Author name cluster

Hua Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution

Hua Liu
Yanbin Wei
Fei Xing
Tyler Derr
Haoyu Han
Yu Zhang

Dynamic graphs are common in real‑world systems such as social media, recommender systems, and traffic networks. Existing dynamic graph models for link prediction often fall short in capturing the full complexity of temporal evolution. They tend to overlook fine‑grained variations in interaction order, struggle with dependencies that span long time horizons, and provide limited modeling of pair‑specific relational dynamics. To address those challenges, we propose Graph2Video, a video‑inspired framework that views the temporal neighborhood of a target link as a sequence of “graph frames”. By stacking temporally ordered subgraph frames into a “graph video”, Graph2Video leverages the inductive biases of video foundation models to capture both fine-grained local variations and long-range temporal dynamics. It generates a link-level embedding that serves as a lightweight, plug-and-play, link-centric memory unit. This embedding integrates seamlessly into existing dynamic graph encoders, effectively addressing the limitations of prior approaches. Extensive experiments on benchmark datasets show that Graph2Video outperforms state‑of‑the‑art baselines in the link prediction task on most cases. The results highlight that borrowing spatio‑temporal modeling techniques from computer vision provides a principled and effective avenue for advancing dynamic graph learning.

PDF Details DOI

JMLR Journal 2023 Journal Article

Functional L-Optimality Subsampling for Functional Generalized Linear Models with Massive Data

Hua Liu
Jinhong You
Jiguo Cao

Massive data bring the big challenges of memory and computation for analysis. These challenges can be tackled by taking subsamples from the full data as a surrogate. For functional data, it is common to collect multiple measurements over their domains, which require even more memory and computation time when the sample size is large. The computation would be much more intensive when statistical inference is required through bootstrap samples. Motivated by analyzing large-scale kidney transplant data, we propose an optimal subsampling method based on the functional L-optimality criterion for functional generalized linear models. To the best of our knowledge, this is the first attempt to propose a subsampling method for functional data analysis. The asymptotic properties of the resultant estimators are also established. The analysis results from extensive simulation studies and from the kidney transplant data show that the functional L-optimality subsampling (FLoS) method is much better than the uniform subsampling approach and can well approximate the results based on the full data while dramatically reducing the computation time and memory. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

PDF Details

EAAI Journal 2023 Journal Article

Research on decision-level fusion method based on structural causal model in system-level fault detection and diagnosis

Haoyuan Pu
Zhi Chen
Jie Liu
Xiaohua Yang
Changan Ren
Hua Liu
Yifan Jian

At present, system-level fault detection and diagnosis (FDD) research often uses correlation-based machine learning methods combined with multiple heterogeneous diagnosis methods to improve the fault detection rate (FDR), that is, decision-level fusion. Since it does not take into account the causal direction of the decision relationship, it will affect the realization of the fusion objectives, and lead to the reduction of the fusion range and the decrease of the global decision on FDR. In this regard, the structural causal model (SCM), a commonly used causal model in causal science, can use the causal graph to ensure causal direction of fusion, and the structural equation can be used to achieve fusion objectives to increase FDR, which can improve this problem. In this paper, we propose seven fusion objectives according to the diagnostic advantage interval of each preliminary method, and use SCM to construct causal graph and structural equation to achieve decision-level fusion according to the proposed seven fusion objectives, thereby improving FDR. The proposed method is validated through the simulation platform Tennessee Eastman process. We choose to combine the prediction results of Linear Discriminant Analysis method and Gaussian Naive Bayes method to achieve decision-level fusion. The results show that compared with the single method and the Bayesian network decision-level fusion method, the proposed method can achieve the best results in the FDR of each single system state and average FDR, and the above indicators are significantly improved.

Details DOI

YNIMG Journal 2019 Journal Article

Modular architecture of metabolic brain network and its effects on the spread of perturbation impact

Tianhao Zhang
Qi Huang
Chunxiang Jiao
Hua Liu
Binbin Nie
Shengxiang Liang
Panlong Li
Xi Sun

Metabolic brain network, which is based on functional correlation patterns of 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) images, has been widely applied in both basic and clinical neuroscience. Exploring the properties of the metabolic brain network can provide valuable insight to the physiologic and pathologic processes of the brain. Based on the network theory, modular architecture has the ability to limit the spread of local perturbation impact and therefore modular networks are more robust against external damage. However, whether the metabolic brain network has modular architecture remains unknown. Methods 77 rats performed 18F-FDG PET brain imaging. The metabolic brain network was then constructed by measuring interregional metabolic correlation in inter-subject manner. Afterwards, modular architecture of the network was detected by a greedy algorithm. Further, we perturbed the metabolic brain network by inducing focal photothrombotic ischemia in the bilateral motor cortex and then measured the glucose metabolic change of each brain region using FDG-PET. Results A significant modular architecture was found in the metabolic brain network. The network could be divided into four modules which corresponding approximately to executive, learning/memory, visual/auditory and sensorimotor processing functional domains. After inducing the focal ischemia on the bilateral motor cortex, most of the significantly changed brain regions (13 of 17) belong to the sensorimotor module. Conclusion Our results revealed an inherent modular architecture in the metabolic brain network and gave an experimental evidence that the modularity of the metabolism brain network could limit the spread of local perturbation impact.

Details DOI