Relational inductive biases, deep learning, and graph networks
打开互动全文版（逐段中英对照 + 图/公式 + 论文问答）→人工智能最近经历了一次复兴，在视觉、语言、控制和决策等关键领域取得了重大进展。这在一定程度上得益于廉价的数据和计算资源，这些资源契合了深度学习的天然优势。然而，人类智能的许多决定性特征——这些特征是在截然不同的压力下发展起来的——对于当前的方法来说仍然遥不可及。特别是，超越自身经验进行泛化——这是从婴儿期起人类智能的标志——对现代人工智能来说仍然是一个艰巨的挑战。本文兼具立场论文、综述和统一框架的性质。我们认为，组合泛化必须是人工智能实现类人能力的首要任务，而结构化表示和计算是实现这一目标的关键。正如生物学合作利用先天和后天一样，我们拒绝在“手工工程”和“端到端”学习之间做出错误选择，而是倡导一种受益于它们互补优势的方法。我们探讨了如何在深度学习架构中使用关系归纳偏置来促进对实体、关系及其组合规则的学习。我们为人工智能工具箱提出了一种具有强关系归纳偏置的新构建块——图网络——它概括并扩展了多种在图上操作的神经网络方法，并提供了一个直观的接口来操作结构化知识和产生结构化行为。我们讨论了图网络如何支持关系推理和组合泛化，为更复杂、可解释和灵活的推理模式奠定基础。作为本文的配套，我们发布了一个用于构建图网络的开源软件库，并演示了如何在实践中使用它们。
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part unification. We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Just as biology uses nature and nurture cooperatively, we reject the false choice between "hand-engineering" and "end-to-end" learning, and instead advocate for an approach which benefits from their complementary strengths. We explore how using relational inductive biases within deep learning architectures can facilitate learning about entities, relations, and rules for composing them. We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization, laying the foundation for more sophisticated, interpretable, and flexible patterns of reasoning. As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.