Related papers: SwitchTab: Switched Autoencoders Are Effective Tab…

Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. While techniques have been proposed to achieve a more balanced training loss and to improve tail classes data…

Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive…

Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s),…

Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is…

In deep learning for drug discovery, chemical data are often represented as simplified molecular-input line-entry system (SMILES) sequences which allow for straightforward implementation of natural language processing methodologies, one…

Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech…

Sparse autoencoders have become a standard tool for uncovering interpretable latent representations in neural networks. Yet salient concepts often span manifolds that current linear methods cannot capture without post hoc analysis. This…

To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…

Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…

Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node. Many of the existing methods focus on obtaining a static vector…

Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's…

Table extraction from PDF and image documents is a ubiquitous task in the real-world. Perfect extraction quality is difficult to achieve with one single out-of-box model due to (1) the wide variety of table styles, (2) the lack of training…

Learning with a limited number of labeled data is a central problem in real-world applications of machine learning, as it is often expensive to obtain annotations. To deal with the scarcity of labeled data, transfer learning is a…

Available data in machine learning applications is becoming increasingly complex, due to higher dimensionality and difficult classes. There exists a wide variety of approaches to measuring complexity of labeled data, according to class…

Self-supervised node representation learning aims to learn node representations from unlabelled graphs that rival the supervised counterparts. The key towards learning informative node representations lies in how to effectively gain…

We examine two fundamental tasks associated with graph representation learning: link prediction and semi-supervised node classification. We present a novel autoencoder architecture capable of learning a joint representation of both local…

Tabular data poses unique challenges for deep learning due to its heterogeneous feature types, lack of spatial structure, and often limited sample sizes. We propose TabNSA, a novel deep learning framework that integrates Native Sparse…

Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setting where the target domain has a few labeled instances…

We propose split-brain autoencoders, a straightforward modification of the traditional autoencoder architecture, for unsupervised representation learning. The method adds a split to the network, resulting in two disjoint sub-networks. Each…

Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…