Fog Computing. Группа авторов
Читать онлайн книгу.
it interacts with, but also recognize their facial emotions at the same time. These tasks all share the same data inputs and the limited resources on the edge device. How to effectively share the data inputs across concurrent deep learning tasks and efficiently utilize the shared resources to maximize the overall performance of all the concurrent deep learning tasks is challenging.
In terms of input data sharing, currently, data acquisition for concurrently running deep-learning tasks on edge devices is exclusive. In other words, at runtime, only one single deep learning task is able to access the sensor data inputs at one time. As a consequence, when there are multiple deep learning tasks running concurrently on edge devices, each deep learning task has to explicitly invoke system Application Programming Interfaces (APIs) to obtain its own data copy and maintain it in its own process space. This mechanism causes considerable system overhead as the number of concurrently running deep learning tasks increases. To address this input data sharing challenge, one opportunity lies at creating a data provider that is transparent to deep learning tasks and sits between them and the operating system as shown in Figure 3.2. The data provider creates a single copy of the sensor data inputs such that deep learning tasks that need to acquire data all access to this single copy for data acquisition. As such, a deep learning task is able to acquire data without interfering other tasks. More important, it provides a solution that scales in terms of the number of concurrently running deep learning tasks.
In terms of resource sharing, in common practice, DNN models are designed for individual deep learning tasks. However, existing works in deep learning show that DNN models exhibit layer-wise semantics where bottom layers extract basic structures and low-level features while layers at upper levels extract complex structures and high-level features. This key finding aligns with a subfield in machine learning named multitask learning [26]. In multitask learning, a single model is trained to perform multiple tasks by sharing low-level features while high-level features differ for different tasks. For example, a DNN model can be trained for scene understanding as well as object classification [27]. Multitask learning provides a perfect opportunity for improving the resource utilization for resource-limited edge devices when concurrently executing multiple deep learning tasks. By sharing the low-level layers of the DNN model across different deep learning tasks, redundancy across deep learning tasks can be maximally reduced. In doing so, edge devices can efficiently utilize the shared resources to maximize the overall performance of all the concurrent deep learning tasks.
Figure 3.2 Illustration of data sharing mechanism.
3.2.7 Offloading to Nearby Edges
For edge devices that have extremely limited resources such as low-end Internet of Things (IoT) devices, they may still not be able to afford executing the most memory and computation-efficient DNN models locally. In such a scenario, instead of running the DNN models locally, it is necessary to offload the execution of DNN models. As mentioned in the introduction section, offloading to the cloud has a number of drawbacks, including leaking user privacy and suffering from unpredictable end-to-end network latency that could affect user experience, especially when real-time feedback is needed. Considering those drawbacks, a better option is to offload to nearby edge devices that have ample resources to execute the DNN models.
To realize edge offloading, the key is to come up with a model partition and allocation scheme that determines which part of model should be executed locally and which part of model should be offloading. To answer this question, the first aspect that needs to take into account is the size of intermediate results of executing a DNN model. A DNN model adopts a layered architecture. The sizes of intermediate results generated out of each layer have a pyramid shape (Figure 3.3), decreasing from lower layers to higher layers. As a result, partitioning at lower layers would generate larger sizes of intermediate results, which could increase the transmission latency. The second aspect that needs to take into account is the amount of information to be transmitted. For a DNN model, the amount of information generated out of each layer decreases from lower layers to higher layers. Partitioning at lower layers would prevent more information from being transmitted, thus preserving more privacy. As such, the edge offloading scheme creates a trade-off between computation workload, transmission latency, and privacy preservation.
Figure 3.3 Illustration of intermediate results of a DNN model. The size of intermediate results generated out of each layer decreases from lower layers to higher layers. The amount of information generated out of each layer also decreases from lower layers to higher layers.
3.2.8 On-device Training
In common practice, DNN models are trained on high-end workstations equipped with powerful GPUs where training data are also located. This is the approach that giant AI companies such as Google, Facebook, and Amazon have adopted. These companies have been collecting a gigantic amount of data from users and use those data to train their DNN models. This approach, however, is privacy-intrusive, especially for mobile phone users because mobile phones may contain the users' privacy-sensitive data. Protecting users' privacy while still obtaining well-trained DNN models becomes a challenge.
To address this challenge, we envision that the opportunity lies in on-device training. As computer resources in edge devices become increasingly powerful, especially with the emergence of AI chipsets, in the near future, it becomes feasible to train a DNN model locally on edge devices. By keeping all the personal data that may contain private information on edge devices, on-device training provides a privacy-preserving mechanism that leverages the compute resources inside edge devices to train DNN models without sending the privacy-sensitive personal data to the giant AI companies. Moreover, today, gigantic amounts of data are generated by edge devices such as mobile phones on a daily basis. These data contain valuable information about users and their personal preferences. With such personal information, on-device training is enabling training personalized DNN models that deliver personalized services to maximally enhance user experiences.
3.3 Concluding Remarks
Edge computing is revolutionizing the way we live, work, and interact with the world. With the recent breakthrough in deep learning, it is expected that in the foreseeable future, majority of the edge devices will be equipped with machine intelligence powered by deep learning. To realize the full promise of deep learning in the era of edge computing, there are daunting challenges to address.
In this chapter, we presented eight challenges at the intersection of computer systems, networking, and machine learning. These challenges are driven by the gap between high computational demand of DNN models and the limited battery lives of edge devices, the data discrepancy in real-world settings, the need to process heterogeneous sensor data and concurrent deep learning tasks on heterogeneous computing units, and the opportunities for offloading to nearby edges and on-device training. We also proposed opportunities that have potential to address these challenges. We hope our discussion could inspire new research that turns the envisioned intelligent edge into reality.
References
1 1 Shi, W., Cao, J., Zhang, Q. et al. (2016). Edge computing: vision and challenges. IEEE Internet of Things Journal 3 (5): 637–646.
2 2 Shi, W. and Dustdar, S. (2016). The promise of edge computing. Computer 49 (5): 78–81.
3 3 Satyanarayanan, M. (2017). The emergence of edge computing.