Search Results for author:
Found 17 papers, 7 papers with code
Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks
Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks.
Interpretable Graph Anomaly Detection using Gradient Attention Maps
Detecting unusual patterns in graph data is a crucial task in data mining.
Monotone Generative Modeling via a Gromov-Monge Embedding
Generative Adversarial Networks (GANs) are powerful tools for creating new content, but they face challenges such as sensitivity to starting conditions and mode collapse.
Hyperbolic Convolution via Kernel Point Aggregation
HKConv not only expressively learns local features according to the hyperbolic geometry, but also enjoys equivariance to permutation of hyperbolic points and invariance to parallel transport of a local neighborhood.
Graph Neural Network Based Node Deployment for Throughput Enhancement
Besides, we show that an expressive GNN has the capacity to approximate both the function value and the gradients of a multivariate permutation-invariant function, as a theoretic support to the proposed method.
An Unpooling Layer for Graph Generation
Since this unpooling layer is trainable, it can be applied to graph generation either in the decoder of a variational autoencoder or in the generator of a generative adversarial network (GAN).
Robust Vector Quantized-Variational Autoencoder
We experimentally demonstrate that RVQ-VAE is able to generate examples from inliers even if a large portion of the training data points are corrupted.
Autoencoding Hyperbolic Representation for Adversarial Generation
We call this network the hyperbolic AE-GAN, or HAEGAN for short.
Ensemble Riemannian Data Assimilation over the Wasserstein Space
Unlike the Eulerian penalization of error in the Euclidean space, the Wasserstein metric can capture translation and difference between the shapes of square-integrable probability distributions of the background state and observations -- enabling to formally penalize geophysical biases in state-space with non-Gaussian distributions.
Methodology
Novelty Detection via Robust Variational Autoencoding
We establish both robustness to outliers and suitability to low-rank modeling of the Wasserstein metric as opposed to the KL divergence.
Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
The encoder maps the data into a latent space, from which the RSR layer extracts the subspace.
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly
+3
Encoding Robust Representation for Graph Generation
The decoder is a simple fully connected network that is adapted to specific tasks, such as link prediction, signal generation on graphs and full graph and signal generation.
Ranked #2 on
Link Prediction
on Pubmed (biased evaluation)
Graph Generation via Scattering
These results are in contrast to experience with Euclidean data, where it is difficult to form a generative scattering network that performs as well as state-of-the-art methods.
On Lipschitz Bounds of General Convolutional Neural Networks
Many convolutional neural networks (CNNs) have a feed-forward structure.
Graph Convolutional Neural Networks via Scattering
We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs.
Ranked #58 on
Node Classification
on Cora
Lipschitz Properties for Deep Convolutional Networks
In this paper we discuss the stability properties of convolutional neural networks.
Phase Retrieval using Lipschitz Continuous Maps
In this note we prove that reconstruction from magnitudes of frame coefficients (the so called "phase retrieval problem") can be performed using Lipschitz continuous maps.
