FoggyCache

Online Learning for Network Resource Allocation

“…But object popularity can be difficult to estimate and can change over time, specially at the level of small geographical areas (as in the case of areas served by an edge server) [166]. Other papers [118][119][120][121][122]167] present more a high-level view of the different components of the application system, without specific contributions in terms of cache management policies (e.g., they apply minor changes to exact caching policies like LRU or LFU). Some recent papers [127,168,169] propose online caching policies that try to minimize the total cost of the system (the sum of the dissimilarity cost and the fetching cost), also in a networked context [168,170], but their schemes apply only to the case 𝑘 = 1, which is of limited practical interest.…”

“…Similarity search [104] is a key building block for a large variety of applications including multimedia retrieval [105][106][107], recommendation systems [108][109][110], genome study [111,112], machine learning training [113][114][115], and serving [116][117][118][119][120][121][122][123][124][125]. Given a query for an object, the goal is to retrieve one or more similar objects from a repository.…”

“…Examples of commonly employed distances are the 𝑝-norm, Mahalanobis or cosine similarity distances. For instance, in augmented reality applications we often require identifying similar objects: the image is coded into a query, i.e., an embedding in R 𝑑 (e.g., set of descriptors like SIFT [129], or ORB [130], or the set of activation values at an intermediate layer of a neural network [131,132]), and the application logic finds similar images to be returned to the user [118][119][120]122]; moreover, in recommendation systems, objects are also embedded in R 𝑑 with a distance metric to capture content dissimilarity. This also the case for other potential applications of similarity caching like 360 • videos, where tiles at the periphery of the user's field of view could be approximated by neighboring tiles that are stored at the cache and can then be served with low latency [133].…”

HiTDL: High-Throughput Deep Learning Inference at the Hybrid Mobile Edge

“…There have been many studies on improving the performance of mobile inference with an edge computing platform [21], [39], [56], [57], [58], [59], [60], [61]. Liu et al propose an edge assisted object recognition system that jointly achieves high accuracy and low processing time by using dynamic RoI encoding, rendering pipeline decoupling, and fast object tracking [39].…”

“…However, these are feature-based inference and do not employ DNNs. Guo et al present Fog-gyCache, a computation reuse system that utilizes the computation results across devices at the edge by designing a two-level cache to reduce the redundant computation [58]. Guo et al also take into consideration the fine-grained input similarity and achieve approximately deduplicate computation across applications [59].…”