TY - GEN
T1 - DIRECTED SCATTERING FOR KNOWLEDGE GRAPH-BASED CELLULAR SIGNALING ANALYSIS
AU - Venkat, Aarthi
AU - Chew, Joyce
AU - Rodriguez, Ferran Cardoso
AU - Tape, Christopher J.
AU - Perlmutter, Michael
AU - Krishnaswamy, Smita
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - biological networks
KW - directed graphs
KW - geometric scattering
KW - graph signal processing
KW - hyperbolic geometry
UR - http://www.scopus.com/inward/record.url?scp=85195378540&partnerID=8YFLogxK
U2 - 10.1109/ICASSP48485.2024.10446530
DO - 10.1109/ICASSP48485.2024.10446530
M3 - Conference contribution
AN - SCOPUS:85195378540
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 9761
EP - 9765
BT - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Y2 - 14 April 2024 through 19 April 2024
ER -