Related papers: Joint & Progressive Learning from High-Dimensional…

Joint representation learning of text and knowledge within a unified semantic space enables us to perform knowledge graph completion more accurately. In this work, we propose a novel framework to embed words, entities and relations into the…

Unsupervised domain adaptation aims to transfer the classifier learned from the source domain to the target domain in an unsupervised manner. With the help of target pseudo-labels, aligning class-level distributions and learning the…

Labeling and maintaining a commercial sound effects library is a time-consuming task exacerbated by databases that continually grow in size and undergo taxonomy updates. Moreover, sound search and taxonomy creation are complicated by…

Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples…

We introduce a novel framework, called Interface Laplace learning, for graph-based semi-supervised learning. Motivated by the observation that an interface should exist between different classes where the function value is non-smooth, we…

We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly…

In this paper, we present a new algorithm for semi-supervised representation learning. In this algorithm, we first find a vector representation for the labels of the data points based on their local positions in the space. Then, we map the…

This paper presents a framework for learning visual representations from unlabeled video demonstrations captured from multiple viewpoints. We show that these representations are applicable for imitating several robotic tasks, including pick…

Text Classification is one of the fundamental tasks in natural language processing, which requires an agent to determine the most appropriate category for input sentences. Recently, deep neural networks have achieved impressive performance…

Joint Embedding Predictive Architectures (JEPAs) learn representations able to solve numerous downstream tasks out-of-the-box. JEPAs combine two objectives: (i) a latent-space prediction term, i.e., the representation of a slightly…

Recent advances in large language models (LLMs) have yielded impressive performance on various tasks, yet they often depend on high-quality feedback that can be costly. Self-refinement methods attempt to leverage LLMs' internal evaluation…

Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by…

Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision availability change simultaneously over time. This setting reflects practical structured…

In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e.g. same classes), but also different latent…

Label noise and class imbalance commonly coexist in real-world data. Previous works for robust learning, however, usually address either one type of the data biases and underperform when facing them both. To mitigate this gap, this work…

In high energy physics, self-supervised learning (SSL) methods have the potential to aid in the creation of machine learning models without the need for labeled datasets for a variety of tasks, including those related to jets -- narrow…

Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that…

This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative…

Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences. We propose to view text classification as a label-word joint embedding…

We introduce Mediffusion -- a new method for semi-supervised learning with explainable classification based on a joint diffusion model. The medical imaging domain faces unique challenges due to scarce data labelling -- insufficient for…