Match!
Mahdieh Soleymani Baghshah
Sharif University of Technology
40Publications
11H-index
348Citations
Publications 40
Newest
#1Mahsa GhorbaniH-Index: 1
Last.Hamid R. Rabiee (Sharif University of Technology)H-Index: 20
view all 3 authors...
Graph embedding is an important approach for graph analysis tasks such as node classification and link prediction. The goal of graph embedding is to find a low dimensional representation of graph nodes that preserves the graph information. Recent methods like Graph Convolutional Network (GCN) try to consider node attributes (if available) besides node relations and learn node embeddings for unsupervised and semi-supervised tasks on graphs. On the other hand, multi-layer graph analysis has been r...
Source
May 1, 2019 in ICASSP (International Conference on Acoustics, Speech, and Signal Processing)
#1Melika Behjati (Sharif University of Technology)H-Index: 1
#2Seyed-Mohsen Moosavi-Dezfooli (EPFL: École Polytechnique Fédérale de Lausanne)H-Index: 9
Last.Pascal Frossard (EPFL: École Polytechnique Fédérale de Lausanne)H-Index: 40
view all 4 authors...
Despite the vast success neural networks have achieved in different application domains, they have been proven to be vulnerable to adversarial perturbations (small changes in the input), which lead them to produce the wrong output. In this paper, we propose a novel method, based on gradient projection, for generating universal adversarial perturbations for text; namely sequence of words that can be added to any input in order to fool the classifier with high probability. We observed that text cl...
4 CitationsSource
#1Ehsan MontahaeiH-Index: 2
#2Danial Alihosseini (Sharif University of Technology)H-Index: 1
Last.Mahdieh Soleymani Baghshah (Sharif University of Technology)H-Index: 11
view all 3 authors...
Text generation is an important Natural Language Processing task with various applications. Although several metrics have already been introduced to evaluate the text generation methods, each of them has its own shortcomings. The most widely used metrics such as BLEU only consider the quality of generated sentences and neglect their diversity. For example, repeatedly generation of only one high quality sentence would result in a high BLEU score. On the other hand, the more recent metric introduc...
2 Citations
#1Amirhossein Akbarnejad (Sharif University of Technology)H-Index: 1
#2Mahdieh Soleymani Baghshah (Sharif University of Technology)H-Index: 11
Multi-label classification has received considerable interest in recent years. Multi-label classifiers usually need to address many issues including: handling large-scale datasets with many instances and a large set of labels, compensating missing label assignments in the training set, considering correlations between labels, as well as exploiting unlabeled data to improve prediction performance. To tackle datasets with a large set of labels, embedding-based methods represent the label assignmen...
Source
#1Ehsan MontahaeiH-Index: 2
#2Danial Alihosseini (Sharif University of Technology)H-Index: 1
Last.Mahdieh Soleymani Baghshah (Sharif University of Technology)H-Index: 11
view all 3 authors...
Although GAN-based methods have received many achievements in the last few years, they have not been such successful in generating discrete data. The most important challenge of these methods is the difficulty of passing the gradient from the discriminator to the generator when the generator outputs are discrete. Despite several attempts done to alleviate this problem, none of the existing GAN-based methods has improved the performance of text generation (using measures that evaluate both the qu...
#1Danial AlihosseiniH-Index: 1
#2Ehsan MontahaeiH-Index: 2
view all 3 authors...
Source
#1Zeinab Golgooni (Sharif University of Technology)
#2Sara Mirsadeghi (Royan Institute)H-Index: 1
Last.Hamid R. Rabiee (Sharif University of Technology)H-Index: 20
view all 7 authors...
An early characterization of drug-induced cardiotoxicity may be possible by combining comprehensive in vitro proarrhythmia assay and deep learning techniques. We aimed to develop a method to automatically detect irregular beating rhythm of field potentials recorded from human pluripotent stem cells (hPSC) derived cardiomyocytes (hPSC-CM) by multi-electrode array (MEA) system. We included field potentials from 380 experiments, which were labeled as normal or arrhythmic by electrophysiology expert...
Source
#1Ehsan MontahaeiH-Index: 2
#2Mahsa GhorbaniH-Index: 1
Last.Hamid R. RabieeH-Index: 20
view all 4 authors...
Adversarial approach has been widely used for data generation in the last few years. However, this approach has not been extensively utilized for classifier training. In this paper, we propose an adversarial framework for classifier training that can also handle imbalanced data. Indeed, a network is trained via an adversarial approach to give weights to samples of the majority class such that the obtained classification problem becomes more challenging for the discriminator and thus boosts its c...
2 Citations
#1Mahsa GhorbaniH-Index: 1
Last.Hamid R. RabieeH-Index: 20
view all 3 authors...
Recently, graph embedding emerges as an effective approach for graph analysis tasks such as node classification and link prediction. The goal of network embedding is to find low dimensional representation of graph nodes that preserves the graph structure. Since there might be signals on nodes as features, recent methods like Graph Convolutional Networks (GCNs) try to consider node signals besides the node relations. On the other hand, multi-layered graph analysis has been received much attention...
1 Citations
#1Seyed Mahdi Roostaiyan (Sharif University of Technology)H-Index: 1
#2Ehsan ImaniH-Index: 1
Last.Mahdieh Soleymani Baghshah (Sharif University of Technology)H-Index: 11
view all 3 authors...
1 CitationsSource
1234