Related papers: A Hierarchical Graphical Model for Record Linkage
Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph…
Deep neural networks are susceptible to label noise. Existing methods to improve robustness, such as meta-learning and regularization, usually require significant change to the network architecture or careful tuning of the optimization…
Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance.…
Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that can be obtained…
Multi-label image classification, which can be categorized into label-dependency and region-based methods, is a challenging problem due to the complex underlying object layouts. Although region-based methods are less likely to encounter…
We consider a novel data driven approach for designing learning algorithms that can effectively learn with only a small number of labeled examples. This is crucial for modern machine learning applications where labels are scarce or…
Label Ranking (LR) corresponds to the problem of learning a hypothesis that maps features to rankings over a finite set of labels. We adopt a nonparametric regression approach to LR and obtain theoretical performance guarantees for this…
In theory, the probabilistic linkage method provides two distinct advantages over non-probabilistic methods, including minimal rates of linkage error and accurate measures of these rates for data users. However, implementations can fall…
Graph-regularized semi-supervised learning has been used effectively for classification when (i) instances are connected through a graph, and (ii) labeled data is scarce. If available, using multiple relations (or graphs) between the…
In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…
In recent years, deep discriminative models have achieved extraordinary performance on supervised learning tasks, significantly outperforming their generative counterparts. However, their success relies on the presence of a large amount of…
Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…
Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation…
In many applications, researchers seek to identify overlapping entities across multiple data files. Record linkage algorithms facilitate this task, in the absence of unique identifiers. As these algorithms rely on semi-identifying…
We propose and illustrate a hierarchical Bayesian approach for matching statistical records observed on different occasions. We show how this model can be profitably adopted both in record linkage problems and in capture--recapture setups,…
Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…
Classifiers for the semi-supervised setting often combine strong supervised models with additional learning objectives to make use of unlabeled data. This results in powerful though very complex models that are hard to train and that demand…
Unravelling hidden patterns in datasets is a classical problem with many potential applications. In this paper, we present a challenge whose objective is to discover nonlinear relationships in noisy cloud of points. If a set of point…
Weakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven methods are the mainstream where user-provided keywords are…
Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models are gaining increasing popularity for text classification due…