As with any new field, the best practices for constructing and analysing brain networks are still evolving. Among recent developments is the understanding that brain networks are fundamentally multi-scale entities (Bassett and Siebenhuhner, 2013). The meaning of “scale” can vary depending on context; here we focus on three possible definitions relevant to the study of brain networks. First, a network's spatial scale refers to the granularity at which its nodes and edges are defined and can range from that of individual cells and synapses (Jarrell et al., 2012, Shimono and Beggs, 2015, Schroeter et al., 2015, Lee et al., 2016) to brain regions and large-scale fiber tracts (Bullmore and Bassett, 2011). Second, networks can be characterized over temporal scales with precision ranging from sub-millisecond (Khambhati et al., 2015, Burns et al., 2014) to that of the entire lifespan (Zuo et al., 2010, Betzel et al., 2014, Gu et al., 2015b), to evolutionary changes across different species (van den Heuvel et al., 2016). Finally, networks can be analyzed at different topological scales ranging from individual nodes to the network as a whole (Stam and Reijneveld, 2007, Bullmore and Sporns, 2009, Rubinov and Sporns, 2010). Collectively, these scales define the axes of a three-dimensional space in which any analysis of brain network data lives (Fig. 1). Most brain network analyses exist as points in this space—i.e. they focus on networks defined singularly at one spatial, temporal, and topological scale. We argue that, while such studies have proven illuminating, in order to better understand the brain's true multi-scale, multi-modal nature, it is essential that our network analyses begin to form bridges that link different scales to one another.