Zhengyang Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhengyang Zhou has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Yang Wang
University of Science and Technology of China, Hefei, China
4 shared publications Kun Wang
University of Science and Technology of China
3 shared publications- Pengkun Wang
University of Science and Technology of China, Hefei, China
3 shared publications - Yuxuan Liang
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
3 shared publications Binwu Wang
2 shared publicationsKang Luo
Hong Kong University of Science and Technology (Guangzhou)
2 shared publications
Latest Publications
- 6 November 2026
- Published by Springer Nature
- p. 158-173
PriST-Init: Privacy-Aware Spatio-Temporal Framework for Cold-Start Traffic Forecasting
- 6 November 2026
- Published by Springer Nature
- p. 158-173
PriST-Init: Privacy-Aware Spatio-Temporal Framework for Cold-Start Traffic Forecasting
- 7 September 2026
- Published by Springer Nature
- p. 573-589
TVSRNet: A Unified Framework for Multivariate Time-Series Classification via Triple-View Sparsified Routing
- 7 September 2026
- Published by Springer Nature
- p. 573-589
TVSRNet: A Unified Framework for Multivariate Time-Series Classification via Triple-View Sparsified Routing
- Open Access
A General ReLearner: Empowering Spatiotemporal Prediction by Re-learning Input-label Residual
Prevailing spatiotemporal prediction models typically operate under a forward (unidirectional) learning paradigm, in which models extract spatiotemporal features from historical observation input and map them to target spatiotemporal space for future forecasting (label). However, these models frequently exhibit suboptimal performance when spatiotemporal discrepancies exist between inputs and labels, for instance, when nodes with similar time-series inputs manifest distinct future labels, or vice versa. To address this limitation, we propose explicitly incorporating label features during the training phase. Specifically, we introduce the Spatiotemporal Residual Theorem, which generalizes the conventional unidirectional spatiotemporal prediction paradigm into a bidirectional learning framework. Building upon this theoretical foundation, we design an universal module, termed ReLearner, which seamlessly augments Spatiotemporal Neural Networks (STNNs) with a bidirectional learning capability via an auxiliary inverse learning process. In this process, the model relearns the spatiotemporal feature residuals between input data and future data. The proposed ReLearner comprises two critical components: (1) a Residual Learning Module, designed to effectively disentangle spatiotemporal feature discrepancies between input and label representations; and (2) a Residual Smoothing Module, employed to smooth residual terms and facilitate stable convergence. Extensive experiments conducted on 11 real-world datasets across 14 backbone models demonstrate that ReLearner significantly enhances the predictive performance of existing STNNs.Our code is available on GitHub.
Open AccessA General ReLearner: Empowering Spatiotemporal Prediction by Re-learning Input-label Residual
Prevailing spatiotemporal prediction models typically operate under a forward (unidirectional) learning paradigm, in which models extract spatiotemporal features from historical observation input and map them to target spatiotemporal space for future forecasting (label). However, these models frequently exhibit suboptimal performance when spatiotemporal discrepancies exist between inputs and labels, for instance, when nodes with similar time-series inputs manifest distinct future labels, or vice versa. To address this limitation, we propose explicitly incorporating label features during the training phase. Specifically, we introduce the Spatiotemporal Residual Theorem, which generalizes the conventional unidirectional spatiotemporal prediction paradigm into a bidirectional learning framework. Building upon this theoretical foundation, we design an universal module, termed ReLearner, which seamlessly augments Spatiotemporal Neural Networks (STNNs) with a bidirectional learning capability via an auxiliary inverse learning process. In this process, the model relearns the spatiotemporal feature residuals between input data and future data. The proposed ReLearner comprises two critical components: (1) a Residual Learning Module, designed to effectively disentangle spatiotemporal feature discrepancies between input and label representations; and (2) a Residual Smoothing Module, employed to smooth residual terms and facilitate stable convergence. Extensive experiments conducted on 11 real-world datasets across 14 backbone models demonstrate that ReLearner significantly enhances the predictive performance of existing STNNs.Our code is available on GitHub.
