Pengkun Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Pengkun Wang has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Yang Wang
University of Science and Technology of China, Hefei, China
27 shared publications - Xu Wang
University of Science and Technology of China, Hefei, China
21 shared publications - Zhengyang Zhou
University of science and Technology of China (USTC)
15 shared publications - Binwu Wang
University of Science and Technology of China, Hefei, China
14 shared publications - Yudong Zhang
University of Science and Technology of China, Heifei, CHINA
13 shared publications - Lei Bai
Shanghai AI Laborotory, Shanghai, China
7 shared publications
Latest Publications
- 17 September 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (10) , 431
LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models
- 17 September 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (10) , 431
LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models
- 8 August 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (8) , 386
ManiDream: Manifold Completion via Prototype-Anchored Dreaming for Long-Tailed Visual Recognition
- 8 August 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134  (8) , 386
ManiDream: Manifold Completion via Prototype-Anchored Dreaming for Long-Tailed Visual Recognition
- 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.
- Open Access
Rethinking Crystal Symmetry Prediction: A Decoupled Perspective
Efficiently and accurately determining the symmetry is a crucial step in the structural analysis of crystalline materials. Existing methods usually mindlessly apply deep learning models while ignoring the underlying chemical rules. More importantly, experiments show that they face a serious sub-property confusion SPC problem. To address the above challenges, from a decoupled perspective, we introduce the XRDecoupler framework, a problem-solving arsenal specifically designed to tackle the SPC problem. Imitating the thinking process of chemists, we innovatively incorporate multidimensional crystal symmetry information as superclass guidance to ensure that the model's prediction process aligns with chemical intuition. We further design a hierarchical PXRD pattern learning model and a multi-objective optimization approach to achieve high-quality representation and balanced optimization. Comprehensive evaluations on three mainstream databases (e.g., CCDC, CoREMOF, and InorganicData) demonstrate that XRDecoupler excels in performance, interpretability, and generalization.
Open AccessRethinking Crystal Symmetry Prediction: A Decoupled Perspective
Efficiently and accurately determining the symmetry is a crucial step in the structural analysis of crystalline materials. Existing methods usually mindlessly apply deep learning models while ignoring the underlying chemical rules. More importantly, experiments show that they face a serious sub-property confusion SPC problem. To address the above challenges, from a decoupled perspective, we introduce the XRDecoupler framework, a problem-solving arsenal specifically designed to tackle the SPC problem. Imitating the thinking process of chemists, we innovatively incorporate multidimensional crystal symmetry information as superclass guidance to ensure that the model's prediction process aligns with chemical intuition. We further design a hierarchical PXRD pattern learning model and a multi-objective optimization approach to achieve high-quality representation and balanced optimization. Comprehensive evaluations on three mainstream databases (e.g., CCDC, CoREMOF, and InorganicData) demonstrate that XRDecoupler excels in performance, interpretability, and generalization.
- 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 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 4, 3171-3179
Causal Learning Meet Covariates: Empowering Lightweight and Effective Nationwide Air Quality Forecasting
Air quality prediction plays a crucial role in the development of smart cities, garnering significant attention from both academia and industry. Current air quality prediction models encounter two major limitations: their high computational complexity limits scalability to nationwide datasets, and they often regard weather covariates as optional auxiliary information. In reality, weather covariates can have a substantial impact on air quality indices (AQI), exhibiting a significant causal association. In this paper, we first present a nationwide air quality dataset to address the lack of open-source, large-scale datasets in this field. Then we propose a causal learning model, CauAir, for air quality prediction that harnesses the powerful representation capabilities of the Transformer to explicitly model the causal association between weather covariates and AQI. To address the high complexity of traditional Transformers, we design CachLormer, which features two key innovations: a simplified architecture with redundant components removed, and a cache-attention mechanism that employs learnable embeddings for perceiving causal association between AQI and weather covariates in a coarsegrained perspective. We use information theory to illustrate the superiority of the proposed model. Finally, experimental results on three datasets with 28 as the baseline demonstrate that our model achieves competitive performance, while maintaining high training efficiency and low memory consumption. The source code is available at CauAir Official Repository.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 4, 3171-3179
Open AccessCausal Learning Meet Covariates: Empowering Lightweight and Effective Nationwide Air Quality Forecasting
