Related papers: Autoencoding Hyperbolic Representation for Adversa…

The recent surge in popularity of deep generative models for 3D objects has highlighted the need for more efficient training methods, particularly given the difficulties associated with training with conventional 3D representations, such as…

The paper proposes a method to effectively fuse multi-exposure inputs and generate high-quality high dynamic range (HDR) images with unpaired datasets. Deep learning-based HDR image generation methods rely heavily on paired datasets. The…

Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning. We here present a novel method to embed directed acyclic graphs. Following prior…

Hypergraph data, which capture multi-way interactions among entities, are increasingly prevalent in the big data era. Generating new hyperlinks from an observed, usually high-dimensional hypergraph is an important yet challenging task with…

Knowledge graph embeddings (KGE) have been validated as powerful methods for inferring missing links in knowledge graphs (KGs) that they typically map entities into Euclidean space and treat relations as transformations of entities.…

Network embedding is an effective way to solve the network analytics problems such as node classification, link prediction, etc. It represents network elements using low dimensional vectors such that the graph structural information and…

We develop a geometric framework to study the structure and function of complex networks. We assume that hyperbolic geometry underlies these networks, and we show that with this assumption, heterogeneous degree distributions and strong…

Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding these networks into hyperbolic space because…

Hyperbolic spaces, which have the capacity to embed tree structures without distortion owing to their exponential volume growth, have recently been applied to machine learning to better capture the hierarchical nature of data. In this…

Deep generative models are attracting great attention as a new promising approach for molecular design. All models reported so far are based on either variational autoencoder (VAE) or generative adversarial network (GAN). Here we propose a…

We have witnessed rapid progress on 3D-aware image synthesis, leveraging recent advances in generative visual models and neural rendering. Existing approaches however fall short in two ways: first, they may lack an underlying 3D…

Synthetic data can be used in various applications, such as correcting bias datasets or replacing scarce original data for simulation purposes. Generative Adversarial Networks (GANs) are considered state-of-the-art for developing generative…

In topology optimization using deep learning, load and boundary conditions represented as vectors or sparse matrices often miss the opportunity to encode a rich view of the design problem, leading to less than ideal generalization results.…

Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks. Different works have improved the limited understanding of the latent space of GANs by embedding images…

Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks. However, most existing algorithms ignore the existence of inherent data distribution and…

Data is the fuel of data science and machine learning techniques for smart grid applications, similar to many other fields. However, the availability of data can be an issue due to privacy concerns, data size, data quality, and so on. To…

Generative adversarial networks (GANs) are one of the most widely adopted semisupervised and unsupervised machine learning methods for high-definition image, video, and audio generation. In this work, we propose a new type of architecture…

The rapid growth of Electronic Health Records (EHRs), as well as the accompanied opportunities in Data-Driven Healthcare (DDH), has been attracting widespread interests and attentions. Recent progress in the design and applications of deep…

Learning representations according to the underlying geometry is of vital importance for non-Euclidean data. Studies have revealed that the hyperbolic space can effectively embed hierarchical or tree-like data. In particular, the few past…

Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve…