Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent
years owing to their capability to model and learn from graph-structured data. Such an ability …

Improving the efficiency of algorithms for fundamental computations can have a widespread
impact, as it can affect the overall speed of a large amount of computations. Matrix …

This paper presents a new Graph Neural Network (GNN) type using feature-wise linear
modulation (FiLM). Many standard GNN variants propagate information along the edges of a …

We present GRIP, a graph neural network accelerator architecture designed for low-latency
inference. Accelerating GNNs is challenging because they combine two distinct types of …

Graph Neural Networks (GNNs) have attracted increasing research interest for their
remarkable capability to model graph-structured knowledge. However, GNNs suffer from …

Deep graph generative modeling has proven capable of learning the distribution of complex,
multi-scale structures characterizing real-world graphs. However, one of the main limitations …

The sparse representation of graphs has shown great potential for accelerating the
computation of graph applications (eg, social networks and knowledge graphs) on …

We propose a HW-SW co-optimization technique to perform energy-efficient spGEMM
operations for deep learning. First, we present an automated pruning algorithm, named …

This thesis proposes novel approaches for machine learning on irregularly structured input
data such as graphs, point clouds and manifolds. Specifically, we are breaking up with the …

Graph neural networks (GNNs) are a powerful approach for machine learning on graph
datasets. Such datasets often consist of millions of modestly-sized graphs, making them well …