Zhanyu Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zhanyu Liu has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Guangjie Zheng
Shanghai Jiao Tong University, Shanghai, China
10 shared publications - Yanwei Yu
Ocean University of China
3 shared publications - Jianrong Ding
Shanghai Jiao Tong University
2 shared publications - Wei Hua
Southeast University
2 shared publications - Bin Lu
Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Chaolv Zeng
Shanghai Jiao Tong University, Shanghai, China
1 shared publication
Latest Publications
- 4 October 2025
- Published by Springer Nature
- p. 474-491
Supply Framework of Physical Machine Demand in Elastic Computing Service
- 4 October 2025
- Published by Springer Nature
- p. 474-491
Supply Framework of Physical Machine Demand in Elastic Computing Service
- Open Access
- 6 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making for Intelligent Transportation System (ITS). However, existing imputation methods generally perform zero pre-filling techniques to initialize missing values, introducing inevitable noise. Moreover, we observe prevalent over-smoothed interpolations, falling short in revealing the intrinsic spatio-temporal correlations of incomplete traffic data. To this end, we propose M ask- a ware g raph i mputation Net work : MagiNet . Our method designs an adaptive mask spatio-temporal encoder to learn the latent representations of incomplete data, eliminating the reliance on pre-filling missing values. Furthermore, we devise a spatio-temporal decoder that stacks multiple blocks to capture the inherent spatial and temporal dependencies within incomplete traffic data, alleviating over-smoothed imputation. Extensive experiments demonstrate that our method outperforms state-of-the-art imputation methods on five real-world traffic datasets, yielding an average improvement of 4.31% in RMSE and 3.72% in MAPE under Missing Completely At Random (MCAR) pattern. Code is available at https://github.com/JeremyChou28/MagiNet .
- 6 June 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
Open AccessMagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making for Intelligent Transportation System (ITS). However, existing imputation methods generally perform zero pre-filling techniques to initialize missing values, introducing inevitable noise. Moreover, we observe prevalent over-smoothed interpolations, falling short in revealing the intrinsic spatio-temporal correlations of incomplete traffic data. To this end, we propose M ask- a ware g raph i mputation Net work : MagiNet . Our method designs an adaptive mask spatio-temporal encoder to learn the latent representations of incomplete data, eliminating the reliance on pre-filling missing values. Furthermore, we devise a spatio-temporal decoder that stacks multiple blocks to capture the inherent spatial and temporal dependencies within incomplete traffic data, alleviating over-smoothed imputation. Extensive experiments demonstrate that our method outperforms state-of-the-art imputation methods on five real-world traffic datasets, yielding an average improvement of 4.31% in RMSE and 3.72% in MAPE under Missing Completely At Random (MCAR) pattern. Code is available at https://github.com/JeremyChou28/MagiNet .
- Open Access
- 9 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (4) , 1-24
Multi-scale Traffic Pattern Bank for Cross-city Few-shot Traffic Forecasting
Traffic forecasting is crucial for intelligent transportation systems (ITS) , aiding in efficient resource allocation and effective traffic control. However, its effectiveness often relies heavily on abundant traffic data, while many cities lack sufficient data due to limited device support, posing a significant challenge for traffic forecasting. Recognizing this challenge, we have made a noteworthy observation: traffic patterns exhibit similarities across diverse cities. Building on this key insight, we propose a solution for the cross-city few-shot traffic forecasting problem called Multi-scale Traffic Pattern Bank (MTPB) . Primarily, MTPB initiates its learning process by leveraging data-rich source cities, effectively acquiring comprehensive traffic knowledge through a spatial-temporal-aware pre-training process. Subsequently, the framework employs advanced clustering techniques to systematically generate a multi-scale traffic pattern bank derived from the learned knowledge. Next, the traffic data of the data-scarce target city could query the traffic pattern bank, facilitating the aggregation of meta-knowledge. This meta-knowledge, in turn, assumes a pivotal role as a robust guide in subsequent processes involving graph reconstruction and forecasting. Empirical assessments conducted on real-world traffic datasets affirm the superior performance of MTPB, surpassing existing methods across various categories and exhibiting numerous attributes conducive to the advancement of cross-city few-shot forecasting methodologies. The code is available in https://github.com/zhyliu00/MTPB .
