Machine learning has revolutionized many fields, including science, healthcare, and business. It is also widely used in network data analysis. This chapter provides an overview of machine learning methods and how they can be applied to network data. Machine learning can be used to clean, process, and analyze network data, as well as make predictions about networks and network attributes. Methods that transform networks into meaningful representations are especially useful for specific network prediction tasks, such as classifying nodes and predicting links. The challenges of using machine learning with network data include recognizing data leakage and detecting dataset shift. As with all machine learning, effective use of machine learning on networks depends on practicing good data hygiene when evaluating a predictive model’s performance.

This chapter seeks to resolve the puzzle of people’s low accuracy in perceptions of local network properties versus their much higher accuracy in perceiving global network structures. We argue that this puzzle is more apparent than real because humans rely on layers of relational schemata—mental structures dictating how social agents ought to be structurally connected—to mentally organize their social contacts. In other words, differences in accuracy reflect differences in the schemata used by the individual to mentally represent social network information at varying levels (e.g., dyadic level, triadic level, and community level). Individuals vary in their schemata repertoire, and their tendencies to adopt certain schemata in a given situation or context, so the specific set of schemata that individuals activate varies in its sufficiency and appropriateness for fully representing the network structure. We define these individual differences as network representation capacities, and review and compare four prominent approaches to quantifying them: the error paradigm, the free-recall paradigm, the structural learning paradigm and the statistical learning paradigm. We conclude by inviting researchers to reconsider the relations between cognition and egocentric networks, as well as the role of network analysis in analyzing, describing and prescribing social relational behavior.