- 8 October 2025
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 67 (12) , 12759-12782
Soft causal learning for generalized molecule property prediction: An environment modeling perspective
- 8 October 2025
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 67 (12) , 12759-12782
Soft causal learning for generalized molecule property prediction: An environment modeling perspective
- Open Access
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 3, 2224-2232
DPMamba: Distillation Prompt Mamba for Multimodal Remote Sensing Image Classification with Missing Modalities
Multimodal remote sensing image classification (RSIC) has emerged as a key focus in Earth observation, driven by its capacity to extract complementary information from diverse sources. Existing methods struggle with modality absence caused by weather or equipment failures, leading to performance degradation. As a solution, knowledge distillation-based methods train student networks (SN) using a full-modality teacher, but they usually require training separate SN for each modality absence scenario, increasing complexity. To this end, we propose a unified Distillation Prompt Mamba (DPMamba) framework for multimodal RSIC with missing modalities. DPMamba leverages knowledge distillation in a shared text semantic space to optimize learnable prompts, transforming them from ``placeholder" to ``adaptation" states by enriching missing modality information with full-modality knowledge. To achieve this, we focus on two main aspects: first, we propose a new modality-aware Mamba for dynamically and hierarchically extracting cross-modality interactive features, providing richer, contextually relevant representations for backpropagation-based optimization of prompts; and second, we introduce a novel text-bridging distillation method to efficiently transfer full-modality knowledge, guiding the inclusion of missing modality information into prompts. Extensive evaluations demonstrate the effectiveness and robustness of the proposed DPMamba.
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 3, 2224-2232
Open AccessDPMamba: Distillation Prompt Mamba for Multimodal Remote Sensing Image Classification with Missing Modalities
Multimodal remote sensing image classification (RSIC) has emerged as a key focus in Earth observation, driven by its capacity to extract complementary information from diverse sources. Existing methods struggle with modality absence caused by weather or equipment failures, leading to performance degradation. As a solution, knowledge distillation-based methods train student networks (SN) using a full-modality teacher, but they usually require training separate SN for each modality absence scenario, increasing complexity. To this end, we propose a unified Distillation Prompt Mamba (DPMamba) framework for multimodal RSIC with missing modalities. DPMamba leverages knowledge distillation in a shared text semantic space to optimize learnable prompts, transforming them from ``placeholder" to ``adaptation" states by enriching missing modality information with full-modality knowledge. To achieve this, we focus on two main aspects: first, we propose a new modality-aware Mamba for dynamically and hierarchically extracting cross-modality interactive features, providing richer, contextually relevant representations for backpropagation-based optimization of prompts; and second, we introduce a novel text-bridging distillation method to efficiently transfer full-modality knowledge, guiding the inclusion of missing modality information into prompts. Extensive evaluations demonstrate the effectiveness and robustness of the proposed DPMamba.
- Open Access
Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning
Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial context, leading to the acquisition of spurious correlations and limited generalization capabilities. To bridge this gap, we initially formulate a Structural Causal Model (SCM) to decipher the trajectory representation learning process from a causal perspective. Building upon the SCM, we further present a Trajectory modeling framework (TrajCL) based on Causal Learning, which leverages the backdoor adjustment theory as an intervention tool to eliminate the spurious correlations between geospatial context and trajectories. Extensive experiments on two real-world datasets verify that TrajCL markedly enhances performance in trajectory classification tasks while showcasing superior generalization and interpretability.
