Weakly supervised grounded image captioning (WSGIC) aims to generate the...
This thesis presents a local-to-global perspective on graph neural netwo...
Graph Transformer (GT) recently has emerged as a new paradigm of graph
l...
The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that...
Although theoretical properties such as expressive power and over-smooth...
The IARAI competition Traffic4cast 2021 aims to predict short-term city-...
Message-passing neural networks (MPNNs) are the leading architecture for...
We present a SE(3)-equivariant graph neural network (GNN) approach that
...
As large-scale graphs become increasingly more prevalent, it poses
signi...
In this paper, the process of forecasting household energy consumption i...
Graph Neural Networks (GNNs) have achieved a lot of success on
graph-str...
An augmented metric space is a metric space (X, d_X) equipped with a
fun...
Recently many efforts have been made to incorporate persistence diagrams...
Knowledge graph embedding has recently become a popular way to model
rel...
The study focuses on estimating and predicting time-varying origin to
de...
Traffic control optimization is a challenging task for various traffic
c...
Predicting traffic incident duration is a major challenge for many traff...
Graphs are a natural abstraction for many problems where nodes represent...
Graphs are complex objects that do not lend themselves easily to typical...