[论文解读] Collective Intelligence for Deep Learning: A Survey of Recent Developments

David Ha, Yujin Tang|arXiv (Cornell University)|Nov 29, 2021

Cellular Automata and Applications参考文献 54被引用 6

一句话总结

本综述探讨了集体智能原则（如自组织、群体行为和涌现动力学）如何解决深度学习中的根本性局限，包括鲁棒性差、适应性不足以及环境假设僵化等问题。通过整合复杂系统领域的思想，本文提出一种范式转变，即通过去中心化、基于交互的学架构，构建更具韧性、适应性和可扩展性的人工智能系统。

ABSTRACT

In the past decade, we have witnessed the rise of deep learning to dominate the field of artificial intelligence. Advances in artificial neural networks alongside corresponding advances in hardware accelerators with large memory capacity, together with the availability of large datasets enabled practitioners to train and deploy sophisticated neural network models that achieve state-of-the-art performance on tasks across several fields spanning computer vision, natural language processing, and reinforcement learning. However, as these neural networks become bigger, more complex, and more widely used, fundamental problems with current deep learning models become more apparent. State-of-the-art deep learning models are known to suffer from issues that range from poor robustness, inability to adapt to novel task settings, to requiring rigid and inflexible configuration assumptions. Collective behavior, commonly observed in nature, tends to produce systems that are robust, adaptable, and have less rigid assumptions about the environment configuration. Collective intelligence, as a field, studies the group intelligence that emerges from the interactions of many individuals. Within this field, ideas such as self-organization, emergent behavior, swarm optimization, and cellular automata were developed to model and explain complex systems. It is therefore natural to see these ideas incorporated into newer deep learning methods. In this review, we will provide a historical context of neural network research's involvement with complex systems, and highlight several active areas in modern deep learning research that incorporate the principles of collective intelligence to advance its current capabilities. We hope this review can serve as a bridge between the complex systems and deep learning communities.

研究动机与目标

• 识别当前深度学习中的核心局限，如脆弱性、泛化能力差以及配置假设僵化。
• 研究集体智能（强调自组织、涌现和去中心化交互）如何解决这些局限。
• 通过突出共享原则和新兴协同效应，弥合复杂系统研究与深度学习之间的鸿沟。
• 综述近期将集体智能机制（如自对弈、模块化智能体和细胞自动机启发架构）融入深度学习的进展。
• 倡导从工程式神经网络设计转向更具适应性、涌现性和韧性的学习系统。

提出的方法

• 调研整合了集体智能概念（如自组织、群体优化和细胞自动机）的近期深度学习研究。
• 分析支持去中心化、多智能体交互的架构，如多智能体强化学习和自对弈训练。
• 研究受生物和物理系统启发的神经网络中的涌现行为，包括模块化和可重构智能体设计。
• 回顾通过局部交互而非集中控制或刚性架构来提升鲁棒性和适应性的方法。
• 强调具身认知和环境交互在实现无需显式微调的适应性行为中的作用。
• 映射深度学习与复杂系统理论之间的联系，特别是在可扩展、可泛化人工智能的语境下。

实验结果

研究问题

• RQ1 集体智能原则如何提升深度学习模型的鲁棒性和适应性？
• RQ2 多智能体系统中的自组织和涌现行为在何种方式下能超越标准训练分布实现更好的泛化？
• RQ3 深度学习中哪些架构和训练机制最接近集体智能现象（如群体行为或细胞自动机）？
• RQ4 深度学习如何摆脱僵化的工程化架构，转向更动态、自组织的系统，以模仿自然群体？
• RQ5 去中心化、局部交互在实现人工智能体中可扩展且可泛化的智能中扮演何种角色？

主要发现

• 自组织和涌现行为等集体智能原则可显著提升模型对对抗性扰动和分布偏移的鲁棒性。
• 自对弈和多智能体训练方案使智能体能够在无需显式奖励设计或固定架构的情况下发展出适应性策略。
• 受生物模块性启发的模块化与可重构智能体系统，支持渐进式适应与自组装，克服了固定架构模型的局限。
• 细胞自动机启发的架构通过基于局部规则的交互，展现出涌现的模式形成与计算能力，为可扩展学习开辟新路径。
• 具身认知与环境交互的整合使智能体能够在不重新训练的情况下泛化到新任务场景。
• 当前的深度学习系统通常依赖工程密集型、僵化的流水线；集体智能为构建更具适应性、韧性与泛化能力的人工智能系统提供了新路径。