Air quality prediction plays a crucial role in the development of smart cities, garnering significant attention from both academia and industry. Current air quality prediction models encounter two major limitations: their high computational complexity limits scalability to nationwide datasets, and they often regard weather covariates as optional auxiliary information. In reality, weather covariates can have a substantial impact on air quality indices (AQI), exhibiting a significant causal association. In this paper, we first present a nationwide air quality dataset to address the lack of open-source, large-scale datasets in this field. Then we propose a causal learning model, CauAir, for air quality prediction that harnesses the powerful representation capabilities of the Transformer to explicitly model the causal association between weather covariates and AQI. To address the high complexity of traditional Transformers, we design CachLormer, which features two key innovations: a simplified architecture with redundant components removed, and a cache-attention mechanism that employs learnable embeddings for perceiving causal association between AQI and weather covariates in a coarsegrained perspective. We use information theory to illustrate the superiority of the proposed model. Finally, experimental results on three datasets with 28 as the baseline demonstrate that our model achieves competitive performance, while maintaining high training efficiency and low memory consumption. The source code is available at CauAir Official Repository.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24  (11) , 11972-11986
MobiMixer: A Multi-Scale Spatiotemporal Mixing Model for Mobile Traffic Prediction
Understanding mobile traffic data and predicting future trends are essential for wireless operators and service providers to allocate resources efficiently and manage energy effectively. Despite the strong performance of existing models, accurately forecasting mobile traffic remains a challenge due to limited spatial and temporal modeling capabilities and high computational complexity. This paper introduces MobiMixer, a lightweight and efficient multi-scale spatiotemporal mixing model. Its core concept is to integrate multi-scale information from both spatial and temporal dimensions to improve performance on mobile traffic data. We develop a hierarchical interaction module that incorporates super nodes to enable global high-level feature interactions among nodes with common patterns. Additionally, we employ a dynamic time warping strategy to decouple mobile traffic sequences into stable and seasonal components, which are then modeled at different scales using a multi-scale temporal mixing module. We conduct extensive experiments on mobile traffic datasets collected from four international cities. Compared with 21 state-of-the-art benchmark models, MobiMixer demonstrates highly competitive performance, achieving a maximum improvement of 48.49% on the Milan mobile dataset. The model achieves an improvement in training efficiency of up to 10.69 times and reduces memory usage by 33.01%.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24  (11) , 11972-11986
MobiMixer: A Multi-Scale Spatiotemporal Mixing Model for Mobile Traffic Prediction
Understanding mobile traffic data and predicting future trends are essential for wireless operators and service providers to allocate resources efficiently and manage energy effectively. Despite the strong performance of existing models, accurately forecasting mobile traffic remains a challenge due to limited spatial and temporal modeling capabilities and high computational complexity. This paper introduces MobiMixer, a lightweight and efficient multi-scale spatiotemporal mixing model. Its core concept is to integrate multi-scale information from both spatial and temporal dimensions to improve performance on mobile traffic data. We develop a hierarchical interaction module that incorporates super nodes to enable global high-level feature interactions among nodes with common patterns. Additionally, we employ a dynamic time warping strategy to decouple mobile traffic sequences into stable and seasonal components, which are then modeled at different scales using a multi-scale temporal mixing module. We conduct extensive experiments on mobile traffic datasets collected from four international cities. Compared with 21 state-of-the-art benchmark models, MobiMixer demonstrates highly competitive performance, achieving a maximum improvement of 48.49% on the Milan mobile dataset. The model achieves an improvement in training efficiency of up to 10.69 times and reduces memory usage by 33.01%.
- Open Access
Spatiotemporal Causal Decoupling Model for Air Quality Forecasting
Due to the profound impact of air pollution on human health, livelihoods, and economic development, air quality forecasting is of paramount significance. Initially, we employ the causal graph method to scrutinize the constraints of existing research in comprehensively modeling the causal relationships between the air quality index (AQI) and meteorological features. In order to enhance prediction accuracy, we introduce a novel air quality forecasting model, AirCade, which incorporates a causal decoupling approach. AirCade leverages a spatiotemporal module in conjunction with knowledge embedding techniques to capture the internal dynamics of AQI. Subsequently, a causal decoupling module is proposed to disentangle synchronous causality from past AQI and meteorological features, followed by the dissemination of acquired knowledge to future time steps to enhance performance. Additionally, we introduce a causal intervention mechanism to explicitly represent the uncertainty of future meteorological features, thereby bolstering the model's robustness. Our evaluation of AirCade on an open-source air quality dataset demonstrates over 20\% relative improvement over state-of-the-art models.
