Recent research indicates that the performance of machine learning model...
Recent studies propose enhancing machine learning models by aligning the...
Hypergraphs are important for processing data with higher-order relation...
Network momentum provides a novel type of risk premium, which exploits t...
We investigate the concept of network momentum, a novel trading signal
d...
We present a novel methodology for modeling and forecasting multivariate...
Certifying the robustness of a graph-based machine learning model poses ...
The increasing availability of graph-structured data motivates the task ...
Graph classification aims to categorise graphs based on their structure ...
Message passing neural networks (MPNNs) have been shown to suffer from t...
Understanding stock market instability is a key question in financial
ma...
Kernels on graphs have had limited options for node-level problems. To
a...
The construction of a meaningful hypergraph topology is the key to proce...
Multi-agent learning has gained increasing attention to tackle distribut...
Strategic interactions between a group of individuals or organisations c...
Dynamic networks are ubiquitous for modelling sequential graph-structure...
We propose a decentralised "local2global"' approach to graph representat...
Most graph neural networks (GNNs) use the message passing paradigm, in w...
While Graph Neural Networks (GNNs) have recently become the de facto sta...
Graph neural networks, a popular class of models effective in a wide ran...
Graph-based models require aggregating information in the graph from
nei...
Learning a graph topology to reveal the underlying relationship between ...
We propose a novel class of graph neural networks based on the discretis...
We propose a decentralised "local2global" approach to graph representati...
Graph-structured data arise in a variety of real-world context ranging f...
Graph neural networks are experiencing a surge of popularity within the
...
The problem of graph learning concerns the construction of an explicit
t...
The effective representation, processing, analysis, and visualization of...
Bayesian optimisation (BO) has been widely used for hyperparameter
optim...
We propose a graph spectrum-based Gaussian process for prediction of sig...
Graph spectral techniques for measuring graph similarity, or for learnin...
We study contextual multi-armed bandit problems in the case of multiple
...
We provide a theoretical analysis of the representation learning problem...
Individuals, or organizations, cooperate with or compete against one ano...
The Data for Refugees (D4R) Challenge is a non-profit challenge initiate...
The construction of a meaningful graph topology plays a crucial role in ...
We present a novel algorithm for learning the spectral density of large ...
Effective information analysis generally boils down to properly identify...
The analysis of large collections of image data is still a challenging
p...
The construction of a meaningful graph plays a crucial role in the succe...
Event detection has been one of the most important research topics in so...
Relationships between entities in datasets are often of multiple nature,...
Observational data usually comes with a multimodal nature, which means t...