Related papers: Prototypical Extreme Multi-label Classification wi…

In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity…

Learning multi-label image recognition with incomplete annotation is gaining popularity due to its superior performance and significant labor savings when compared to training with fully labeled datasets. Existing literature mainly focuses…

Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

The goal of Bayesian deep learning is to provide uncertainty quantification via the posterior distribution. However, exact inference over the weight space is computationally intractable due to the ultra-high dimensions of the neural…

Extreme compression, particularly ultra-low bit precision (binary/ternary) quantization, has been proposed to fit large NLP models on resource-constraint devices. However, to preserve the accuracy for such aggressive compression schemes,…

Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments. Despite their great success, the…

Classifier chains is a key technique in multi-label classification, since it allows to consider label dependencies effectively. However, the classifiers are aligned according to a static order of the labels. In the concept of dynamic…

We propose a new application of embedding techniques for problem retrieval in adaptive tutoring. The objective is to retrieve problems whose mathematical concepts are similar. There are two challenges: First, like sentences, problems…

The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative…

Recent years have seen a surge of novel neural network architectures for the integration of multi-omics data for prediction. Most of the architectures include either encoders alone or encoders and decoders, i.e., autoencoders of various…

Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…

Multi-label image classification is a foundational topic in various domains. Multimodal learning approaches have recently achieved outstanding results in image representation and single-label image classification. For instance, Contrastive…

Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…

We propose the Limited Multi-Label (LML) projection layer as a new primitive operation for end-to-end learning systems. The LML layer provides a probabilistic way of modeling multi-label predictions limited to having exactly k labels. We…

Graphs are powerful representations for relations among objects, which have attracted plenty of attention. A fundamental challenge for graph learning is how to train an effective Graph Neural Network (GNN) encoder without labels, which are…

This paper proposes a novel formulation of prototypical loss with mixup for speaker verification. Mixup is a simple yet efficient data augmentation technique that fabricates a weighted combination of random data point and label pairs for…

The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…

Existing rumor detection methods often neglect the content within images as well as the inherent relationships between contexts and images across different visual scales, thereby resulting in the loss of critical information pertinent to…

Existed pre-trained models have achieved state-of-the-art performance on various text classification tasks. These models have proven to be useful in learning universal language representations. However, the semantic discrepancy between…