Open AccessSpatiotemporal Causal Decoupling Model for Air Quality Forecasting
Due to the profound impact of air pollution on human health, livelihoods, and economic development, air quality forecasting is of paramount significance. Initially, we employ the causal graph method to scrutinize the constraints of existing research in comprehensively modeling the causal relationships between the air quality index (AQI) and meteorological features. In order to enhance prediction accuracy, we introduce a novel air quality forecasting model, AirCade, which incorporates a causal decoupling approach. AirCade leverages a spatiotemporal module in conjunction with knowledge embedding techniques to capture the internal dynamics of AQI. Subsequently, a causal decoupling module is proposed to disentangle synchronous causality from past AQI and meteorological features, followed by the dissemination of acquired knowledge to future time steps to enhance performance. Additionally, we introduce a causal intervention mechanism to explicitly represent the uncertainty of future meteorological features, thereby bolstering the model's robustness. Our evaluation of AirCade on an open-source air quality dataset demonstrates over 20\% relative improvement over state-of-the-art models.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (21) , 22858-22866
STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis
Time series forecasting plays a crucial role in domains such as finance, healthcare, and climate science. However, as modern time series data become increasingly complex, featuring high dimensionality, intricate spatiotemporal dependencies, and multi-scale evolutionary patterns, traditional analytical methods and existing predictive models face significant challenges. Although Large Language Models (LLMs) excel in capturing long-range dependencies, they still struggle with multi-scale dynamics and seasonal patterns. Moreover, while LLMs' semantic representation capabilities are rich, they often lack explicit alignment with the numerical patterns and temporal structures of time series data, leading to limitations in predictive accuracy and interpretability. To address these challenges, this paper proposes a novel framework, STEM-LTS (Semantic-TEmporal Modeling for Large-scale Time Series). STEM-LTS enhances the ability to capture complex spatiotemporal dependencies by integrating time series decomposition techniques with LLM-based modeling. The semantic-temporal alignment mechanism within the framework significantly improves LLMs' ability to interpret and forecast time series data. Additionally, we develop an adaptive multi-task learning strategy to optimize the model's performance across multiple dimensions. Through extensive experiments on various real-world datasets, we demonstrate that STEM-LTS achieves significant improvements in prediction accuracy, robustness to noise, and interpretability. Our work not only advances LLM-based time series analysis but also offers new perspectives on handling complex temporal data.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (21) , 22858-22866
Open AccessSTEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis
Time series forecasting plays a crucial role in domains such as finance, healthcare, and climate science. However, as modern time series data become increasingly complex, featuring high dimensionality, intricate spatiotemporal dependencies, and multi-scale evolutionary patterns, traditional analytical methods and existing predictive models face significant challenges. Although Large Language Models (LLMs) excel in capturing long-range dependencies, they still struggle with multi-scale dynamics and seasonal patterns. Moreover, while LLMs' semantic representation capabilities are rich, they often lack explicit alignment with the numerical patterns and temporal structures of time series data, leading to limitations in predictive accuracy and interpretability. To address these challenges, this paper proposes a novel framework, STEM-LTS (Semantic-TEmporal Modeling for Large-scale Time Series). STEM-LTS enhances the ability to capture complex spatiotemporal dependencies by integrating time series decomposition techniques with LLM-based modeling. The semantic-temporal alignment mechanism within the framework significantly improves LLMs' ability to interpret and forecast time series data. Additionally, we develop an adaptive multi-task learning strategy to optimize the model's performance across multiple dimensions. Through extensive experiments on various real-world datasets, we demonstrate that STEM-LTS achieves significant improvements in prediction accuracy, robustness to noise, and interpretability. Our work not only advances LLM-based time series analysis but also offers new perspectives on handling complex temporal data.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (20) , 21330-21338
Multi-label Self Knowledge Distillation
Self-Knowledge Distillation (SKD) leverages the student's own knowledge to create a virtual teacher for distillation when the pre-trained bulky teacher is not available. Whilst existing SKD approaches demonstrate gorgeous efficiency in single-label learning, to directly apply them to multi-label learning would suffer from dramatic degradation due to the following inherent imbalance: \textit{targets with unified labels but multifarious visual scales are crammed into one image, resulting in biased learning of major targets and disequilibrium of precision-recall}. To address this issue, this paper proposes a novel SKD method for multi-label learning named Multi-label Self-knowledge Distillation (MSKD), incorporating three Spatial Decoupling mechanisms (i.e. Locality-SD (L-SD), Reconstruction-SD (R-SD), and Step-SD (S-SD)). L-SD exploits relational dark knowledge from regional outputs to amplify the model's perception of visual details. R-SD reconstructs global semantics by integrating regional outputs from local patches and leverages it to guide the model. S-SD aligns outputs of the same input at different steps, aiming to find a synthetical optimizing direction and avoid the overconfidence. In addition, MSKD combines our tailored loss named MBD for balanced distillation. Exhaustive experiments demonstrate that MSKD not only outperforms previous approaches but also effectively mitigates biased learning and equips the model with more robustness.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (20) , 21330-21338
Open AccessMulti-label Self Knowledge Distillation
Self-Knowledge Distillation (SKD) leverages the student's own knowledge to create a virtual teacher for distillation when the pre-trained bulky teacher is not available. Whilst existing SKD approaches demonstrate gorgeous efficiency in single-label learning, to directly apply them to multi-label learning would suffer from dramatic degradation due to the following inherent imbalance: \textit{targets with unified labels but multifarious visual scales are crammed into one image, resulting in biased learning of major targets and disequilibrium of precision-recall}. To address this issue, this paper proposes a novel SKD method for multi-label learning named Multi-label Self-knowledge Distillation (MSKD), incorporating three Spatial Decoupling mechanisms (i.e. Locality-SD (L-SD), Reconstruction-SD (R-SD), and Step-SD (S-SD)). L-SD exploits relational dark knowledge from regional outputs to amplify the model's perception of visual details. R-SD reconstructs global semantics by integrating regional outputs from local patches and leverages it to guide the model. S-SD aligns outputs of the same input at different steps, aiming to find a synthetical optimizing direction and avoid the overconfidence. In addition, MSKD combines our tailored loss named MBD for balanced distillation. Exhaustive experiments demonstrate that MSKD not only outperforms previous approaches but also effectively mitigates biased learning and equips the model with more robustness.