Deep Learning and Machine Learning has made breakthroughs in recent years. There is tens of billions of dollars going into development of the new AI.
Google and Deep Mind are recognizing that Deep Learning is not going to reach human cognition. They propose using models of networks to find relations between things to enable computers to generalize more broadly about the world.
Deep learning faces challenges in complex language and scene understanding, reasoning about structured data, transferring learning beyond the training conditions, and learning from small amounts of experience. These challenges demand combinatorial generalization, and so it is perhaps not surprising that an approach which eschews compositionality and explicit structure
struggles to meet them.
A key path forward for modern AI is to commit to combinatorial generalization as a top priority, and we advocate for integrative approaches to realize this goal.
Neural networks that operate on graphs, and structure their computations accordingly, have been developed and explored extensively for more than a decade under the umbrella of “graph neural networks”.
They have a new graph networks framework, which generalizes and extends several lines of work in this area.
They define a class of functions for relational reasoning over graph-structured representations.
They are excited about the potential impacts that graph networks can have, they caution that
these models are only one step forward. Realizing the full potential of graph networks will likely be far more challenging than organizing their behavior under one framework, and indeed, there are a number of unanswered questions regarding the best ways to use graph networks.
Graphs are not able to express everything. Notions like recursion, control flow, and conditional iteration are not straightforward to represent with graphs, and, minimally, require additional assumptions.
Other structural forms will be needed like imitations of computer-based structures, including registers, memory I/O controllers, stacks, queues and others.
Recent advances in AI, propelled by deep learning, have been transformative across many important domains. Despite this, a vast gap between human and machine intelligence remains, especially with respect to efficient, generalizable learning. They argue for making combinatorial generalization a top priority for AI, and advocate for embracing integrative approaches which draw on ideas from human cognition, traditional computer science, standard engineering practice, and modern deep learning.
They explored flexible learning-based approaches which implement strong relational inductive biases to capitalize on explicitly structured representations and computations, and presented a framework called graph networks, which generalize and extend various recent approaches for neural networks applied to graphs. Graph networks are designed to promote building complex architectures using customizable graph-to-graph building blocks, and their relational inductive biases promote combinatorial generalization and improved sample efficiency over other standard machine learning building blocks.
Despite their benefits and potential, however, learnable models which operate on graphs are only a stepping stone on the path toward human-like intelligence. They are optimistic about a number of other relevant, and perhaps underappreciated, research directions, including marrying learning-based approaches with programs, developing model-based approaches with an emphasis on abstraction investing more heavily in meta-learning, and exploring multi-agent learning and interaction as a key catalyst for advanced intelligence. These directions each involve rich notions of entities, relations, and combinatorial generalization, and can potentially benefit, and benefit from, greater interaction with approaches for learning relational reasoning over explicitly structured representations.
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.