- 9 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 19 (4) , 1-24
Open AccessMulti-scale Traffic Pattern Bank for Cross-city Few-shot Traffic Forecasting
Traffic forecasting is crucial for intelligent transportation systems (ITS) , aiding in efficient resource allocation and effective traffic control. However, its effectiveness often relies heavily on abundant traffic data, while many cities lack sufficient data due to limited device support, posing a significant challenge for traffic forecasting. Recognizing this challenge, we have made a noteworthy observation: traffic patterns exhibit similarities across diverse cities. Building on this key insight, we propose a solution for the cross-city few-shot traffic forecasting problem called Multi-scale Traffic Pattern Bank (MTPB) . Primarily, MTPB initiates its learning process by leveraging data-rich source cities, effectively acquiring comprehensive traffic knowledge through a spatial-temporal-aware pre-training process. Subsequently, the framework employs advanced clustering techniques to systematically generate a multi-scale traffic pattern bank derived from the learned knowledge. Next, the traffic data of the data-scarce target city could query the traffic pattern bank, facilitating the aggregation of meta-knowledge. This meta-knowledge, in turn, assumes a pivotal role as a robust guide in subsequent processes involving graph reconstruction and forecasting. Empirical assessments conducted on real-world traffic datasets affirm the superior performance of MTPB, surpassing existing methods across various categories and exhibiting numerous attributes conducive to the advancement of cross-city few-shot forecasting methodologies. The code is available in https://github.com/zhyliu00/MTPB .
- 1 October 2024
- Published by Springer Nature
- p. 225-234
POI-Based Traffic Generation via Supervised Contrastive Learning on Reconstructed Graph
- 1 October 2024
- Published by Springer Nature
- p. 225-234
POI-Based Traffic Generation via Supervised Contrastive Learning on Reconstructed Graph
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1992-2002
Graph Data Condensation via Self-expressive Graph Structure Reconstruction
With the increasing demands of training graph neural networks (GNNs) on large-scale graphs, graph data condensation has emerged as a critical technique to relieve the storage and time costs during the training phase. It aims to condense the original large-scale graph to a much smaller synthetic graph while preserving the essential information necessary for efficiently training a downstream GNN. However, existing methods concentrate either on optimizing node features exclusively or endeavor to independently learn node features and the graph structure generator. They could not explicitly leverage the information of the original graph structure and failed to construct an interpretable graph structure for the synthetic dataset. To address these issues, we introduce a novel framework named Graph Data Condensation via Self-expressive Graph Structure Reconstruction (GCSR). Our method stands out by (1) explicitly incorporating the original graph structure into the condensing process and (2) capturing the nuanced interdependencies between the condensed nodes by reconstructing an interpretable self-expressive graph structure. Extensive experiments and comprehensive analysis validate the efficacy of the proposed method across diverse GNN models and datasets. Our code is available at https://github.com/zclzcl0223/GCSR.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1992-2002
Open AccessGraph Data Condensation via Self-expressive Graph Structure Reconstruction
With the increasing demands of training graph neural networks (GNNs) on large-scale graphs, graph data condensation has emerged as a critical technique to relieve the storage and time costs during the training phase. It aims to condense the original large-scale graph to a much smaller synthetic graph while preserving the essential information necessary for efficiently training a downstream GNN. However, existing methods concentrate either on optimizing node features exclusively or endeavor to independently learn node features and the graph structure generator. They could not explicitly leverage the information of the original graph structure and failed to construct an interpretable graph structure for the synthetic dataset. To address these issues, we introduce a novel framework named Graph Data Condensation via Self-expressive Graph Structure Reconstruction (GCSR). Our method stands out by (1) explicitly incorporating the original graph structure into the condensing process and (2) capturing the nuanced interdependencies between the condensed nodes by reconstructing an interpretable self-expressive graph structure. Extensive experiments and comprehensive analysis validate the efficacy of the proposed method across diverse GNN models and datasets. Our code is available at https://github.com/zclzcl0223/GCSR.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1980-1991
Dataset Condensation for Time Series Classification via Dual Domain Matching
