资源受限边缘网络中的多源多维信息融合
Multi-Source and Multi-Dimensional Information Fusion in Resource-Constrained Edge Networks
Yushi Wang · Zhengxin Yu · Guhan Zheng · Wang Miao · Merouane Debbah
中文摘要
多源语义信息融合使边缘网络能够利用分布式终端采集的观测数据支持全局推理。然而,通信与计算资源受限制约了语义上传,导致边缘服务器获得的令牌不完整,且在模态、语义粒度、到达时间与信道条件上存在差异。令牌的自身价值还取决于其他终端所提供信息的互补或冗余程度。提出一种多源多维语义信息融合框架,在资源约束下协调终端上传与边缘端融合。设计 Hyper-Slot,通过迭代的令牌到槽位分配(token-to-slot assignment)与槽位到令牌反馈(slot-to-token feedback),将语义内容与可用令牌属性结合,生成用于全局推理的紧凑表示。为激励有效的语义上传,进一步设计基于贡献度的激励机制,利用 Hyper-Slot 分配评估信息覆盖度与跨类型互补性。借助一个双层 Stackelberg-Nash 博弈,服务器在考虑计算与通信能耗的前提下确定奖励池与各终端的传输质量策略。在 COCO2014 三模态扩展数据集与 Flickr30K 图像-文本检索上的实验表明,Hyper-Slot 相比最强基线分别将 mAP 提升 3.66 个百分点、将 RSum 提升 15.9 点,同时较朴素拼接融合基线减少超过 80% 的参数量。
关键要点
- 01问题:边缘网络中通信与计算资源受限,终端上传的语义令牌在模态、粒度、时序、信道等维度上不完整,且各终端贡献存在互补或冗余。
- 02方法:提出多源多维语义融合框架,核心组件 Hyper-Slot 通过令牌-槽位迭代分配与反馈将语义与属性融合为紧凑表示。
- 03激励:基于贡献度的激励机制利用 Hyper-Slot 分配评估覆盖度与跨类型互补性,通过 Stackelberg-Nash 博弈联合优化奖励池与终端传输策略。
- 04结果:在 COCO2014 三模态扩展与 Flickr30K 上 mAP 提升 3.66 个百分点,RSum 提升 15.9 点,参数量较朴素拼接融合基线减少 80% 以上。
- 05局限:摘要未给出对极端资源约束场景与真实边缘部署的鲁棒性分析。
解读
尚无解读。
原始英文摘要
arXiv:2610.13298v1 Announce Type: cross 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.