Deep Transfer Learning Across Cities for Mobile Traffic Prediction

Wu, Qiong; He, Kaiwen; Chen, Xu; Yu, Shuai; Zhang, Junshan

doi:10.1109/tnet.2021.3136707

Cited by 15 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attention is used to assign weights to historical input. GASTN , which was proposed in [24] for mobile traffic prediction based on attention and recurrent neural networks. …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

TransMUSE: Transferable Traffic Prediction in MUlti-Service Edge Networks

Liu

Song

et al. 2023

Computer Networks

View full text Add to dashboard Cite

“…Attention is used to assign weights to historical input. GASTN , which was proposed in [24] for mobile traffic prediction based on attention and recurrent neural networks. …”

Section: Methodsmentioning

confidence: 99%

“…GASTN , which was proposed in [24] for mobile traffic prediction based on attention and recurrent neural networks.…”

Section: Methodsmentioning

confidence: 99%

TransMUSE: Transferable Traffic Prediction in MUlti-Service Edge Networks

Liu

Song

et al. 2023

Computer Networks

View full text Add to dashboard Cite

“…There are unanswered questions about how models trained in specific regions generalize to other areas. Recent studies of transfer learning approaches, such as those by Wu et al [125] are promising in this sense, and pave the way for further investigations.…”

Section: B Directions For Improving Forecasting Modelsmentioning

confidence: 98%

Forecasting Network Traffic: A Survey and Tutorial With Open-Source Comparative Evaluation

et al. 2023

View full text Add to dashboard Cite

This paper presents a review of the literature on network traffic prediction, while also serving as a tutorial to the topic. We examine works based on autoregressive moving average models, like ARMA, ARIMA and SARIMA, as well as works based on Artifical Neural Networks approaches, such as RNN, LSTM, GRU, and CNN. In all cases, we provide a complete and self-contained presentation of the mathematical foundations of each technique, which allows the reader to get a full understanding of the operation of the different proposed methods. Further, we perform numerical experiments based on real data sets, which allows comparing the various approaches directly in terms of fitting quality and computational costs. We make our code publicly available, so that readers can readily access a wide range of forecasting tools, and possibly use them as benchmarks for more advanced solutions.

show abstract

“…Recently, transfer learning across cities provides a good perspective on the data insufficiency problem, which transfers the knowledge learned from data-rich cities (source cities) to the data-insufficient city (target city), alleviating the target data insufficiency [3]- [6]. However, most prior studies only focus on a single data insufficiency problem alone or simplify the learning problems with a strong assumption.…”

Section: Introductionmentioning

confidence: 99%

“…For example, [3] assumed that the target data is sparse instead of missing and then developed a cross-city transfer learning method RegionTrans for deep spatio-temporal prediction tasks. [6] proposed a cross-city transfer learning framework for citywide mobile traffic prediction, which only solved the label scarcity problem. Though achieving great progress, the idealized experimental settings in prior studies discount the availability when facing two kinds of data insufficiency problems simultaneously in real scenarios.…”

Section: Introductionmentioning

confidence: 99%

A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling

Chen¹,

Su²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Data insufficiency problem (i.e., data missing and label scarcity issues) caused by inadequate services and infrastructures or unbalanced development levels of cities has seriously affected the urban computing tasks in real scenarios. Prior transfer learning methods inspire an elegant solution to the data insufficiency, but are only concerned with one kind of insufficiency issue and fail to give consideration to both sides. In addition, most previous cross-city transfer methods overlooks the inter-city data privacy which is a public concern in practical application. To address above challenging problems, we propose a novel Cross-city Federated Transfer Learning framework (CcFTL) to cope with the data insufficiency and privacy problems. Concretely, CcFTL transfers the relational knowledge from multiple rich-data source cities to the target city. Besides, the model parameters specific to the target task are firstly trained on the source data and then fine-tuned to the target city by parameter transfer. With our adaptation of federated training and homomorphic encryption settings, CcFTL can effectively deal with the data privacy problem among cities. We take the urban region profiling as an application of smart cities and evaluate the proposed method with a real-world study. The experiments demonstrate the notable superiority of our framework over several competitive state-of-the-art models.

show abstract

Deep Transfer Learning Across Cities for Mobile Traffic Prediction

Cited by 15 publications

References 34 publications

TransMUSE: Transferable Traffic Prediction in MUlti-Service Edge Networks

TransMUSE: Transferable Traffic Prediction in MUlti-Service Edge Networks

Forecasting Network Traffic: A Survey and Tutorial With Open-Source Comparative Evaluation

A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling

Contact Info

Product

Resources

About