Yubao Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yubao Liu has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Weiyang Kong
Sun Yat-Sen University Guangzhou China
6 shared publications Genan Dai
Sun Yat-sen University
4 shared publications- Raymond Chi-Wing Wong
The Hong Kong University of Science and Technology, Hong Kong, Hong Kong
4 shared publications - Sen Zhang
Sun Yat-Sen University Guangzhou China
4 shared publications - Youming Ge
Sun Yat Sen University, Guangzhou, China
3 shared publications Zitong Chen
Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China
3 shared publications
Latest Publications
- 30 January 2026
- Published by Springer Nature
- p. 703-716
Reinforcement Learning-Enhanced Adaptive Buffer Replacement for Modern Databases
- 30 January 2026
- Published by Springer Nature
- p. 703-716
Reinforcement Learning-Enhanced Adaptive Buffer Replacement for Modern Databases
- 22 July 2025
- Published by Springer Nature
- p. 120-131
IDMixer: Decomposition Spatial-Temporal Identity for Traffic Flow Forecasting
- 22 July 2025
- Published by Springer Nature
- p. 120-131
IDMixer: Decomposition Spatial-Temporal Identity for Traffic Flow Forecasting
- Open Access
- 27 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (1) , 1-19
Tucker Decomposition-Enhanced Dynamic Graph Convolutional Networks for Crowd Flows Prediction
Crowd flows prediction is an important problem for traffic management and public safety. Graph Convolutional Network (GCN), known for its ability to effectively capture and utilize topological information, has demonstrated significant advancements in addressing this problem. However, GCN-based models were often based on predefined crowd-flow graphs via historical movement behaviors of human beings and traffic vehicles, which ignored the abnormal changes in crowd flows. In this study, we propose a multi-scale fusion GCN-based framework with Tucker decomposition named mTDNet to enhance dynamic GCN for crowd flows prediction. Following the paradigm of extant methods, we also employ the predefined crowd-flow graphs as a part of mTDNet to effectively capture the historical movement behaviors of crowd flows. To capture the abnormal changes, we propose a Tucker decomposition-based network with the product of the adjacency matrix of historical movement pattern graphs and an Adaptive Learning Tensor ( ALT ) by reconstructing the crowd flows. Particularly, we utilize the Tucker decomposition scheme to decompose ALT , which enhances the dynamic learning of graph structures, allowing for effective capturing of the dynamic changes in crowd flow, including abnormal changes. Furthermore, a multi-scale 3DGCN is utilized to mine and fuse the multi-scale spatio-temporal information from crowd flows, to further boost the mTDNet prediction performance. Experiments conducted on two real-world datasets showed that the proposed mTDNet surpasses other crowd flow prediction methods.
- 27 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 16 (1) , 1-19
Open AccessTucker Decomposition-Enhanced Dynamic Graph Convolutional Networks for Crowd Flows Prediction
Crowd flows prediction is an important problem for traffic management and public safety. Graph Convolutional Network (GCN), known for its ability to effectively capture and utilize topological information, has demonstrated significant advancements in addressing this problem. However, GCN-based models were often based on predefined crowd-flow graphs via historical movement behaviors of human beings and traffic vehicles, which ignored the abnormal changes in crowd flows. In this study, we propose a multi-scale fusion GCN-based framework with Tucker decomposition named mTDNet to enhance dynamic GCN for crowd flows prediction. Following the paradigm of extant methods, we also employ the predefined crowd-flow graphs as a part of mTDNet to effectively capture the historical movement behaviors of crowd flows. To capture the abnormal changes, we propose a Tucker decomposition-based network with the product of the adjacency matrix of historical movement pattern graphs and an Adaptive Learning Tensor ( ALT ) by reconstructing the crowd flows. Particularly, we utilize the Tucker decomposition scheme to decompose ALT , which enhances the dynamic learning of graph structures, allowing for effective capturing of the dynamic changes in crowd flow, including abnormal changes. Furthermore, a multi-scale 3DGCN is utilized to mine and fuse the multi-scale spatio-temporal information from crowd flows, to further boost the mTDNet prediction performance. Experiments conducted on two real-world datasets showed that the proposed mTDNet surpasses other crowd flow prediction methods.
