Collaborative Edge Inference via Semantic Grouping under Wireless Channel Constraints

2025-10-02

AI Summary

To address the trade-off between communication overhead and classification accuracy in edge-device collaborative inference under wireless channel constraints, this paper proposes a semantic-grouping collaborative inference framework based on a key-value mechanism. The method enables adaptive selection of collaborating nodes and channel-aware semantic-level feature compression through intermediate feature exchange, selective information transmission, key-value matching, and communication pruning. A key insight is that query transmission requires higher reliability than feature transmission to ensure robust collaborative inference. Experiments demonstrate that the approach reduces bandwidth consumption by up to 62% while maintaining high classification accuracy (error increase <1.2%) and exhibiting strong robustness against channel noise and bit errors. Thus, it significantly enhances inference efficiency and generalization capability in resource-constrained edge environments.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

In this paper, we study the framework of collaborative inference, or edge ensembles. This framework enables multiple edge devices to improve classification accuracy by exchanging intermediate features rather than raw observations. However, efficient communication strategies are essential to balance accuracy and bandwidth limitations. Building upon a key-query mechanism for selective information exchange, this work extends collaborative inference by studying the impact of channel noise in feature communication, the choice of intermediate collaboration points, and the communication-accuracy trade-off across tasks. By analyzing how different collaboration points affect performance and exploring communication pruning, we show that it is possible to optimize accuracy while minimizing resource usage. We show that the intermediate collaboration approach is robust to channel errors and that the query transmission needs a higher degree of reliability than the data transmission itself.

Problem

• Optimizing collaborative edge inference under wireless bandwidth constraints
• Analyzing channel noise impact on feature communication reliability
• Balancing accuracy and resource usage through strategic collaboration points

Innovation

• Exchanging intermediate features for accuracy improvement
• Using key-query mechanism for selective information exchange
• Optimizing collaboration points under channel constraints