Test-Time Collaborative Classification over Multi-Agent Networks

2026-08-25

AI Summary

研究提出一种多智能体网络分布式二分类协作框架，通过独立训练模型在测试时交换本地决策统计来协同预测，探讨了通信预算和学习规则下的性能。

Abstract

The increasing heterogeneity of multi-agent systems poses significant challenges for jointly training a global model across agents. At the same time, cooperative inference between agents has long been recognized as a powerful mechanism for distributed decision making over networks. Motivated by these observations, we propose a collaboration framework for distributed binary classification over multi-agent networks, where a set of independently trained agents, potentially differing in architecture, feature space, or modality, coordinate their actions during test time to form collective predictions. This coordination is achieved by exchanging local decision statistics through a distributed learning protocol. We develop a theoretical and experimental study of this independent training and cooperative inference paradigm, and examine its performance under different communication budgets and distributed learning rules. We establish classification error guarantees under sufficient, finite-round, and finite-precision communication, together with PAC-style generalization bounds. These results capture the influence of model heterogeneity, network topology, combination policy, and communication constraints on prediction accuracy. Taken together with the experimental results, they reveal both the price of independent training and the benefit of collective prediction for the proposed distributed decision making framework with models learned from data.

Problem

• multi-agent networks
• distributed binary classification
• independent training
• cooperative inference
• communication constraints

Innovation

• Distributed Binary Classification
• Multi-Agent Networks
• Test-Time Collaboration
• Independent Training
• Cooperative Inference