Article

Generalization as diffusion: human function learning on graphs

2019-02-03

Abstract excerpt

From social networks to public transportation, graph structures are a ubiquitous feature of life. Yet little is known about how humans learn functions on graphs, where relationships are defined by the connectivity structure. We adapt a Bayesian framework for function learning to graph structures, and propose that people perform generalization by diffusing observed function values across the graph. We test the pred...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: b9b296f3-6cee-5fa6-be8a-91316164212d
DOI: 10.1101/538934

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Generalization as diffusion: human function learning on graphsDOI 10.1101/538934Read

Searching for rewards in graph-structured spacesSemantic proximity Read

Towards a unifying theory of generalizationSemantic proximity Read

Inference and search on graph-structured spacesSemantic proximity Read

Generalizing Functions in Sparse DomainsSemantic proximity Read

Learning from oneself: Function learning with self-generated samplesSemantic proximity Read

Similarities and differences in spatial and non-spatial cognitive mapsSemantic proximity Read

Transferring structural knowledge across cognitive maps in humans and modelsSemantic proximity Read

Connecting conceptual and spatial search via a model of generalizationSemantic proximity Read

Finding structure in multi-armed banditsSemantic proximity Read

Learning the determinants of human behaviorSemantic proximity Read

Inferences on a Multidimensional Social Hierarchy Use a Grid-like CodeSemantic proximity Read

Generalizing to generalize: when (and when not) to be compositional in task structure learningSemantic proximity Read