多智能体学习与合作驱动的优化动力学

中文摘要 AI 辅助

通过反向传播训练的多层人工神经网络是许多更复杂分类算法的基本组成部分。它们的优势在于能够以任意精度实现任何函数。这一结果是以需要优化的大量参数为代价的。在这项工作中，我们提出了一种合作机制，即多个人工神经网络之间的信息交换，其目标是在保持性能的同时降低模型复杂度。更具体地说，我们考虑几个“小型”智能体，即包含的参数少于参考“大型”智能体，在训练过程中通过将它们的预测信息纳入损失函数来共享预测，从而直接影响权重更新。我们考虑了实现合作的几种策略，例如投票者模型、多数模型以及基于智能体对其预测置信度的加权平均模型。我们在几个标准基准上数值比较了这些策略的准确性。我们的结果支持这样的主张：在给定的分类任务中，几个小型智能体可以胜过单个大型模型；共享信号通过调节下降方向和步长来影响每个智能体的优化算法，从而收敛到全局共识。所提出的概念验证显著减少了需要训练的参数数量，同时保持了可比较的性能，从而限制了计算资源的使用。

英文摘要

Multilayer Artificial Neural Networks trained via backpropagation are the basic blocks of many, more complex, classification algorithms. Their strength lies in the possibility of realizing, with arbitrary precision, any function. This result comes at the cost of the large number of involved parameters to be optimized. In this work, we propose a mechanism for cooperation, i.e., information exchange among several artificial neural networks, with the goal of reducing model complexity while maintaining performance. More precisely, we consider several "small" agents, i.e., containing fewer parameters than a reference "large" one, that during training share their predictions by incorporating this information into the loss function and thus directly influence weight updates. We consider several strategies for implementing cooperation, e.g., the voter model, majority model, and weighted average model based on an agent's confidence in its prediction. We numerically compare the accuracy of those strategies on several standard benchmarks. Our results support the claim that several small agents can outperform a single large model on a given classification task; the shared signals affect each agent's optimization algorithm by modulating both the descent direction and the step size, converging toward a global consensus. The proposed proof-of-concept significantly reduces the number of parameters to be trained while preserving comparable performance, thereby limiting computational resource usage.

发表机构

• University of Namur（那慕尔大学）
• Institute of Technology of Cambodia（柬埔寨理工学院）

机构由 AI 辅助整理，请以论文原文为准。