Network-Wide Traffic States Imputation Using Self-interested Coalitional Learning

Qin, Hua; Zhan, Xianyuan; Li, Yuanxun; Yang, Xiaodu; Zheng, Yu

doi:10.1145/3447548.3467424

Cited by 18 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many recent studies [23,36] use graph embeddings or GNN to model the spatio-temporal dependencies in data for network-wide traffic state estimation. Researchers further combine temporal GCN with variational autoencoder and generative adversarial network to impute network-wide traffic state [21]. However, most of these methods assume the connectivity between road segments is static, whereas the connectivity changes dynamically with traffic signals in the real world.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Network-level Traffic Flow Transitions on Sparse Data

Lei

Mei

Shi

et al. 2022

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Modeling how network-level traffic flow changes in the urban environment is useful for decision-making in transportation, public safety and urban planning. The traffic flow system can be viewed as a dynamic process that transits between states (e.g., traffic volumes on each road segment) over time. In the real-world traffic system with traffic operation actions like traffic signal control or reversible lane changing, the system's state is influenced by both the historical states and the actions of traffic operations. In this paper, we consider the problem of modeling network-level traffic flow under a real-world setting, where the available data is sparse (i.e., only part of the traffic system is observed). We present DTIGNN , an approach that can predict network-level traffic flows from sparse data. DTIGNN models the traffic system as a dynamic graph influenced by traffic signals, learns the transition models grounded by fundamental transition equations from transportation, and predicts future traffic states with imputation in the process. Through comprehensive experiments, we demonstrate that our method outperforms state-of-the-art methods and can better support decision-making in transportation. CCS CONCEPTS• Information systems → Spatial-temporal systems; • Computing methodologies → Neural networks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…To deal with sparse observations, a typical approach is to infer the missing observations first [2,6,14,18,21,37] and then learn the model with the transition of traffic states. This two-step approach has an obvious weakness, especially in the problem of learning transition models with some observations entirely missing.…”

Section: Introductionmentioning

confidence: 99%

Modeling Network-level Traffic Flow Transitions on Sparse Data

Lei

Mei

Shi

et al. 2022

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…More recently, adversarial training strategy has been incorporated to generate realistic reconstructed times series (Yoon et al, 2018a;Luo et al, 2018;Luo et al, 2019;Richardson et al, 2020;Miao et al, 2021;Qin et al, 2021). Specifically, Yoon et al (2018a) proposed GAIN to perform missing value imputation in the i.i.d.…”

Section: Related Workmentioning

confidence: 99%

“…These aforementioned methods primarily rely on modifications of standard neural architectures tailored for modeling temporal dependencies, while relational information between time series has not been explored. To capture the complex spatio-temporal patterns in traffic data imputation, Qin et al (2021) designed a temporal graph convolutional variational autoencoder, which introduced a selfinterested coalitional learning (SCL) strategy by leveraging the cooperation and competition with an additional discriminator. Due to its strong dependence on the temporal characteristics of the dataset, this approach is merely designed for the data imputation under intermittent missing pattern setting but not for the persistent missing pattern setting.…”

Section: Related Workmentioning

confidence: 99%

Adaptive graph convolutional imputation network for environmental sensor data recovery

Chen

Wang²,

Lei³

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Environmental sensors are essential for tracking weather conditions and changing trends, thus preventing adverse effects on species and environment. Missing values are inevitable in sensor recordings due to equipment malfunctions and measurement errors. Recent representation learning methods attempt to reconstruct missing values by capturing the temporal dependencies of sensor signals as handling time series data. However, existing approaches fall short of simultaneously capturing spatio-temporal dependencies in the network and fail to explicitly model sensor relations in a data-driven manner. In this work, we propose a novel Adaptive Graph Convolutional Imputation Network for missing value imputation in environmental sensor networks. A bidirectional graph convolutional gated recurrent unit module is introduced to extract spatio-temporal features which takes full advantage of the available observations from the target sensor and its neighboring sensors to recover the missing values. In addition, we design an adaptive graph learning layer that learns a sensor network topology in an end-to-end framework, in which no prior network information is needed for capturing spatial dependencies. Extensive experiments on three real-world environmental sensor datasets (solar radiation, air quality, relative humidity) in both in-sample and out-of-sample settings demonstrate the superior performance of the proposed framework for completing missing values in the environmental sensor network, which could potentially support environmental monitoring and assessment.

show abstract

“…Note that it is difficult for workers to collect fully observable data in real time [ 13 , 14 , 15 , 16 ]. Most collected data have hidden confounding factors [ 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

Self-Interested Coalitional Crowdsensing for Multi-Agent Interactive Environment Monitoring

Liu,

Lei,

et al. 2024

Sensors

View full text Add to dashboard Cite

As a promising paradigm, mobile crowdsensing (MCS) takes advantage of sensing abilities and cooperates with multi-agent reinforcement learning technologies to provide services for users in large sensing areas, such as smart transportation, environment monitoring, etc. In most cases, strategy training for multi-agent reinforcement learning requires substantial interaction with the sensing environment, which results in unaffordable costs. Thus, environment reconstruction via extraction of the causal effect model from past data is an effective way to smoothly accomplish environment monitoring. However, the sensing environment is often so complex that the observable and unobservable data collected are sparse and heterogeneous, affecting the accuracy of the reconstruction. In this paper, we focus on developing a robust multi-agent environment monitoring framework, called self-interested coalitional crowdsensing for multi-agent interactive environment monitoring (SCC-MIE), including environment reconstruction and worker selection. In SCC-MIE, we start from a multi-agent generative adversarial imitation learning framework to introduce a new self-interested coalitional learning strategy, which forges cooperation between a reconstructor and a discriminator to learn the sensing environment together with the hidden confounder while providing interpretability on the results of environment monitoring. Based on this, we utilize the secretary problem to select suitable workers to collect data for accurate environment monitoring in a real-time manner. It is shown that SCC-MIE realizes a significant performance improvement in environment monitoring compared to the existing models.

show abstract

Network-Wide Traffic States Imputation Using Self-interested Coalitional Learning

Cited by 18 publications

References 15 publications

Modeling Network-level Traffic Flow Transitions on Sparse Data

Modeling Network-level Traffic Flow Transitions on Sparse Data

Adaptive graph convolutional imputation network for environmental sensor data recovery

Self-Interested Coalitional Crowdsensing for Multi-Agent Interactive Environment Monitoring

Contact Info

Product

Resources

About