- Top Cited PapersOpen Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (8) , 8627-8635
Spatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting
Traffic flow forecasting is a classical spatio-temporal data mining problem with many real-world applications. Recently, various methods based on Graph Neural Networks (GNN) have been proposed for the problem and achieved impressive prediction performance. However, we argue that the majority of existing methods disregarding the importance of certain nodes (referred to as pivotal nodes) that naturally exhibit extensive connections with multiple other nodes. Predicting on pivotal nodes poses a challenge due to their complex spatio-temporal dependencies compared to other nodes. In this paper, we propose a novel GNN-based method called Spatio-Temporal Pivotal Graph Neural Networks (STPGNN) to address the above limitation. We introduce a pivotal node identification module for identifying pivotal nodes. We propose a novel pivotal graph convolution module, enabling precise capture of spatio-temporal dependencies centered around pivotal nodes. Moreover, we propose a parallel framework capable of extracting spatio-temporal traffic features on both pivotal and non-pivotal nodes. Experiments on seven real-world traffic datasets verify our proposed method's effectiveness and efficiency compared to state-of-the-art baselines.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (8) , 8627-8635
Top Cited PapersOpen AccessSpatio-Temporal Pivotal Graph Neural Networks for Traffic Flow Forecasting
Traffic flow forecasting is a classical spatio-temporal data mining problem with many real-world applications. Recently, various methods based on Graph Neural Networks (GNN) have been proposed for the problem and achieved impressive prediction performance. However, we argue that the majority of existing methods disregarding the importance of certain nodes (referred to as pivotal nodes) that naturally exhibit extensive connections with multiple other nodes. Predicting on pivotal nodes poses a challenge due to their complex spatio-temporal dependencies compared to other nodes. In this paper, we propose a novel GNN-based method called Spatio-Temporal Pivotal Graph Neural Networks (STPGNN) to address the above limitation. We introduce a pivotal node identification module for identifying pivotal nodes. We propose a novel pivotal graph convolution module, enabling precise capture of spatio-temporal dependencies centered around pivotal nodes. Moreover, we propose a parallel framework capable of extracting spatio-temporal traffic features on both pivotal and non-pivotal nodes. Experiments on seven real-world traffic datasets verify our proposed method's effectiveness and efficiency compared to state-of-the-art baselines.
- 22 January 2024
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 18 (3) , 1-11
Unsupervised social network embedding via adaptive specific mappings
- 22 January 2024
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 18 (3) , 1-11
Unsupervised social network embedding via adaptive specific mappings
- 15 November 2023
- Published by Springer Nature
- p. 56-68
Modeling User’s Neutral Feedback in Conversational Recommendation
- 15 November 2023
- Published by Springer Nature
- p. 56-68
Modeling User’s Neutral Feedback in Conversational Recommendation
- 27 October 2023
- Published by Springer Nature
- p. 140-158
Disentangled Contrastive Learning for Knowledge-Aware Recommender System
- 27 October 2023
- Published by Springer Nature
- p. 140-158
Disentangled Contrastive Learning for Knowledge-Aware Recommender System
- Open Access
- 9 September 2023
- Published by Springer Nature in Data Science and Engineering
- Vol. 8 (4) , 368-384
An Efficient Keywords Search in Temporal Social Networks
With the increasing of requirements from many aspects, various queries and analyses arise focusing on social network. Time is a common and necessary dimension in various types of social networks. Social networks with time information are called temporal social networks, in which time information can be the time when a user sends message to another user. Keywords search in temporal social networks consists of finding relationships between a group users that has a set of query labels and is valid within the query time interval. It provides assistance in social network analysis, classification of social network users, community detection, etc. However, the existing methods have limitations in solving temporal social network keyword search problems. We propose a basic algorithm, the discrete timestamp algorithm, with the intention of turning the problem into a traditional keyword search on social networks. We also propose an approximative algorithm based on the discrete timestamp algorithm, but it still suffers from the traditional algorithms’ low efficiency. To further improve the performance, we propose a new algorithm based on dynamic programming to solve the keyword search in temporal social network. The main idea is to extend a vertex into a solution by edge-growth operation and tree-merger operation. We also propose two powerful pruning techniques to reduce the intermediate results during the extension. Additionally, all of the algorithms we proposed are capable of handling a variety of ranking functions, and all of them can be made to conform to top-N keyword querying. The efficiency and effectiveness of the proposed algorithms are verified through extensive empirical studies.
