Over-the-Air Ensemble Inference with Model Privacy

Yılmaz, Selim; Hasırcıoglu, Burak; Gündüz, Deniz

doi:10.1109/isit50566.2022.9834591

Cited by 13 publications

(7 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, privacy concerns arise in Edge Ensembles due to data transmission to other devices. Yilmaz et al [8] proposed the security-enhanced method where each device adds noise to the inference results to prevent leakage of information about the model on that device. This approach is similar to FL, where models train collaboratively while keeping their individual information confidential.…”

Section: Cascadementioning

confidence: 99%

“…To address these challenges, ensemble-based collaborative inference systems, Edge Ensembles, have been proposed [5]- [8]. Edge Ensembles utilize ensemble methods to aggregate the inference results from respective models deployed on each edge device, achieving higher accuracy than single-device inference.…”

Section: Introductionmentioning

confidence: 99%

“…In previous Edge Ensembles, they have utilized conventional model integration methods such as majority voting [8], averaging the output of each model [5], [8], and weighted averaging based on the importance of each model [6], [7]. In addition to these methods, various effective model integration techniques have been used in previous DNN ensembles [10]- [13].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Toward Improving Ensemble-Based Collaborative Inference at the Edge

Kumazawa,

Yu,

Kawamura

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Ensemble-based collaborative inference systems, Edge Ensembles, are deep learning edge inference systems that enhance accuracy by aggregating predictions from models deployed on each device. They offer several advantages, including scalability based on task complexity and decentralized functionality without dependency on centralized servers. In general, ensemble methods effectively improve the accuracy of deep learning, and conventional research uses several model integration techniques for deep learning ensembles. Some of these existing integration methods are more effective than those used in previous Edge Ensembles. However, it remains uncertain whether these methods can be directly applied in the context of cooperative inference systems involving multiple edge devices. This study investigates the effectiveness of conventional model integration techniques, including cascade, weighted averaging, and testtime augmentation (TTA), when applied to Edge Ensembles to enhance their performance. Furthermore, we propose enhancements of these techniques tailored for Edge Ensembles. The cascade reduces the number of models required for inference but worsens latency by sequential inference processing. To address this latency issue, we propose m-parallel cascade, which adjusts the number of models processed simultaneously to m. We also propose learning TTA policies and weights for weighted averaging using ensemble prediction labels instead of ground truth labels. In the experiments, we verified the effectiveness of each technique for Edge Ensembles. The proposed m-parallel cascade achieved a 2.8 times reduction in latency compared to the conventional cascade, even with a 1.06 times increase in computational costs. Additionally, the ensemble label-based learning demonstrated comparable effectiveness to the approach using ground truth labels.INDEX TERMS Ensemble, edge computing, collaborative inference, neural networks, cascade, test time augmentation.

show abstract

Section: Cascadementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Toward Improving Ensemble-Based Collaborative Inference at the Edge

Kumazawa,

Yu,

Kawamura

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Most recently, AirComp sees growing popularity in its application to supporting efficient model/gradient aggregation in federated learning, known as over-the-air federated learning [18], [20]- [22]. Researchers also proposed the use of AirComp to realize majority-voting over-the-air in a distributed inference system [23]. AirPooling is a task-oriented AirComp technique targeting AIoT sensing.…”

Section: Introductionmentioning

confidence: 99%

Over-the-Air Multi-View Pooling for Distributed Sensing

Liu¹,

Li²,

Kalør³

et al. 2023

Preprint

View full text Add to dashboard Cite

Sensing is envisioned as a key network function of the sixth-generation (6G) mobile networks.Artificial intelligence (AI)-empowered sensing fuses features of multiple sensing views from devices distributed in edge networks for the edge server to perform accurate inference. This process, known as multi-view pooling, creates a communication bottleneck due to multi-access by many devices. To alleviate this issue, we propose a task-oriented simultaneous access scheme for distributed sensing called Overthe-Air Pooling (AirPooling). The existing Over-the-Air Computing (AirComp) technique can be directly applied to enable Average-AirPooling, which exploits the waveform superposition property of a multiaccess channel to implement fast over-the-air averaging of pooled features. However, despite being most popular in practice, the over-the-air maximization, called Max-AirPooling, is not AirComp realizable given the fact that AirComp addresses only a limited subset of functions. We tackle the challenge by proposing the novel generalized AirPooling framework that can be configured to support both Maxand Average-AirPooling by controlling a configuration parameter and extended to even other pooling functions. The former is realized by adding to AirComp the designed pre-processing at devices and postprocessing at the server. To characterize the End-to-End (E2E) sensing performance in object recognition, the theory of classification margin is applied to relate the classification accuracy and the AirPooling error, which allows the latter to be a tractable surrogate of the former. Furthermore, the analysis reveals an inherent tradeoff of Max-AirPooling between the accuracy of the pooling-function approximation and the effectiveness of noise suppression. Using the tradeoff, we make an attempt to optimize the configuration parameter of Max-AirPooling, yielding a sub-optimal closed-form method of adaptive parametric control. Experimental results obtained on real-world datasets show that AirPooling provides sensing accuracies close to those achievable by the traditional digital air interface but dramatically reduces the communication latency, by up to an order of magnitude.

show abstract

“…AirComp's basic principle is to exploit the wave superposition property to achieve over-the-air aggregation of uncoded analog signals simultaneously transmitted by multiple devices. The scalability as a result of simultaneous access makes AirComp a popular air-interface technology for supporting fast and efficient distributed computing in 6G operations such as distributed learning [22], inference [23], and sensing [6], [24]. In addition, the use of uncoded analog transmission in AirComp is another factor contributing to the technology's ultra-low-latency while the resultant unreliability can be coped with by the robustness of data-analytics techniques or an AI algorithm [6], [25], [26].…”

Section: Introductionmentioning

confidence: 99%

An Integrated Method for River Water Level Recognition from Surveillance Images Using Convolution Neural Networks

Chen

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Water conservancy personnel usually need to know the water level by water gauge images in real-time and with an expected accuracy. However, accurately recognizing the water level from water gauge images is still a complex problem. This article proposes a composite method applied in the Wuyuan City, Jiangxi Province, in China. This method can detect water gauge areas and number areas from complex and changeable scenes, accurately detect the water level line from various water gauges, and finally, obtain the accurate water level value. Firstly, FCOS is improved by fusing a contextual adjustment module to meet the requirements of edge computing and ensure considerable detection accuracy. Secondly, to deal with scenes with indistinct water level features, we also apply the contextual adjustment module for Deeplabv3+ to segment the water gauge area above the water surface. Then, the area can be used to obtain the position of the water level line. Finally, the results of the previous two steps are combined to calculate the water level value. Detailed experiments prove that this method solves the problem of water level recognition in complex hydrological scenes. Furthermore, the recognition error of the water level by this method is less than 1 cm, proving it is capable of being applied in real river scenes.

show abstract

Over-the-Air Ensemble Inference with Model Privacy

Cited by 13 publications

References 66 publications

Toward Improving Ensemble-Based Collaborative Inference at the Edge

Toward Improving Ensemble-Based Collaborative Inference at the Edge

Over-the-Air Multi-View Pooling for Distributed Sensing

An Integrated Method for River Water Level Recognition from Surveillance Images Using Convolution Neural Networks

Contact Info

Product

Resources

About