Hai Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hai Wang has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Shuai Wang
Southeast University
8 shared publications - Tian He
University of Minnesota
6 shared publications - Desheng Zhang
Rutgers University
5 shared publications - Li Lin
Southeast University
4 shared publications - Xiaolei Zhou
National University of Defense Technology
4 shared publications - Baoshen Guo
Southeast University
3 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (23) , 56105-56117
Adversarial Multievent Modeling for Multicategory Sales Forecasting in Community Commerce
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (23) , 56105-56117
Adversarial Multievent Modeling for Multicategory Sales Forecasting in Community Commerce
- Open Access
- 1 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Foundation Model for Conditional Trajectory Generation with Unstable Context Availability
With the proliferation of data-driven smart city applications, massive amounts of trajectory data are being collected. These trajectories are typically captured as sequences of GPS coordinates, and are often enriched with diverse contextual information, such as timestamps, user IDs, and service metadata. They form the backbone of many smart city applications such as navigation, logistics, and urban planning. Generative tasks on this data - such as trajectory prediction, recovery, and synthesis - play a critical role in these applications by filling data gaps, simulating scenarios, or augmenting datasets, which all require generating coordinates conditioned on partial observations and auxiliary context. There are two weaknesses in most existing methods: i) they are typically tailored for a specific task and rely on fixed sets of contextual features, leading to repeated efforts across tasks and domains; ii) they are not robust to unstable context availability, as contextual information is often incomplete, unavailable, or inconsistent in real-world settings. In this work, we present TrajWeaver , a novel diffusion-based foundation model designed to support multiple conditional trajectory generation tasks within a single framework, while being flexible to diverse conetxts and robust to unstable context availability. TrajWeaver introduces a novel State Propagation Pipeline (SPP) on top of the diffusion model, which uses multi-scale state features as messengers to proprgate and refine contextual information and knowledge across denoising steps. This design improves robustness to missing or partial context and enables seamless adaptation to new types of conditional features without retraining the full model. Experiments across three trajectory generation tasks demonstrate that TrajWeaver achieves strong performance and generalization under different settings, showcasing its potential as a foundation model for trajectory generation.
- 1 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
Open AccessFoundation Model for Conditional Trajectory Generation with Unstable Context Availability
With the proliferation of data-driven smart city applications, massive amounts of trajectory data are being collected. These trajectories are typically captured as sequences of GPS coordinates, and are often enriched with diverse contextual information, such as timestamps, user IDs, and service metadata. They form the backbone of many smart city applications such as navigation, logistics, and urban planning. Generative tasks on this data - such as trajectory prediction, recovery, and synthesis - play a critical role in these applications by filling data gaps, simulating scenarios, or augmenting datasets, which all require generating coordinates conditioned on partial observations and auxiliary context. There are two weaknesses in most existing methods: i) they are typically tailored for a specific task and rely on fixed sets of contextual features, leading to repeated efforts across tasks and domains; ii) they are not robust to unstable context availability, as contextual information is often incomplete, unavailable, or inconsistent in real-world settings. In this work, we present TrajWeaver , a novel diffusion-based foundation model designed to support multiple conditional trajectory generation tasks within a single framework, while being flexible to diverse conetxts and robust to unstable context availability. TrajWeaver introduces a novel State Propagation Pipeline (SPP) on top of the diffusion model, which uses multi-scale state features as messengers to proprgate and refine contextual information and knowledge across denoising steps. This design improves robustness to missing or partial context and enables seamless adaptation to new types of conditional features without retraining the full model. Experiments across three trajectory generation tasks demonstrate that TrajWeaver achieves strong performance and generalization under different settings, showcasing its potential as a foundation model for trajectory generation.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5484-5492
TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 5484-5492
Open AccessTRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (3) , 2205-2218
InfSquad: SLO-Aware Serverless Machine Learning Inference With Wasm-Assisted Hybrid Functions
Though serverless computing offers transformative benefits for deploying machine learning (ML) services, it faces challenges in meeting strict real-time service-level objectives (SLOs) of ML inference while maintaining resource efficiency. Fortunately, a new binary instruction format, WebAssembly (or Wasm), offers a promising solution for serverless ML inferences thanks to its short startup time and efficient execution compared with traditional container-based solutions. Therefore, we introduce InfSquad, a serverless ML inference framework designed to balance SLO-aware execution with resource efficiency. The key design of InfSquad is a Wasm-assisted hybrid serverless function runtime to harness the complementary strengths of Wasm and traditional containerized function runtime. Based on the hybrid runtime, InfSquad advocates an SLO-aware runtime scheduling approach that delivers efficient serverless inference. InfSquad leverages a proactive runtime recycling mechanism to increase resource efficiency further. Experiments on real-world applications show that, compared with state-of-the-art serverless systems, InfSquad achieves 19.8% 85.1% SLO violation reduction with 32.5% 74.8% fewer resources.
