Directed Scattering for Knowledge Graph-based Cellular Signaling Analysis
This work addresses the challenge of effectively leveraging directed and hierarchical properties in scientific knowledge graphs for cellular signaling analysis, representing an incremental improvement over existing methods.
The paper tackled the problem of learning from directed graphs with hierarchical structure, such as cellular signaling networks, by proposing a Directed Scattering Autoencoder (DSAE) that outperformed other methods on tasks like embedding directed graphs and learning cellular signaling networks.
Directed graphs are a natural model for many phenomena, in particular scientific knowledge graphs such as molecular interaction or chemical reaction networks that define cellular signaling relationships. In these situations, source nodes typically have distinct biophysical properties from sinks. Due to their ordered and unidirectional relationships, many such networks also have hierarchical and multiscale structure. However, the majority of methods performing node- and edge-level tasks in machine learning do not take these properties into account, and thus have not been leveraged effectively for scientific tasks such as cellular signaling network inference. We propose a new framework called Directed Scattering Autoencoder (DSAE) which uses a directed version of a geometric scattering transform, combined with the non-linear dimensionality reduction properties of an autoencoder and the geometric properties of the hyperbolic space to learn latent hierarchies. We show this method outperforms numerous others on tasks such as embedding directed graphs and learning cellular signaling networks.