发表机构
University of Arizona; Old Dominion University; InterDigital（亚利桑那大学; 奥多明尼昂大学; InterDigital公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多模态边缘推理的通信开销与延迟问题，提出CST框架，仅传输辅助设备与主设备表征互补的稀疏特征，在低特征传输占比下实现最优任务性能，且端到端推理速度最高提升4.27倍。
AI 中文摘要
协作式多模态推理通过融合分布式传感设备的观测结果提升边缘感知能力，但传输高维辅助表征会产生大量通信开销，还可能导致端到端延迟过高。现有通信高效方法通过压缩、语义编码或特征选择减少负载，但通常仅优化紧凑性或任务相关性，未明确考虑主设备已表征的信息，因此与任务相关但冗余的辅助特征仍会消耗带宽。本文提出协作式选择性传输（Collaborative Selective Transmission，CST），这是一种主设备主导的查询-响应框架，仅检索与当前主表征互补的辅助信息。受部分信息分解和多视图冗余假设启发，CST学习样本自适应、辅助设备特有的稀疏检索支持，同时阻止检索主设备已覆盖或辅助设备间重复的语义。推理时，主设备仅传输支持索引，各辅助设备返回对应隐值，避免密集辅助特征交换。在三个真实多模态传感基准测试中，CST传输的辅助特征值占比不超过14.18%，同时在评估方法中实现了最优或接近最优的任务性能。在5节点NVIDIA Jetson Orin Nano测试平台上，5至100 Mbps带宽下的实验显示，其端到端推理速度相比全传输（Transmit-All）最高提升4.27倍，证实了实际端到端延迟的降低效果。
英文摘要
Collaborative multimodal inference improves edge perception by combining observations from distributed sensing devices, but transmitting high-dimensional helper representations incurs substantial communication overhead and can lead to high end-to-end latency. Existing communication-efficient methods reduce payloads through compression, semantic coding, or feature selection, yet typically optimize compactness or task relevance without explicitly accounting for information already represented at the main device. Consequently, task-relevant but redundant helper features may still consume bandwidth. We present Collaborative Selective Transmission (CST), a main-directed query--response framework that retrieves only helper information complementary to the current main representation. Inspired by Partial Information Decomposition and the Multiview Redundancy Assumption, CST learns sample-adaptive, helper-specific sparse retrieval supports while discouraging retrieval of semantics already covered by the main device or duplicated across helpers. During inference, the main device transmits only support indices, and each helper returns the corresponding latent values, avoiding dense helper-feature exchange. Across three real-world multimodal sensing benchmarks, CST transmits no more than 14.18% of helper feature values while achieving best or near-best task performance among the evaluated methods. Experiments on a five-node NVIDIA Jetson Orin Nano testbed across 5--100 Mbps demonstrate up to a $4.27\times$ speedup over Transmit-All in end-to-end inference, confirming practical end-to-end latency reductions.
Comments11 pages, 6 figures, 6 tables