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (3) , 2205-2218
InfSquad: SLO-Aware Serverless Machine Learning Inference With Wasm-Assisted Hybrid Functions
Though serverless computing offers transformative benefits for deploying machine learning (ML) services, it faces challenges in meeting strict real-time service-level objectives (SLOs) of ML inference while maintaining resource efficiency. Fortunately, a new binary instruction format, WebAssembly (or Wasm), offers a promising solution for serverless ML inferences thanks to its short startup time and efficient execution compared with traditional container-based solutions. Therefore, we introduce InfSquad, a serverless ML inference framework designed to balance SLO-aware execution with resource efficiency. The key design of InfSquad is a Wasm-assisted hybrid serverless function runtime to harness the complementary strengths of Wasm and traditional containerized function runtime. Based on the hybrid runtime, InfSquad advocates an SLO-aware runtime scheduling approach that delivers efficient serverless inference. InfSquad leverages a proactive runtime recycling mechanism to increase resource efficiency further. Experiments on real-world applications show that, compared with state-of-the-art serverless systems, InfSquad achieves 19.8% 85.1% SLO violation reduction with 32.5% 74.8% fewer resources.
- 24 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (4) , 1885-1901
HPST-GT: Full-Link Delivery Time Estimation Via Heterogeneous Periodic Spatial-Temporal Graph Transformer
A warehouse-distribution integration (WDI) e-commerce platform is an approach that combines warehousing and distribution processes, which is increasingly adopted in industry to enhance business efficiency. In the WDI e-commerce, one of the most important problems is to estimate the full-link delivery time for decision-making. Traditional methods designed for separate warehouse-distribution models struggle to address challenges in integrated systems. The difficulties stem from two main factors: (i) the contextual influence exerted by neighboring units within heterogeneous delivery networks, and (ii) the uncertainty in delivery times caused by dynamic and periodic temporal factors such as fluctuations in online sales volumes and the varying characteristics of different delivery units (e.g., warehouses and sorting centers). To address these challenges, we propose a novel full-link delivery time estimation framework called Heterogeneous Periodic Spatial-Temporal Graph Transformer (HPST-GT). First, we develop heterogeneous graph transformers to capture the hierarchical and diverse information of the warehouse-distribution network. Next, we design spatial-temporal transformers based on heterogeneous features to analyze the correlation between spatial and temporal information. Finally, we create a heterogeneous spatial-temporal graph prediction module to estimate full-link delivery time. Our method, evaluated on a one-month dataset from a leading e-commerce platform, surpasses current benchmarks across multiple performance metrics.
- 24 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (4) , 1885-1901
HPST-GT: Full-Link Delivery Time Estimation Via Heterogeneous Periodic Spatial-Temporal Graph Transformer
A warehouse-distribution integration (WDI) e-commerce platform is an approach that combines warehousing and distribution processes, which is increasingly adopted in industry to enhance business efficiency. In the WDI e-commerce, one of the most important problems is to estimate the full-link delivery time for decision-making. Traditional methods designed for separate warehouse-distribution models struggle to address challenges in integrated systems. The difficulties stem from two main factors: (i) the contextual influence exerted by neighboring units within heterogeneous delivery networks, and (ii) the uncertainty in delivery times caused by dynamic and periodic temporal factors such as fluctuations in online sales volumes and the varying characteristics of different delivery units (e.g., warehouses and sorting centers). To address these challenges, we propose a novel full-link delivery time estimation framework called Heterogeneous Periodic Spatial-Temporal Graph Transformer (HPST-GT). First, we develop heterogeneous graph transformers to capture the hierarchical and diverse information of the warehouse-distribution network. Next, we design spatial-temporal transformers based on heterogeneous features to analyze the correlation between spatial and temporal information. Finally, we create a heterogeneous spatial-temporal graph prediction module to estimate full-link delivery time. Our method, evaluated on a one-month dataset from a leading e-commerce platform, surpasses current benchmarks across multiple performance metrics.
