Related papers: Transfer Learning or Self-supervised Learning? A T…

In recent years, self-supervised learning (SSL) frameworks have been extensively applied to sensor-based Human Activity Recognition (HAR) in order to learn deep representations without data annotations. While SSL frameworks reach…

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced…

Conventional text-to-SQL studies are limited to a single task with a fixed-size training and test set. When confronted with a stream of tasks common in real-world applications, existing methods struggle with the problems of insufficient…

As an effective way to alleviate the burden of data annotation, semi-supervised learning (SSL) provides an attractive solution due to its ability to leverage both labeled and unlabeled data to build a predictive model. While significant…

Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has diminished significantly in recent years, indicating that a…

Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training…

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),…

Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual learning (CL), where multiple tasks are learned sequentially,…

Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak…

Deep models trained in supervised mode have achieved remarkable success on a variety of tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a new paradigm for making use of large amounts of unlabeled…

Text classification is a widely studied problem and has broad applications. In many real-world problems, the number of texts for training classification models is limited, which renders these models prone to overfitting. To address this…

This paper presents a production Semi-Supervised Learning (SSL) pipeline based on the student-teacher framework, which leverages millions of unlabeled examples to improve Natural Language Understanding (NLU) tasks. We investigate two…

Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data…

Accurate prediction of material properties facilitates the discovery of novel materials with tailored functionalities. Deep learning models have recently shown superior accuracy and flexibility in capturing structure-property relationships.…

Deep learning is pushing the state-of-the-art in many computer vision applications. However, it relies on large annotated data repositories, and capturing the unconstrained nature of the real-world data is yet to be solved. Semi-supervised…

Contrastive, self-supervised learning (SSL) is used to train a model that predicts cancer type from miRNA, mRNA or RPPA expression data. This model, a pretrained FT-Transformer, is shown to outperform XGBoost and CatBoost, standard…

Incorporating self-supervised learning (SSL) before standard supervised learning (SL) has become a widely used strategy to enhance model performance, particularly in data-limited scenarios. However, this approach introduces a trade-off…

Self-Supervised Learning (SSL) is an increasingly popular ML paradigm that trains models to transform complex inputs into representations without relying on explicit labels. These representations encode similarity structures that enable…

Self-supervised learning (SSL) plays a central role in molecular representation learning. Yet, many recent innovations in masking-based pretraining are introduced as heuristics and lack principled evaluation, obscuring which design choices…

In this paper, we investigate self-supervised pre-training methods for document text recognition. Nowadays, large unlabeled datasets can be collected for many research tasks, including text recognition, but it is costly to annotate them.…