Time series data has been demonstrated to be crucial in various research fields. The management of large quantities of time series data presents challenges in terms of deep learning tasks, particularly for training a deep neural network. Recently, a technique named Dataset Condensation has emerged as a solution to this problem. This technique generates a smaller synthetic dataset that has comparable performance to the full real dataset in downstream tasks such as classification. However, previous methods are primarily designed for image and graph datasets, and directly adapting them to the time series dataset leads to suboptimal performance due to their inability to effectively leverage the rich information inherent in time series data, particularly in the frequency domain. In this paper, we propose a novel framework named Dataset Condensation for Time Series Classification via Dual Domain Matching (CondTSC) which focuses on the time series classification dataset condensation task. Different from previous methods, our proposed framework aims to generate a condensed dataset that matches the surrogate objectives in both the time and frequency domains. Specifically, CondTSC incorporates multi-view data augmentation, dual domain training, and dual surrogate objectives to enhance the dataset condensation process in the time and frequency domains. Through extensive experiments, we demonstrate the effectiveness of our proposed framework, which outperforms other baselines and learns a condensed synthetic dataset that exhibits desirable characteristics such as conforming to the distribution of the original data.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1980-1991
Open AccessDataset Condensation for Time Series Classification via Dual Domain Matching
Time series data has been demonstrated to be crucial in various research fields. The management of large quantities of time series data presents challenges in terms of deep learning tasks, particularly for training a deep neural network. Recently, a technique named Dataset Condensation has emerged as a solution to this problem. This technique generates a smaller synthetic dataset that has comparable performance to the full real dataset in downstream tasks such as classification. However, previous methods are primarily designed for image and graph datasets, and directly adapting them to the time series dataset leads to suboptimal performance due to their inability to effectively leverage the rich information inherent in time series data, particularly in the frequency domain. In this paper, we propose a novel framework named Dataset Condensation for Time Series Classification via Dual Domain Matching (CondTSC) which focuses on the time series classification dataset condensation task. Different from previous methods, our proposed framework aims to generate a condensed dataset that matches the surrogate objectives in both the time and frequency domains. Specifically, CondTSC incorporates multi-view data augmentation, dual domain training, and dual surrogate objectives to enhance the dataset condensation process in the time and frequency domains. Through extensive experiments, we demonstrate the effectiveness of our proposed framework, which outperforms other baselines and learns a condensed synthetic dataset that exhibits desirable characteristics such as conforming to the distribution of the original data.
- 22 August 2024
- Published by Springer Nature
- p. 35-52
Frequency Enhanced Pre-training for Cross-City Few-shot Traffic Forecasting
- 22 August 2024
- Published by Springer Nature
- p. 35-52
Frequency Enhanced Pre-training for Cross-City Few-shot Traffic Forecasting
- Open Access
- 16 April 2024
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 15, 1346587
Tumor-derived extracellular vesicles regulate macrophage polarization: role and therapeutic perspectives
Extracellular vesicles (EVs) are important cell-to-cell communication mediators. This paper focuses on the regulatory role of tumor-derived EVs on macrophages. It aims to investigate the causes of tumor progression and therapeutic directions. Tumor-derived EVs can cause macrophages to shift to M1 or M2 phenotypes. This indicates they can alter the M1/M2 cell ratio and have pro-tumor and anti-inflammatory effects. This paper discusses several key points: first, the factors that stimulate macrophage polarization and the cytokines released as a result; second, an overview of EVs and the methods used to isolate them; third, how EVs from various cancer cell sources, such as hepatocellular carcinoma, colorectal carcinoma, lung carcinoma, breast carcinoma, and glioblastoma cell sources carcinoma, promote tumor development by inducing M2 polarization in macrophages; and fourth, how EVs from breast carcinoma, pancreatic carcinoma, lungs carcinoma, and glioblastoma cell sources carcinoma also contribute to tumor development by promoting M2 polarization in macrophages. Modified or sourced EVs from breast, pancreatic, and colorectal cancer can repolarize M2 to M1 macrophages. This exhibits anti-tumor activities and offers novel approaches for tumor treatment. Therefore, we discovered that macrophage polarization to either M1 or M2 phenotypes can regulate tumor development. This is based on the description of altering macrophage phenotypes by vesicle contents.