- 9 September 2023
- Published by Springer Nature in Data Science and Engineering
- Vol. 8 (4) , 368-384
Open AccessAn Efficient Keywords Search in Temporal Social Networks
With the increasing of requirements from many aspects, various queries and analyses arise focusing on social network. Time is a common and necessary dimension in various types of social networks. Social networks with time information are called temporal social networks, in which time information can be the time when a user sends message to another user. Keywords search in temporal social networks consists of finding relationships between a group users that has a set of query labels and is valid within the query time interval. It provides assistance in social network analysis, classification of social network users, community detection, etc. However, the existing methods have limitations in solving temporal social network keyword search problems. We propose a basic algorithm, the discrete timestamp algorithm, with the intention of turning the problem into a traditional keyword search on social networks. We also propose an approximative algorithm based on the discrete timestamp algorithm, but it still suffers from the traditional algorithms’ low efficiency. To further improve the performance, we propose a new algorithm based on dynamic programming to solve the keyword search in temporal social network. The main idea is to extend a vertex into a solution by edge-growth operation and tree-merger operation. We also propose two powerful pruning techniques to reduce the intermediate results during the extension. Additionally, all of the algorithms we proposed are capable of handling a variety of ranking functions, and all of them can be made to conform to top-N keyword querying. The efficiency and effectiveness of the proposed algorithms are verified through extensive empirical studies.
- 14 April 2023
- Published by Springer Nature
- p. 563-573
Revisiting Positive and Negative Samples in Variational Autoencoders for Top-N Recommendation
- 14 April 2023
- Published by Springer Nature
- p. 563-573
Revisiting Positive and Negative Samples in Variational Autoencoders for Top-N Recommendation
- Open Access
- 1 January 2023
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2023 (1)
An Efficient Dynamic Programming Algorithm for Finding Group Steiner Trees in Temporal Graphs
The computation of a group Steiner tree (GST) in various types of graph networks, such as social network and transportation network, is a fundamental graph problem in graphs, with important applications. In these graphs, time is a common and necessary dimension, for example, time information in social network can be the time when a user sends a message to another user. Graphs with time information can be called temporal graphs. However, few studies have been conducted on GST in terms of temporal graphs. This study analyzes the computation of GST for temporal graphs, i.e., the computation of temporal GST (TGST), which is shown to be an NP‐hard problem. We propose an efficient solution based on a dynamic programming algorithm for our problem. This study adopts new optimization techniques, including graph simplification, state pruning, and A∗ search, are adopted to dramatically reduce the algorithm search space. Moreover, we consider three extensions for our problem, namely the TGST with unspecified tree root, the progressive search of TGST, and the top‐N search of TGST. Results of the experimental study performed on real temporal networks verify the efficiency and effectiveness of our algorithms.
- 1 January 2023
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 2023 (1)
Open AccessAn Efficient Dynamic Programming Algorithm for Finding Group Steiner Trees in Temporal Graphs
The computation of a group Steiner tree (GST) in various types of graph networks, such as social network and transportation network, is a fundamental graph problem in graphs, with important applications. In these graphs, time is a common and necessary dimension, for example, time information in social network can be the time when a user sends a message to another user. Graphs with time information can be called temporal graphs. However, few studies have been conducted on GST in terms of temporal graphs. This study analyzes the computation of GST for temporal graphs, i.e., the computation of temporal GST (TGST), which is shown to be an NP‐hard problem. We propose an efficient solution based on a dynamic programming algorithm for our problem. This study adopts new optimization techniques, including graph simplification, state pruning, and A∗ search, are adopted to dramatically reduce the algorithm search space. Moreover, we consider three extensions for our problem, namely the TGST with unspecified tree root, the progressive search of TGST, and the top‐N search of TGST. Results of the experimental study performed on real temporal networks verify the efficiency and effectiveness of our algorithms.