AI Advances in Edge Computing

Dear Colleagues,

Nowadays, with the rise in popularity of large language models (LLMs) and generative AI, more intelligent applications and research are being implemented in daily life and production. One significant trend is edge devices’ model compression and deployment to enhance rapid response, flexible customization with the application environments, and more controllable local data protection. Accordingly, various studies on model deployment and compression and cross-domain integration have been proposed to address these issues.

The increasing offering of new AI methods affords significant advances for edge computing and IoT applications. Examples of innovations unlocking new possibilities for resource-constrained AI at the edge include the following: a novel structured pruning approach which can greatly reduce complex CNN resource requirements without sacrificing accuracy; multi-compression scale DNN inference acceleration (MCIA), which uses cloud-edge-end collaboration and deep reinforcement learning; an optimization problem and algorithm, proposed for hosting LLM-powered generative AI on edge devices; and, finally, a method for the multistage low-rank fine-tuning of super-transformers (MLFS), which enables the parameter-efficient supernet training of LLMs, allowing the production of smaller models for edge applications at a constant cost.

This Special Issue will focus on the latest theoretical and computational studies on deploying intelligent models on computationally limited edge devices, with an emphasis on model compression, optimization, and application expansion. The topics include, but are not limited to, the following:

• Theoretical research on large-model compression;
• Performance optimization of model compression;
• Applications of generative AI on edge devices;
• Collaborative research on distributed multi-agent systems;
• Security studies on edge intelligence;
• Communication and collaboration in distributed multi-agent systems.

Dr. Qun Wang
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• edge AI
• GenAI security
• sparsity pruning
• network compression
• convolutional neural networks
• edge computing
• large language models
• mixed sparsity