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.
Our work presents a foundation for assessing the impact of homophilic and heterophilic behaviour on minorities in social networks.
Social networks are comprised of individuals with a variety of attributes, such as race, age, educational background, or gender.
Browse some of our latest publications spanning a wide range of core AI disciplines.
Project Debater is the first AI system that can debate humans on complex topics.
Commonly, these attributes are distributed unequally in the population.
For example, in many schools across the United States and Europe, Asian or Black students form a minority.