arXiv cs.AI· Sicong Liu, Fengmin Wu, Yuan Gao, Bin Guo, Zimu Zhou, Hongkai Wen, Zhiwen Yu·· 56 分钟前AI 评分35
AdaFlowLite:面向异步移动数据的可扩展非阻塞推理框架
AdaFlowLite: Scalable and Non-blocking Inference on Asynchronous Mobile Data
AI 导读
AdaFlowLite 提出针对异步分布式多模态移动数据的"机会式"推理,部分数据到达即开始推理,避免等待慢数据造成的延迟或直接推理导致的精度下降。该方法用层次化分析归一化矩阵刻画跨模态亲和性,并借助轻量级多模态 Swin Transformer(MMLST)实现免重训的实时数据补全。实验显示推理延迟最高降低 80.4%,精度最高提升 62.1%,能耗减少近 50%,优于现有方法。
正文 · 原文
Abstract:The rise of mobile devices equipped with numerous sensors, such as LiDAR and cameras, has driven the adoption of multi-modal deep intelligence for distributed sensing tasks, such as smart cabins and driving assistance. However, the arrival time of mobile sensory data vary due to modality size and network dynamics, which can lead to delays (if waiting for slow data) or accuracy decline (if inference proceeds without waiting). Moreover, the diversity and dynamic nature of mobile systems exacerbate this challenge. In response, we present a shift to \textit{opportunistic} inference for asynchronous distributed multi-modal data, enabling inference as soon as partial data arrives. While existing methods focus on optimizing modality consistency and complementarity, known as modal affinity, they lack a \textit{computational} approach to control this affinity in open-world mobile environments. % \sysname pioneers the formulation of structured cross-modality affinity in mobile contexts using a hierarchical analysis-based normalized matrix. This approach accommodates the diversity and dynamics of modalities, generalizing across different types and numbers of inputs. Employing an multi-modal lightweight Swin Transformer (MMLST), \sysname facilitates real-time and flexible data imputation, adapting to various modalities and downstream tasks without retraining. Experiments show that \sysname significantly reduces inference latency by up to 80.4\% and enhances accuracy by up to 62.1\%, while achieving nearly a 50\% reduction in energy consumption, outperforming status quo approaches. Also, this method can enhance LLM performance to preprocess asynchronous data.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.21691 [cs.LG] |
| (or arXiv:2611.21691v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21691 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.1109/TMC.2025.3582060
DOI(s) linking to related resources |
Submission history
From: Fengmin Wu [view email]
[v1]
Mon, 16 Nov 2026 07:55:57 UTC (7,647 KB)
来源:arXiv cs.AI · arxiv.org