Mixed-integer optimisation of graph neural networks for computer-aided molecular design

ReLU neural networks have been modelled as constraints in mixed integer linear programming (MILP), enabling surrogate-based optimisation in various domains and efficient solution of machine learning certification problems. However, previous works are mostly limited to MLPs. Graph neural networks (GNNs) can learn from non-euclidean data...

Multi-class Trajectory Prediction in Urban Traffic using the View-of-Delft Dataset

Critical to the safe application of autonomous vehicles is the ability to accurately predict the future motion of agents surrounding the vehicle. This is especially important - and challenging - in urban traffic, where vehicles share the road with Vulnerable Road Users (VRUs) such as pedestrians and cyclists. However, the majority of the...

On leveraging physical knowledge to augment neural network-based surrogate models for simulations

The computational cost of high-fidelity engineering simulations, for example CFD, is prohibitive if the application requires frequent design iterations or even fully fledged optimization. A popular way to reduce the computational cost and enable fast iteration cycles is to use surrogate models that are trained to predict simulation results from...

Graph Neural Networks for Intelligent Transportation Systems: A Survey

Graph neural networks (GNNs) have been extensively used in a wide variety of domains in recent years. Owing to their power in analyzing graph-structured data, they have become broadly popular in intelligent transportation systems (ITS) applications as well. Despite their widespread applications in different transportation domains, there is no...

A hybrid deep-learning-metaheuristic framework for bi-level network design problems

This study proposes a hybrid deep-learning-metaheuristic framework with a bi-level architecture for road network design problems (NDPs). We train a graph neural network (GNN) to approximate the solution of the user equilibrium (UE) traffic assignment problem and use inferences made by the trained model to calculate fitness function...

Mixed Integer (Non-) Linear Programming Formulations of Graph Neural Networks

Recently, ReLU neural networks have been modelled as constraints in mixed integer linear programming (MILP) enabling surrogate-based optimisation in various domains as well as efficient solution of machine learning verification problems. However, previous works have been limited to multilayer perceptrons (MLPs). The Graph Convolutional Neural...

Self-Supervised Few Shot Learning: Prototypical Contrastive Learning with Graphs

A primary trait of humans is the ability to learn rich representations and relationships between entities from just a handful of examples without much guidance. Unsupervised few-shot learning is an undertaking aimed at reducing this fundamental gap between smart human adaptability and machines. We present a contrastive learning scheme for...

Label-Only Membership Inference Attack against \\Node-Level Graph Neural Networks

Graph Neural Networks (GNNs), inspired by Convolutional Neural Networks (CNNs), aggregate the message of nodes' neighbors and structure information to acquire expressive representations of nodes for node classification, graph classification, and link prediction. Previous studies have indicated that node-level GNNs are vulnerable to Membership...

Streaming Graph Embeddings via Incremental Neighborhood Sketching

Graph embeddings have become a key paradigm to learn node representations and facilitate downstream graph analysis tasks. Many real-world scenarios such as online social networks and communication networks involve streaming graphs, where edges connecting nodes are continuously received in a streaming manner, making the underlying graph...

Side-channel analysis with graph neural networks

In cyber security, side-channel attacks (SCA) are of interest because they target the vulnerabilities in implementation rather than inherent vulnerabilities in the algorithm. Profiled SCA is especially interesting as it assumes that the adversary has unlimited access to a clone device that can generate sufficient traces to create a profile of...

GReS: Workshop on graph neural networks for recommendation and search

Graph neural networks (GNNs) have recently gained significant momentum in the recommendation community, demonstrating state-of-the-art performance in top-k recommendation and next-item recommendation. Despite promising results on GNN-based recommendation and search, most of the current GNN research remains essentially concentrated on more...

Graph-time convolutional neural networks

Spatiotemporal data can be represented as a process over a graph, which captures their spatial relationships either explicitly or implicitly. How to leverage such a structure for learning representations is one of the key challenges when working with graphs. In this paper, we represent the spatiotemporal relationships through product graphs...

Nonlinear State-Space Generalizations of Graph Convolutional Neural Networks

Graph convolutional neural networks (GCNNs) learn compositional representations from network data by nesting linear graph convolutions into nonlinearities. In this work, we approach GCNNs from a state-space perspective revealing that the graph convolutional module is a minimalistic linear state-space model, in which the state update matrix is...

Identifying Author Fingerprints in Texts via Graph Neural Networks

The world is generating more and more network data in many different areas (e.g., sensor networks, social networks and even text). A unique characteristic of these data is the coupling between data values and underlying irregular structure on which these values are defined. Thus, researchers developed Graph Neural Networks (GNNs) to use deep...