- 16 April 2024
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 15, 1346587
Open AccessTumor-derived extracellular vesicles regulate macrophage polarization: role and therapeutic perspectives
Extracellular vesicles (EVs) are important cell-to-cell communication mediators. This paper focuses on the regulatory role of tumor-derived EVs on macrophages. It aims to investigate the causes of tumor progression and therapeutic directions. Tumor-derived EVs can cause macrophages to shift to M1 or M2 phenotypes. This indicates they can alter the M1/M2 cell ratio and have pro-tumor and anti-inflammatory effects. This paper discusses several key points: first, the factors that stimulate macrophage polarization and the cytokines released as a result; second, an overview of EVs and the methods used to isolate them; third, how EVs from various cancer cell sources, such as hepatocellular carcinoma, colorectal carcinoma, lung carcinoma, breast carcinoma, and glioblastoma cell sources carcinoma, promote tumor development by inducing M2 polarization in macrophages; and fourth, how EVs from breast carcinoma, pancreatic carcinoma, lungs carcinoma, and glioblastoma cell sources carcinoma also contribute to tumor development by promoting M2 polarization in macrophages. Modified or sourced EVs from breast, pancreatic, and colorectal cancer can repolarize M2 to M1 macrophages. This exhibits anti-tumor activities and offers novel approaches for tumor treatment. Therefore, we discovered that macrophage polarization to either M1 or M2 phenotypes can regulate tumor development. This is based on the description of altering macrophage phenotypes by vesicle contents.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1451-1460
Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank
Traffic forecasting is a critical service in Intelligent Transportation Systems (ITS). Utilizing deep models to tackle this task relies heavily on data from traffic sensors or vehicle devices, while some cities might lack device support and thus have few available data. So, it is necessary to learn from data-rich cities and transfer the knowledge to data-scarce cities in order to improve the performance of traffic forecasting. To address this problem, we propose a cross-city few-shot traffic forecasting framework via Traffic Pattern Bank (TPB) due to that the traffic patterns are similar across cities. TPB utilizes a pre-trained traffic patch encoder to project raw traffic data from data-rich cities into high-dimensional space, from which a traffic pattern bank is generated through clustering. Then, the traffic data of the data-scarce city could query the traffic pattern bank and explicit relations between them are constructed. The metaknowledge is aggregated based on these relations and an adjacency matrix is constructed to guide a downstream spatial-temporal model in forecasting future traffic. The frequently used meta-training framework Reptile is adapted to find a better initial parameter for the learnable modules. Experiments on real-world traffic datasets show that TPB outperforms existing methods and demonstrates the effectiveness of our approach in cross-city few-shot traffic forecasting.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1451-1460
Open AccessCross-city Few-Shot Traffic Forecasting via Traffic Pattern Bank
Traffic forecasting is a critical service in Intelligent Transportation Systems (ITS). Utilizing deep models to tackle this task relies heavily on data from traffic sensors or vehicle devices, while some cities might lack device support and thus have few available data. So, it is necessary to learn from data-rich cities and transfer the knowledge to data-scarce cities in order to improve the performance of traffic forecasting. To address this problem, we propose a cross-city few-shot traffic forecasting framework via Traffic Pattern Bank (TPB) due to that the traffic patterns are similar across cities. TPB utilizes a pre-trained traffic patch encoder to project raw traffic data from data-rich cities into high-dimensional space, from which a traffic pattern bank is generated through clustering. Then, the traffic data of the data-scarce city could query the traffic pattern bank and explicit relations between them are constructed. The metaknowledge is aggregated based on these relations and an adjacency matrix is constructed to guide a downstream spatial-temporal model in forecasting future traffic. The frequently used meta-training framework Reptile is adapted to find a better initial parameter for the learnable modules. Experiments on real-world traffic datasets show that TPB outperforms existing methods and demonstrates the effectiveness of our approach in cross-city few-shot traffic forecasting.
- 17 September 2023
- Published by Springer Nature
- p. 174-191
FDTI: Fine-Grained Deep Traffic Inference with Roadnet-Enriched Graph
- 17 September 2023
- Published by Springer Nature
- p. 174-191
FDTI: Fine-Grained Deep Traffic Inference with Roadnet-Enriched Graph