Related papers: Towards DNA-Encoded Library Generation with GFlowN…

Single-stranded libraries generated from ancient DNA extracts have specific sequencing requirements. The short library molecules typically associated with ancient DNA templates are expected to behave differently during the annealing to the…

Mathematical reasoning problems are among the most challenging, as they typically require an understanding of fundamental laws to solve. The laws are universal, but the derivation of the final answer changes depending on how a problem is…

We introduce a class of auto-encoder neural networks tailored to data from the natural exponential family (e.g., count data). The architectures are inspired by the problem of learning the filters in a convolutional generative model with…

Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions. However,…

Recent advances in geometric deep learning and generative modeling have enabled the design of novel proteins with a wide range of desired properties. However, current state-of-the-art approaches are typically restricted to generating…

Accurate localization of proteins from fluorescence microscopy images is challenging due to the inter-class similarities and intra-class disparities introducing grave concerns in addressing multi-class classification problems. Conventional…

Deep Learning (DL) algorithms hold great promise for applications in the field of computational biophysics. In fact, the vast amount of available molecular structures, as well as their notable complexity, constitutes an ideal context in…

Increased complexity and heterogeneity of emerging 5G and beyond 5G (B5G) wireless networks will require a paradigm shift from traditional resource allocation mechanisms. Deep learning (DL) is a powerful tool where a multi-layer neural…

While there exist a plethora of deep learning tools and frameworks, the fast-growing complexity of the field brings new demands and challenges, such as more flexible network design, speedy computation on distributed setting, and…

Deep learning has transformed protein design, enabling accurate structure prediction, sequence optimization, and de novo protein generation. Advances in single-chain protein structure prediction via AlphaFold2, RoseTTAFold, ESMFold, and…

Current biocomputing approaches predominantly rely on engineered circuits with fixed logic, offering limited stability and reliability under diverse environmental conditions. Here, we use the GRNN framework introduced in our previous work…

We propose Distribution Embedding Networks (DEN) for classification with small data. In the same spirit of meta-learning, DEN learns from a diverse set of training tasks with the goal to generalize to unseen target tasks. Unlike existing…

Deep Neural Networks (DNNs) have revolutionized many aspects of our lives. The use of DNNs is becoming ubiquitous including in softwares for image recognition, speech recognition, speech synthesis, language translation, to name a few. he…

Federated learning (FL) can fully leverage large-scale terminal data while ensuring privacy and security, and is considered as a distributed alternative for the centralized machine learning. However, the issue of data heterogeneity poses…

This proposal aims to develop more accurate federated learning (FL) methods with faster convergence properties and lower communication requirements, specifically for forecasting distributed energy resources (DER) such as renewables, energy…

The design of molecules and materials with tailored properties is challenging, as candidate molecules must satisfy multiple competing requirements that are often difficult to measure or compute. While molecular structures, produced through…

Federated learning (FL) was proposed to facilitate the training of models in a distributed environment. It supports the protection of (local) data privacy and uses local resources for model training. Until now, the majority of research has…

Federated Learning (FL) has emerged as a solution for distributed systems that allow clients to train models on their data and only share models instead of local data. Generative Models are designed to learn the distribution of a dataset…

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed…

GFlowNets are a promising alternative to MCMC sampling for discrete compositional random variables. Training GFlowNets requires repeated evaluations of the unnormalized target distribution or reward function. However, for large-scale…