A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper analyzes GCNN sensitivity to probabilistic graph perturbations.
In this paper, we propose a perturbation framework to measure the robustness of graph properties. Although there are already perturbation methods proposed to tackle this problem, they are limited by the fact that the strength of the perturbation cannot be well controlled. We firstly provide a perturbation framework on …
Adding node feature kernels improves GCN robustness to graph perturbations.
Graph convolutional networks (GCNs) are vulnerable to perturbations of the graph structure that are either random, or, adversarially designed. The perturbed links modify the graph neighborhoods, which critically affects the performance of GCNs in semi-supervised learning (SSL) tasks. Aiming at robustifying GCNs conditi…
This work analyzes the stability of graph filters under large perturbations.
Study on stability of GCNNs under graph perturbations.
This paper focuses on spectral filters on graphs, namely filters defined as elementwise multiplication in the frequency domain of a graph. In many graph signal processing settings, it is important to transfer a filter from one graph to another. One example is in graph convolutional neural networks (ConvNets), where the…
Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which deliberately add carefully created unnoticeable perturbation to the graph structure. …
Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (\eg articles with citation link tend to be in the same class), graph neural networks could be more sensiti…
Deep learning models for graphs have advanced the state of the art on many tasks. Despite their recent success, little is known about their robustness. We investigate training time attacks on graph neural networks for node classification that perturb the discrete graph structure. Our core principle is to use meta-gradi…
New invariant counts graph configurations in 3D manifolds.
Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However, compared with non-graph data, the discrete features, graph connections and diff…
Graph cuts find global optima for Potts models in slight perturbations.
Pro-GNN defends graph neural networks from adversarial attacks by learning graph structure.
SIGNNAP learns stable and identifiable node representations in GNNs against graph perturbations.
Novel TRI-GNN framework improves graph classification robustness.
A new framework explains GNN predictions by simulating graph structure and feature changes.
Novel framework predicts cell responses to perturbations using GRNs.
Cellina uses supervised disentanglement to predict cell behavior in tissues.
Graphs can be fooled by small edge changes, but this work protects them.
We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model's output distribution against local perturbations around the input. We propose two algorithms, sample-based…
LGKDE learns graph density using neural networks and perturbations.
GNNs robustness in community detection is studied with various perturbations.
This paper examines how graph topology affects adversarial attacks on vertex classification.
An overview of the perturbative expansion of the Chern--Simons path integral is given. The main goal is to describe how trivalent graphs appear: as they already occur in the perturbative expansion of an analogous finite-dimensional integral, we discuss this case in detail.
DefenseVGAE defends graph neural networks against adversarial attacks.
Recent works show that Graph Neural Networks (GNNs) are highly non-robust with respect to adversarial attacks on both the graph structure and the node attributes, making their outcomes unreliable. We propose the first method for certifiable (non-)robustness of graph convolutional networks with respect to perturbations …
Graph neural networks detect structural perturbations from time series data.
Despite the exploding interest in graph neural networks there has been little effort to verify and improve their robustness. This is even more alarming given recent findings showing that they are extremely vulnerable to adversarial attacks on both the graph structure and the node attributes. We propose the first method…
New framework assesses graph-learning datasets for better evaluation.
GNNGuard defends Graph Neural Networks against structural perturbations.
Indirect attacks can fool graph classifiers even with poisoned neighbors.
ELD compares graphs by their embedded Laplacian eigenvectors, resolving ambiguities.
In a graph convolutional network, we assume that the graph is generated wrt some observation noise. During learning, we make small random perturbations of the graph and try to improve generalization. Based on quantum information geometry, can be characterized by the eigendecomposition of the graph Laplaci…
Deep learning models for graphs have achieved strong performance for the task of node classification. Despite their proliferation, currently there is no study of their robustness to adversarial attacks. Yet, in domains where they are likely to be used, e.g. the web, adversaries are common. Can deep learning models for …
Paper shows how to hide individuals in graphs to fool community detection models.
GraphCL learns node representations by maximizing similarity between perturbed node features.
node2coords learns interpretable graph node representations robust to graph perturbations.
Some of the most effective influential spreader detection algorithms are unstable to small perturbations of the network structure. Inspired by bagging in Machine Learning, we propose the first Perturb and Combine (P&C) procedure for networks. It (1) creates many perturbed versions of a given graph, (2) applies a node s…
Paper tackles robust graph matching in dense graphs with AMP type algorithm.
Paper tackles fairness issues in GNNs by proposing ELEGANT for certification.
Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However, only few work has addressed the adversarial robustness of GNNs. In this paper, we first present a novel gradient-based attack method that fa…
iGCL preserves graph semantics in latent space augmentations.
New regularization techniques improve stability of deep neural networks.
This paper focuses on spectral graph convolutional neural networks (ConvNets), where filters are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the dataset consists of signals defined on many different graphs, the trained ConvNet should generalize to signals…
New algorithm improves graph-based active learning by identifying unexplored regions.
Scattering transforms are non-trainable deep convolutional architectures that exploit the multi-scale resolution of a wavelet filter bank to obtain an appropriate representation of data. More importantly, they are proven invariant to translations, and stable to perturbations that are close to translations. This stabili…
The original contributions of this paper are twofold: a new understanding of the influence of noise on the eigenvectors of the graph Laplacian of a set of image patches, and an algorithm to estimate a denoised set of patches from a noisy image. The algorithm relies on the following two observations: (1) the low-index e…