Edge networks fuse multi-source data under resource limits
Multi-Source and Multi-Dimensional Information Fusion in Resource-Constrained Edge Networks
Distributed, Parallel, and Cluster ComputingComputer Vision and Pattern Recognition
Summary
Edge networks try to combine information from many devices to make smarter decisions. But because these devices can only send limited data and have different types of information, the edge server gets an incomplete picture. The authors propose a system called Hyper-Slot that smartly groups and mixes these data pieces to create a clearer overall view. They also set up a reward system so devices send the most useful information while balancing their energy and connection limits. Tests show their approach improves performance and reduces complexity compared to older methods.
What this means in practice
- •For edge network engineers: Optimize data fusion in systems where edge servers must infer from limited multi-device inputs improving accuracy without increasing resource use.
- •For mobile device developers: Design device transmission protocols that maximize useful semantic content uploaded under energy and bandwidth constraints using contribution-based rewards.
Authors
Yushi Wang, Zhengxin Yu, Guhan Zheng, Wang Miao, Merouane Debbah
Abstract
Multi-source semantic information fusion enables edge networks to support global inference using observations collected by distributed terminals. However, limited communication and computation resources restrict semantic uploading, leaving the edge server with incomplete tokens that differ in modality, semantic granularity, arrival time, and channel condition. The value of these tokens also depends on the complementary or redundant information provided by other terminals. In this paper, we propose a multi-source and multi-dimensional semantic information fusion framework that coordinates terminal uploading and edge-side fusion under resource constraints. We develop Hyper-Slot to combine semantic content with available token attributes through iterative token-to-slot assignment and slot-to-token feedback, producing a compact representation for global inference. To encourage useful semantic uploading, we further design a contribution-based incentive mechanism that uses Hyper-Slot assignments to evaluate information coverage and cross-type complementarity. A bi-level Stackelberg-Nash game determines the server reward pool and terminal transmission-quality strategies while accounting for computation and communication energy costs. Experiments on a tri-modal extension of COCO2014 and image-text retrieval on Flickr30K show that Hyper-Slot improves mAP by 3.66 percentage points and RSum by 15.9 points over the strongest evaluated baselines, respectively, while reducing the number of parameters by more than 80% compared with a naive concatenation-based fusion baseline.