Generative and Representation Learning Models for Spatio-Temporal Tasks and Recommendation: Towards Collaborative Computing Optimization

Dear Colleagues,

The rapid proliferation of Internet of Things (IoT) sensors, mobile devices, and interconnected digital platforms has led to an explosion of complex data characterized by intricate spatiotemporal dependencies. Effectively modeling these dynamics is crucial for many applications, ranging from smart city management and autonomous transportation to personalized recommendation systems. However, traditional modeling approaches often struggle with data sparsity, high dimensionality, and the inherent noise found in real-world environments.

This Special Issue focuses on the transformative potential of Generative Models (e.g., Diffusion Models, GANs, and Large Language Models) and Representation Learning (e.g., Graph Neural Networks, Contrastive Learning, and Self-Supervised Learning) in addressing these challenges. By extracting robust, low-dimensional features and generating high-fidelity synthetic data, these methodologies enable more accurate forecasting and decision-making.

A key theme of this collection is the movement towards collaborative computing optimization. As data processing shifts from centralized clouds to the network edge, there is a critical need for lightweight, privacy-preserving, and communication-efficient architectures. We are particularly interested in research that explores how advanced learning models can be optimized for distributed environments, including federated learning frameworks, knowledge distillation for model compression, and causal-driven inference for resource-constrained devices.

We invite researchers to contribute original research articles and comprehensive reviews. The scope of this Special Issue is intentionally broad to encompass theoretical innovations, algorithmic developments, and practical system implementations. Potential topics include, but are not limited to, the following:

• Spatio-temporal forecasting (traffic, weather, human mobility).
• Generative AI for data augmentation and missing value imputation in spatio-temporal sequences.
• Graph-based representation learning for complex social and sensor networks.
• Next-generation recommendation systems utilizing multi-modal spatio-temporal context.
• Collaborative and Edge Computing optimization for real-time AI tasks.
• Privacy-preserving computation and federated learning in distributed sensing.
• Causal inference and explainable AI (XAI) for spatio-temporal modeling.
• Cross-domain knowledge transfer and lightweight model deployment on IoT devices.

Dr. Zhizhe Lin
Prof. Dr. Teng Zhou
Prof. Dr. Chunjie Cao
Guest Editors

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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics 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 2400 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.

• spatio-temporal data mining
• generative AI & large language models
• representation learning
• recommender systems
• collaborative & edge computing