Related papers: AgForce Enables Antigen-conditioned Generative Ant…

Accurate and robust drug response prediction is of utmost importance in precision medicine. Although many models have been developed to utilize the representations of drugs and cancer cell lines for predicting cancer drug responses (CDR),…

Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by…

We explore recurrent encoder multi-decoder neural network architectures for semi-supervised sequence classification and reconstruction. We find that the use of multiple reconstruction modules helps models generalize in a classification task…

Computational protein design, i.e. inferring novel and diverse protein sequences consistent with a given structure, remains a major unsolved challenge. Recently, deep generative models that learn from sequences alone or from sequences and…

The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from attacking DNNs successfully, rather than preventing their…

Graph anomaly detection (GAD) has become an increasingly important task across various domains. With the rapid development of graph neural networks (GNNs), GAD methods have achieved significant performance improvements. However, fairness…

Image compression is an essential approach for decreasing the size in bytes of the image without deteriorating the quality of it. Typically, classic algorithms are used but recently deep-learning has been successfully applied. In this work,…

We propose a new compression scheme for genomic data given as sequence fragments called reads. The scheme uses a reference genome at the decoder side only, freeing the encoder from the burdens of storing references and performing…

With the growing complexity of deep learning methods adopted in practical applications, there is an increasing and stringent need to explain and interpret the decisions of such methods. In this work, we focus on explainable AI and propose a…

Reliable training of generative adversarial networks (GANs) typically require massive datasets in order to model complicated distributions. However, in several applications, training samples obey invariances that are \textit{a priori}…

We propose GANCoder, an automatic programming approach based on Generative Adversarial Networks (GAN), which can generate the same functional and logical programming language codes conditioned on the given natural language utterances. The…

This paper introduces Associative Compression Networks (ACNs), a new framework for variational autoencoding with neural networks. The system differs from existing variational autoencoders (VAEs) in that the prior distribution used to model…

Discovering novel drug candidate molecules is one of the most fundamental and critical steps in drug development. Generative deep learning models, which create synthetic data given a probability distribution, offer a high potential for…

Conditional Generative Adversarial Networks (cGAN) generate realistic images by incorporating class information into GAN. While one of the most popular cGANs is an auxiliary classifier GAN with softmax cross-entropy loss (ACGAN), it is…

Generative adversarial networks (GANs) are one of the most widely used generative models. GANs can learn complex multi-modal distributions, and generate real-like samples. Despite the major success of GANs in generating synthetic data, they…

We use a mean-field-based transformer model to theoretically investigate how auxiliary variables, such as positional encoding, prevent mode collapse of self-attention mechanisms. The use of mean-field transformers to analyze the properties…

Multiphysics problems such as multicomponent diffusion, phase transformations in multiphase systems and alloy solidification involve numerical solution of a coupled system of nonlinear partial differential equations (PDEs). Numerical…

The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN)…

Antibodies are Y-shaped proteins that neutralize pathogens and constitute the core of our adaptive immune system. De novo generation of new antibodies that target specific antigens holds the key to accelerating vaccine discovery. However,…

Recent studies show that the deep neural networks (DNNs) have achieved great success in various tasks. However, even the \emph{state-of-the-art} deep learning based classifiers are extremely vulnerable to adversarial examples, resulting in…