Tianyang and Tang, Jing},
     booktitle = {The Thirteenth International Conference on Learning Representations},
     year = {2025},
   }

2024

1. VLDB 2025

   Efficient Graph Embedding Generation and Update for Large-Scale Temporal Graph

   Yifan Song, Xiaolong Chen, Wenqing Lin, and 5 more authors

   Proc. VLDB Endow., Dec 2024

   Abs DOI Bib

   Graph embedding aims at mapping each node to a low-dimensional vector, beneficial for various applications like pattern matching, retrieval augmented generation and recommendation. In this paper, we study the large-scale temporal graph embedding problem. Different from simple graphs, each edge has a timestamp in temporal graphs, which requires the embeddings to encode the temporal biases. Factorizing similarity matrix is a common approach for generating simple graph embeddings where similarity can be well characterized by some conventional metrics like personalized PageRank. However, how to construct a similarity that can encode interactions with temporal biases is a critical problem for large scale temporal graphs. To address this, we introduce the concept of temporal-based bipartite graph (TBG) and develop the temporal preferential attachment similarity (TPASim) that reflects concurrent node activity over time. Directly factorizing the TPASim matrix, which contains nearly n2 non-zeros, is not feasible for large graphs with n nodes. Instead, we present LTGE, which constructs and factorizes a temporal matrix with at most 2m non-zeros, where m is the number of edges. Our theoretical analysis shows that LTGE achieves the same embeddings as factorizing the TPASim matrix but significantly reduces complexity by a factor of n2/m. On the other hand, when graphs evolve over time, to avoid recomputing, we further propose LTGEInc that utilizes a novel incremental singular value decomposition (SVD) algorithm with provable guarantee for updating the embeddings. Extensive experiments on several datasets with up to 17 million nodes and 1.3 billion edges demonstrate that LTGE outperforms the state of the art significantly and is orders of magnitude faster than the baselines specially designed for temporal graphs. For embeddings update, LTGEInc retains the performance with small computational overhead.

   @article{song2025graph,
     author = {Song, Yifan and Chen, Xiaolong and Lin, Wenqing and Li, Jia and Zhang, Chen and Zhou, Yan and Chen, Lei and Tang, Jing},
     title = {Efficient Graph Embedding Generation and Update for Large-Scale Temporal Graph},
     year = {2024},
     issue_date = {December 2024},
     publisher = {VLDB Endowment},
     volume = {18},
     number = {4},
     issn = {2150-8097},
     url = {https://doi.org/10.14778/3717755.3717756},
     doi = {10.14778/3717755.3717756},
     journal = {Proc. VLDB Endow.},
     month = dec,
     pages = {929-942},
     numpages = {14},
   }

2. WWW 2024

   Link recommendation to augment influence diffusion with provable guarantees

   Xiaolong Chen, Yifan Song, and Jing Tang

   In Proceedings of the ACM Web Conference 2024, 2024

   Oral Presentation DOI Bib

   This paper was selected for an Oral Presentation at the conference

   @inproceedings{chen2024link,
     title = {Link recommendation to augment influence diffusion with provable guarantees},
     author = {Chen, Xiaolong and Song, Yifan and Tang, Jing},
     booktitle = {Proceedings of the ACM Web Conference 2024},
     pages = {2509--2518},
     year = {2024},
     doi = {10.1145/3589334.3645521},
   }