1 code implementation • Expert Systems with Applications 2023 • Alireza Amouzad, Zahra Dehghanian, Saeed Saravani, Maryam Amirmazlaghani, Behnam Roshanfekr
Recent methods leverage learnable parameters to extract structural information from neural networks and extend pooling and unpooling to graphs using node features and graph structural information.
Ranked #2 on Graph Classification on PTC
1 code implementation • 16 Apr 2023 • Zahra Dehghanian, Saeed Saravani, Maryam Amirmazlaghani, Mohammad Rahmati
This study presents an adversarial method for anomaly detection in real-world applications, leveraging the power of generative adversarial neural networks (GANs) through cycle consistency in reconstruction error.
Ranked #1 on Anomaly Detection on SVHN
1 code implementation • 5 Feb 2022 • Mohammad Khalooei, Mohammad Mehdi Homayounpour, Maryam Amirmazlaghani
This paper introduces a novel framework (Layer Sustainability Analysis (LSA)) for the analysis of layer vulnerability in an arbitrary neural network in the scenario of adversarial attacks.
no code implementations • ICML Workshop AML 2021 • Hossein Mohasel Arjomandi, Mohammad Khalooei, Maryam Amirmazlaghani
An adversary wants to attack a limited number of images within a stream of known length to reduce the exposure risk.
no code implementations • 3 Aug 2020 • Sadegh Etemad, Maryam Amirmazlaghani
In the proposed framework, Gaussian Copula is used to model the dependencies between different sub-bands of the Non Subsample Shearlet Transform (NSST) and non-Gaussian models are used for marginal modeling of the coefficients.
no code implementations • 12 May 2020 • Aysan Aghazadeh, Maryam Amirmazlaghani
Nowadays, face recognition and more generally image recognition have many applications in the modern world and are widely used in our daily tasks.
1 code implementation • 19 Dec 2019 • Mehrzad Saremi, Maryam Amirmazlaghani
With a motivation to compensate for this shortage, we developed an algorithm called GENEREF that can accumulate information from multiple types of data sets in an iterative manner, with each iteration boosting the performance of the prediction results.
no code implementations • 25 Aug 2018 • Ammar Gilani, Maryam Amirmazlaghani
In this paper, we propose an unsupervised hypergraph feature selection method via a novel point-weighting framework and low-rank representation that captures the importance of different data points.