Analysis of social networks has the potential to provide insight into a wide range of applications. As datasets grow, a key challenge is the lack of existing truth models. Unlike traditional signal processing, where models of truth and background data exist and are often well defined, these models are commonly lacking for social networks. This paper presents a transdisciplinary approach of mitigating this challenge by leveraging research on scientific innovation together with a novel Signal Processing for Graphs (SPG) algorithmic framework. The results suggest new ways for the study of innovation patterns in publication networks.