Sheaf Hypergraph Networks
Dec 10, 2023
Speakers
Iulia Duta
Speaker · 0 followers
Giulia Cassarà
Speaker · 0 followers
Fabrizio Silvestri
Speaker · 0 followers
Pietro Liò
Speaker · 0 followers
About
Higher-order relations are widespread in nature, with numerous phenomena involving complex interactions that extend beyond simple pairwise connections. As a result, advancements in higher-order processing can accelerate the growth of various fields requiring structured data. Current approaches typically represent these interactions using hypergraphs.We enhance this representation by introducing cellular sheaves for hypergraphs, a mathematical construction that adds extra structure to the conventional hypergraph while maintaining their local, higher-order connectivity. Drawing inspiration from existing Laplacians in the literature, we develop two unique formulations of sheaf hypergraph Laplacians: linear and non-linear. Our theoretical analysis demonstrates that incorporating sheaves into the hypergraph Laplacian provides a more expressive inductive bias than standard hypergraph diffusion, creating a powerful instrument for effectively modelling complex data structures.We employ these sheaf hypergraph Laplacians to design two categories of models: Sheaf Hypergraph Neural Networks and Sheaf Hypergraph Convolutional Networks. These models generalize classical Hypergraph Networks often found in the literature. Through extensive experimentation, we show that this generalization significantly improves performance, achieving top results on multiple benchmark datasets for hypergraph node classification.Higher-order relations are widespread in nature, with numerous phenomena involving complex interactions that extend beyond simple pairwise connections. As a result, advancements in higher-order processing can accelerate the growth of various fields requiring structured data. Current approaches typically represent these interactions using hypergraphs.We enhance this representation by introducing cellular sheaves for hypergraphs, a mathematical construction that adds extra structure to the convent…
Organizer
NeurIPS 2023
Account · 648 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Variational Gaussian Processes For Linear Inverse Problems
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Generative al for Structure-Based Drug Design
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Bayes beats Cross Validation: Efficient and Accurate Ridge Regression via Expectation Maximization
Watch later
Shu Yu Tew, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Weakly-Semi-Supervised Object Detection in Remotely Sensed Imagery
Watch later
Ji Hun Wang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination
Watch later
Yuchen Bai, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%