相关论文: On the Transferability of VAE Embeddings using Rel…

We present a semi-supervised learning framework based on graph embeddings. Given a graph between instances, we train an embedding for each instance to jointly predict the class label and the neighborhood context in the graph. We develop…

We address the problem of learning a distributed representation of entities in a relational database using a low-dimensional embedding. Low-dimensional embeddings aim to encapsulate a concise vector representation for an underlying dataset…

We propose TabTransformer, a novel deep tabular data modeling architecture for supervised and semi-supervised learning. The TabTransformer is built upon self-attention based Transformers. The Transformer layers transform the embeddings of…

Zero-shot learning has gained popularity due to its potential to scale recognition models without requiring additional training data. This is usually achieved by associating categories with their semantic information like attributes.…

In recent years, extending variational autoencoder's framework to learn disentangled representations has received much attention. We address this problem by proposing a framework capable of disentangling class-related and class-independent…

Many graph embedding approaches have been proposed for knowledge graph completion via link prediction. Among those, translating embedding approaches enjoy the advantages of light-weight structure, high efficiency and great interpretability.…

Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A…

Detecting visual relationships, i.e. <Subject, Predicate, Object> triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply…

Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However,…

Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy…

Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…

Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data. One of the most effective methods in representing knowledge graphs is to embed symbolic relations and…

Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels. In this paper we propose multi-space variational encoder-decoders, a new model for labeled…

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Given new tasks with very little data$-$such as new classes in a classification problem or a domain shift in the input$-$performance of modern vision systems degrades remarkably quickly. In this work, we illustrate how the neural network…

We make two theoretical contributions to disentanglement learning by (a) defining precise semantics of disentangled representations, and (b) establishing robust metrics for evaluation. First, we characterize the concept "disentangled…

Semi-supervised learning is sought for leveraging the unlabelled data when labelled data is difficult or expensive to acquire. Deep generative models (e.g., Variational Autoencoder (VAE)) and semisupervised Generative Adversarial Networks…

Deep generative models (DGMs) have achieved remarkable advances. Semi-supervised variational auto-encoders (SVAE) as a classical DGM offer a principled framework to effectively generalize from small labelled data to large unlabelled ones,…