1 code implementation • 6 Mar 2024 • Jing Gu, Dongmian Zou
Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks.
no code implementations • 10 Nov 2023 • Yifei Yang, Peng Wang, Xiaofan He, Dongmian Zou
Detecting unusual patterns in graph data is a crucial task in data mining.
no code implementations • 2 Nov 2023 • Wonjun Lee, Yifei Yang, Dongmian Zou, Gilad Lerman
Generative Adversarial Networks (GANs) are powerful tools for creating new content, but they face challenges such as sensitivity to starting conditions and mode collapse.
1 code implementation • 15 Jun 2023 • Eric Qu, Dongmian Zou
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.
no code implementations • 19 Aug 2022 • Yifei Yang, Dongmian Zou, Xiaofan He
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.
1 code implementation • 4 Jun 2022 • Yinglong Guo, Dongmian Zou, Gilad Lerman
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).
no code implementations • 4 Feb 2022 • Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman
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.
no code implementations • 30 Jan 2022 • Eric Qu, Dongmian Zou
We call this network the hyperbolic AE-GAN, or HAEGAN for short.
no code implementations • 7 Sep 2020 • Sagar K. Tamang, Ardeshir Ebtehaj, Peter J. Van Leeuwen, Dongmian Zou, Gilad Lerman
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
1 code implementation • 9 Jun 2020 • Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman
We establish both robustness to outliers and suitability to low-rank modeling of the Wasserstein metric as opposed to the KL divergence.
2 code implementations • ICLR 2020 • Chieh-Hsin Lai, Dongmian Zou, Gilad Lerman
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
1 code implementation • 28 Sep 2018 • Dongmian Zou, Gilad Lerman
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)
no code implementations • 27 Sep 2018 • Dongmian Zou, Gilad Lerman
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.
no code implementations • 4 Aug 2018 • Dongmian Zou, Radu Balan, Maneesh Singh
Many convolutional neural networks (CNNs) have a feed-forward structure.
1 code implementation • 31 Mar 2018 • Dongmian Zou, Gilad Lerman
We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs.
Ranked #58 on Node Classification on Cora
no code implementations • 18 Jan 2017 • Radu Balan, Maneesh Singh, Dongmian Zou
In this paper we discuss the stability properties of convolutional neural networks.
no code implementations • 10 Mar 2014 • Radu Balan, Dongmian Zou
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.