Open AccessTowards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning
Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial context, leading to the acquisition of spurious correlations and limited generalization capabilities. To bridge this gap, we initially formulate a Structural Causal Model (SCM) to decipher the trajectory representation learning process from a causal perspective. Building upon the SCM, we further present a Trajectory modeling framework (TrajCL) based on Causal Learning, which leverages the backdoor adjustment theory as an intervention tool to eliminate the spurious correlations between geospatial context and trajectories. Extensive experiments on two real-world datasets verify that TrajCL markedly enhances performance in trajectory classification tasks while showcasing superior generalization and interpretability.
- Open 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 (14) , 15906-15914
Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community. Many recent studies have concentrated on meticulously reconciling various advantages, leading to designed models that are neither simple nor practical. To address this issue, this paper presents a systematic study on existing shortcomings faced by off-the-shelf models, including lack of local fidelity, poor prediction performance over long time-steps, low scalability, and inefficiency. To systematically address the aforementioned problems, we propose an EarthFarseer, a concise framework that combines parallel local convolutions and global Fourier-based transformer architectures, enabling dynamically capture the local-global spatial interactions and dependencies. EarthFarseer also incorporates a multi-scale fully convolutional and Fourier architectures to efficiently and effectively capture the temporal evolution. Our proposal demonstrates strong adaptability across various tasks and datasets, with fast convergence and better local fidelity in long time-steps predictions. Extensive experiments and visualizations over eight human society physical and natural physical datasets demonstrates the state-of-the-art performance of EarthFarseer. We release our code at https://github.com/easylearningscores/EarthFarseer.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (14) , 15906-15914
Open AccessEarthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community. Many recent studies have concentrated on meticulously reconciling various advantages, leading to designed models that are neither simple nor practical. To address this issue, this paper presents a systematic study on existing shortcomings faced by off-the-shelf models, including lack of local fidelity, poor prediction performance over long time-steps, low scalability, and inefficiency. To systematically address the aforementioned problems, we propose an EarthFarseer, a concise framework that combines parallel local convolutions and global Fourier-based transformer architectures, enabling dynamically capture the local-global spatial interactions and dependencies. EarthFarseer also incorporates a multi-scale fully convolutional and Fourier architectures to efficiently and effectively capture the temporal evolution. Our proposal demonstrates strong adaptability across various tasks and datasets, with fast convergence and better local fidelity in long time-steps predictions. Extensive experiments and visualizations over eight human society physical and natural physical datasets demonstrates the state-of-the-art performance of EarthFarseer. We release our code at https://github.com/easylearningscores/EarthFarseer.
- Open 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) , 9089-9097
Towards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective
With the progress of urban transportation systems, a significant amount of high-quality traffic data is continuously collected through streaming manners, which has propelled the prosperity of the field of spatial-temporal graph prediction. In this paper, rather than solely focusing on designing powerful models for static graphs, we shift our focus to spatial-temporal graph prediction in the dynamic scenario, which involves a continuously expanding and evolving underlying graph. To address inherent challenges, a decoupled learning framework (DLF) is proposed in this paper, which consists of a spatial-temporal graph learning network (DSTG) with a specialized decoupling training strategy. Incorporating inductive biases of time-series structures, DSTG can interpret time dependencies into latent trend and seasonal terms. To enable prompt adaptation to the evolving distribution of the dynamic graph, our decoupling training strategy is devised to iteratively update these two types of patterns. Specifically, for learning seasonal patterns, we conduct thorough training for the model using a long time series (e.g., three months of data). To enhance the learning ability of the model, we also introduce the masked auto-encoding mechanism. During this period, we frequently update trend patterns to expand new information from dynamic graphs. Considering both effectiveness and efficiency, we develop a subnet sampling strategy to select a few representative nodes for fine-tuning the weights of the model. These sampled nodes cover unseen patterns and previously learned patterns. Experiments on dynamic spatial-temporal graph datasets further demonstrate the competitive performance, superior efficiency, and strong scalability of the proposed framework.