- 28 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (6) , 6775-6789
Full-Link Delivery Time Prediction in Logistics Using Federated Heterogeneous Graph Transformer
Motivated by the pursuit of greater efficiency, companies, such as Amazon and JD, are shifting toward a warehouse-distribution integration model to optimize logistics operations. In general full-link logistics scenarios, the collaboration between warehouses and sorting centers managed by different enterprises leads to data silos, posing challenges in securely sharing information and accurately predicting delivery times across the entire logistics network. Current delivery time prediction methods often overlook the heterogeneity of logistics networks and face data sharing constraints. We aim to address these issues by facilitating secure internode relationship analysis and leveraging distinct spatio-temporal characteristics to enhance efficiency. However, challenges remain in overcoming data isolation while maintaining protection and integrating diverse node characteristics for optimized modeling. To address these challenges, we propose the federated heterogeneous graph transformer (Fed-HGT) framework. This framework includes a federated training module that integrates local and central gradients by exchanging node representations and model parameters between logistics nodes and the central server. Additionally, it features a federated prediction module where local nodes compute time representations using their local data and transmit these to the central server. The central server then uses these representations to make accurate full-link delivery time predictions. Our method was evaluated on a dataset from a major e-commerce platform in China, demonstrating significant performance improvements over existing solutions.
- 28 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (6) , 6775-6789
Full-Link Delivery Time Prediction in Logistics Using Federated Heterogeneous Graph Transformer
Motivated by the pursuit of greater efficiency, companies, such as Amazon and JD, are shifting toward a warehouse-distribution integration model to optimize logistics operations. In general full-link logistics scenarios, the collaboration between warehouses and sorting centers managed by different enterprises leads to data silos, posing challenges in securely sharing information and accurately predicting delivery times across the entire logistics network. Current delivery time prediction methods often overlook the heterogeneity of logistics networks and face data sharing constraints. We aim to address these issues by facilitating secure internode relationship analysis and leveraging distinct spatio-temporal characteristics to enhance efficiency. However, challenges remain in overcoming data isolation while maintaining protection and integrating diverse node characteristics for optimized modeling. To address these challenges, we propose the federated heterogeneous graph transformer (Fed-HGT) framework. This framework includes a federated training module that integrates local and central gradients by exchanging node representations and model parameters between logistics nodes and the central server. Additionally, it features a federated prediction module where local nodes compute time representations using their local data and transmit these to the central server. The central server then uses these representations to make accurate full-link delivery time predictions. Our method was evaluated on a dataset from a major e-commerce platform in China, demonstrating significant performance improvements over existing solutions.
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4710-4717
DIFN: A Dual Intention-aware Network for Repurchase Recommendation with Hierarchical Spatio-temporal Fusion
Recommendation systems play a crucial role in both industrial applications and research fields, which target to understand user preferences and intentions to provide personalized services. Compared to conventional recommendations, repurchase recommendations aim to suggest suitable products to users that they used to buy based on their intention evolution. Existing research on product recommendation can mainly be divided into behavior sequence-based methods and graph-based methods. Although these methods represent user interests and preference features effectively, they still fail to model repurchase behaviors because (i) the environment causing repurchase intention change is neglected and (ii) the lack of feedback after purchasing makes it difficult to learn the impacts of diverse behaviors. To comprehensively consider these limitations, we design a D ual I ntention-aware F usion N etwork framework (DIFN) to understand the effects of environment and after-purchasing feedback on users' intentions. Firstly, a hierarchical graph-based multi-level relational attention module is designed to effectively extract basic user features and spatial features from complex environmental information. Then, we introduce a behavior intention module and a usage intention module for different types of feedback data. Finally, we propose a dual intention fusion network that effectively fuses user basic features with spatial attributes and user intention features with temporal attributes for recommendation. Comprehensive evaluations on real-world datasets show that our method exceeds state-of-the-art baselines, which show an average of 8.2% improvements in different metrics.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4710-4717
Open AccessDIFN: A Dual Intention-aware Network for Repurchase Recommendation with Hierarchical Spatio-temporal Fusion
Recommendation systems play a crucial role in both industrial applications and research fields, which target to understand user preferences and intentions to provide personalized services. Compared to conventional recommendations, repurchase recommendations aim to suggest suitable products to users that they used to buy based on their intention evolution. Existing research on product recommendation can mainly be divided into behavior sequence-based methods and graph-based methods. Although these methods represent user interests and preference features effectively, they still fail to model repurchase behaviors because (i) the environment causing repurchase intention change is neglected and (ii) the lack of feedback after purchasing makes it difficult to learn the impacts of diverse behaviors. To comprehensively consider these limitations, we design a D ual I ntention-aware F usion N etwork framework (DIFN) to understand the effects of environment and after-purchasing feedback on users' intentions. Firstly, a hierarchical graph-based multi-level relational attention module is designed to effectively extract basic user features and spatial features from complex environmental information. Then, we introduce a behavior intention module and a usage intention module for different types of feedback data. Finally, we propose a dual intention fusion network that effectively fuses user basic features with spatial attributes and user intention features with temporal attributes for recommendation. Comprehensive evaluations on real-world datasets show that our method exceeds state-of-the-art baselines, which show an average of 8.2% improvements in different metrics.