Adaptive Equivalent Models for Distribution Networks

As the power system grows more complex and active, equivalent models have become a solution for modelling parts of the network that have limited observability or are confidential or too complex to simulate otherwise. In the past decade, this topic has also made its way to distribution networks because of its transition towards an active network,...

Private Graph Extraction via Feature Explanations

Privacy and interpretability are two important ingredients for achieving trustworthy machine learning. We study the interplay of these two aspects in graph machine learning through graph reconstruction attacks. The goal of the adversary here is to reconstruct the graph structure of the training data given access to model explanations. Based on...

Rethinking the Trigger-injecting Position in Graph Backdoor Attack

Backdoor attacks have been demonstrated as a security threat for machine learning models. Traditional backdoor attacks intend to inject backdoor functionality into the model such that the backdoored model will perform abnormally on inputs with predefined backdoor triggers and still retain state-of-the-art performance on the clean inputs. While...

A GNN-Based Generative Model for Generating Synthetic Cyber-Physical Power System Topology

Synthetic networks aim at generating realistic projections of real-world networks while concealing the actual system information. This paper proposes a scalable and effective approach based on graph neural networks (GNN) to generate synthetic topologies of Cyber-Physical power Systems (CPS) with realistic network feature distribution. In order...

EdgeNets: Edge Varying Graph Neural Networks

Driven by the outstanding performance of neural networks in the structured euclidean domain, recent years have seen a surge of interest in developing neural networks for graphs and data supported on graphs. The graph is leveraged at each layer of the neural network as a parameterization to capture detail at the node level with a reduced...

Graph machine learning for design of high-octane fuels

Fuels with high-knock resistance enable modern spark-ignition engines to achieve high efficiency and thus low CO₂ emissions. Identification of molecules with desired autoignition properties indicated by a high research octane number and a high octane sensitivity is therefore of great practical relevance and can be supported by...

Poster: Clean-label Backdoor Attack on Graph Neural Networks

Graph Neural Networks (GNNs) have achieved impressive results in various graph learning tasks. They have found their way into many applications, such as fraud detection, molecular property prediction, or knowledge graph reasoning. However, GNNs have been recently demonstrated to be vulnerable to backdoor attacks. In this work, we explore a...

More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks

Graph Neural Networks (GNNs) are a class of deep learning-based methods for processing graph domain information. GNNs have recently become a widely used graph analysis method due to their superior ability to learn representations for complex graph data. Due to privacy concerns and regulation restrictions, centralized GNNs can be difficult to...

Explainability-based Backdoor Attacks against Graph Neural Networks

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already numerous works on backdoor attacks on neural networks, but only a few works consider graph neural...

Design of a Graph Neural Network: to predict the optimal resolution of the Sonar Performance Model

Graph Neural Networks are a unique type of Deep Learning models that have a capability to exploit an explicitly stated structure of data representation. By design they carry a strong relational inductive bias, which is a set of assumptions that makes the algorithm prioritize some solutions over another, independent of observed data. This makes...

Towards Finite-Time Consensus with Graph Convolutional Neural Networks

Atrial electrograms are often used to gain understanding on the development of atrial fibrillation (AF). Using such electrograms, cardiologists can reconstruct how the depolarization wave-front propagates across the atrium. Knowing the exact moment at which the depolarization wavefront in the tissue reaches each electrode is an important aspect...

Graph-Adaptive Activation Functions for Graph Neural Networks

Network data are essential in applications such as recommender systems, social networks, and sensor networks. A unique characteristic that these data encompass is the coupling between the data values and the underlying network structure on which these data are defined. Graph Neural Networks (GNNs) have been designed as tools to extend the...

Convolutional Graph Neural Networks

Convolutional neural networks (CNNs) restrict the, otherwise arbitrary, linear operation of neural networks to be a convolution with a bank of learned filters. This makes them suitable for learning tasks based on data that exhibit the regular structure of time signals and images. The use of convolutions, however, makes them unsuitable for...

Aggregation Graph Neural Networks

Graph neural networks (GNNs) regularize classical neural networks by exploiting the underlying irregular structure supporting graph data, extending its application to broader data domains. The aggregation GNN presented here is a novel GNN that exploits the fact that the data collected at a single node by means of successive local exchanges...