- 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) , 9089-9097
Open AccessTowards Dynamic Spatial-Temporal Graph Learning: A Decoupled Perspective
With the progress of urban transportation systems, a significant amount of high-quality traffic data is continuously collected through streaming manners, which has propelled the prosperity of the field of spatial-temporal graph prediction. In this paper, rather than solely focusing on designing powerful models for static graphs, we shift our focus to spatial-temporal graph prediction in the dynamic scenario, which involves a continuously expanding and evolving underlying graph. To address inherent challenges, a decoupled learning framework (DLF) is proposed in this paper, which consists of a spatial-temporal graph learning network (DSTG) with a specialized decoupling training strategy. Incorporating inductive biases of time-series structures, DSTG can interpret time dependencies into latent trend and seasonal terms. To enable prompt adaptation to the evolving distribution of the dynamic graph, our decoupling training strategy is devised to iteratively update these two types of patterns. Specifically, for learning seasonal patterns, we conduct thorough training for the model using a long time series (e.g., three months of data). To enhance the learning ability of the model, we also introduce the masked auto-encoding mechanism. During this period, we frequently update trend patterns to expand new information from dynamic graphs. Considering both effectiveness and efficiency, we develop a subnet sampling strategy to select a few representative nodes for fine-tuning the weights of the model. These sampled nodes cover unseen patterns and previously learned patterns. Experiments on dynamic spatial-temporal graph datasets further demonstrate the competitive performance, superior efficiency, and strong scalability of the proposed framework.
- Open 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 (1) , 401-409
NondBREM: Nondeterministic Offline Reinforcement Learning for Large-Scale Order Dispatching
One of the most important tasks in ride-hailing is order dispatching, i.e., assigning unserved orders to available drivers. Recent order dispatching has achieved a significant improvement due to the advance of reinforcement learning, which has been approved to be able to effectively address sequential decision-making problems like order dispatching. However, most existing reinforcement learning methods require agents to learn the optimal policy by interacting with environments online, which is challenging or impractical for real-world deployment due to high costs or safety concerns. For example, due to the spatiotemporally unbalanced supply and demand, online reinforcement learning-based order dispatching may significantly impact the revenue of the ride-hailing platform and passenger experience during the policy learning period. Hence, in this work, we develop an offline deep reinforcement learning framework called NondBREM for large-scale order dispatching, which learns policy from only the accumulated logged data to avoid costly and unsafe interactions with the environment. In NondBREM, a Nondeterministic Batch-Constrained Q-learning (NondBCQ) module is developed to reduce the algorithm extrapolation error and a Random Ensemble Mixture (REM) module that integrates multiple value networks with multi-head networks is utilized to improve the model generalization and robustness. Extensive experiments on large-scale real-world ride-hailing datasets show the superiority of our design.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (1) , 401-409
Open AccessNondBREM: Nondeterministic Offline Reinforcement Learning for Large-Scale Order Dispatching
One of the most important tasks in ride-hailing is order dispatching, i.e., assigning unserved orders to available drivers. Recent order dispatching has achieved a significant improvement due to the advance of reinforcement learning, which has been approved to be able to effectively address sequential decision-making problems like order dispatching. However, most existing reinforcement learning methods require agents to learn the optimal policy by interacting with environments online, which is challenging or impractical for real-world deployment due to high costs or safety concerns. For example, due to the spatiotemporally unbalanced supply and demand, online reinforcement learning-based order dispatching may significantly impact the revenue of the ride-hailing platform and passenger experience during the policy learning period. Hence, in this work, we develop an offline deep reinforcement learning framework called NondBREM for large-scale order dispatching, which learns policy from only the accumulated logged data to avoid costly and unsafe interactions with the environment. In NondBREM, a Nondeterministic Batch-Constrained Q-learning (NondBCQ) module is developed to reduce the algorithm extrapolation error and a Random Ensemble Mixture (REM) module that integrates multiple value networks with multi-head networks is utilized to improve the model generalization and robustness. Extensive experiments on large-scale real-world ride-hailing datasets show the superiority of our design.