English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Split learning is a privacy-preserving distributed learning paradigm in whichan ML model (e.g., a neural network) is split into two parts (i.e., an encoderand a decoder). The encoder shares so-called latent representation, rather thanraw data, for model training. In mobile-edge computing, network functions (suchas traffic forecasting) can be trained via split learning where an encoderresides in a user equipment (UE) and a decoder resides in the edge network.Based on the data processing inequality and the information bottleneck (IB)theory, we present a new framework and training mechanism to enable a dynamicbalancing of the transmission resource consumption with the informativeness ofthe shared latent representations, which directly impacts the predictiveperformance. The proposed training mechanism offers an encoder-decoder neuralnetwork architecture featuring multiple modes of complexity-relevancetradeoffs, enabling tunable performance. The adaptability can accommodatevarying real-time network conditions and application requirements, potentiallyreducing operational expenditure and enhancing network agility. As a proof ofconcept, we apply the training mechanism to a millimeter-wave (mmWave)-enabledthroughput prediction problem. We also offer new insights and highlight somechallenges related to recurrent neural networks from the perspective of the IBtheory. Interestingly, we find a compression phenomenon across the temporaldomain of the sequential model, in addition to the compression phase thatoccurs with the number of training epochs.

Dynamic Encoding and Decoding of Information for Split Learning in Mobile-Edge Computing: Leveraging Information Bottleneck Theory