5 papers
The Logical Expressiveness of Topological Neural Networks
Amirreza Akbari, Amauri H. Souza, Vikas Garg
Graph neural networks (GNNs) are the standard for learning on graphs, yet they have limited expressive power, often expressed in terms of the Weisfeiler-Leman (WL) hierarchy or wit…
On topological descriptors for graph products
Mattie Ji, Amauri H. Souza, Vikas Garg
Topological descriptors have been increasingly utilized for capturing multiscale structural information in relational data. In this work, we consider various filtrations on the (bo…
Graph Persistence goes Spectral
Mattie Ji, Amauri H. Souza, Vikas Garg
Including intricate topological information (e.g., cycles) provably enhances the expressivity of message-passing graph neural networks (GNNs) beyond the Weisfeiler-Leman (WL) hiera…
Employing Federated Learning for Training Autonomous HVAC Systems
Fredrik Hagström, Vikas Garg, Fabricio Oliveira
Buildings account for 40% of global energy consumption. A considerable portion of building energy consumption stems from heating, ventilation, and air conditioning (HVAC), and thus…
Algebraic Positional Encodings
Konstantinos Kogkalidis, Jean-Philippe Bernardy, Vikas Garg
We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches. Our framework provides a flexible…