arXiv research

Paper proposes a method to adapt classifiers using complementary labels instead of true labels.

Paper bridges ordinary-label and complementary-label learning frameworks.

In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that observations do \textbf{not} belong to. Let $Y$ and $\bar{Y}$ be the true and complementary labels, respectively. We first model the annotati…

A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However, the existing complementary-label learning methods cannot learn from the easily …

Collecting labeled data is costly and thus a critical bottleneck in real-world classification tasks. To mitigate this problem, we propose a novel setting, namely learning from complementary labels for multi-class classification. A complementary label specifies a class that a pattern does not belong to. Collecting compl…

Clarinet uses complementary labels to train classifiers with less source data.

Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increa…

In contrast to the standard classification paradigm where the true class is given to each training pattern, complementary-label learning only uses training patterns each equipped with a complementary label, which only specifies one of the classes that the pattern does not belong to. The goal of this paper is to derive …

UREs lead to overfitting in complex models, especially in complementary label learning.

In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial networks (GANs) can be used for multiple purposes. Triple-GAN, which aims to jointly optimize model components by incorporating three players, ge…

In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e.g. pedestrian, bicycle and tree) and is properly characterized by multiple visual features (e.g. color, texture and shape). Currentl…

We consider the problem of online multiclass classification with partial feedback, where an algorithm predicts a class for a new instance in each round and only receives its correctness. Although several methods have been developed for this problem, recent challenging real-world applications require further performance…

A complementary label (CL) simply indicates an incorrect class of an example, but learning with CLs results in multi-class classifiers that can predict the correct class. Unfortunately, the problem setting only allows a single CL for each example, which notably limits its potential since our labelers may easily identif…

This is the first step of the two steps to enumerate the minimal charts with two crossings. For a label $m$ of a chart $Γ$ we denote by $Γ_m$ the union of all the edges of label $m$ and their vertices. For a minimal chart $Γ$ with exactly two crossings, we can show that the two crossings are contained in $Γ_α\capΓ_β$ f…

New method uses SHapley Additive Explanations to identify anomaly detectors with complementary behaviors.

Weakly-supervised learning is a paradigm for alleviating the scarcity of labeled data by leveraging lower-quality but larger-scale supervision signals. While existing work mainly focuses on utilizing a certain type of weak supervision, we present a probabilistic framework, learning from indirect observations, for learn…

Anytime-valid confirmation of label-shift corrections

Study compares unsupervised and weakly-supervised methods for anomaly detection at the LHC.

We present a novel approach to train pixel resolution segmentation models on whole slide images in a weakly supervised setup. The model is trained to classify patches extracted from slides. This leads the training to be made under noisy labeled data. We solve the problem with two complementary strategies. First, the pa…

SFB uses stable features to adapt unstable ones for better performance.

CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.

CrossFilter tackles noisy labels in audio tagging.

To explore underlying complementary information from multiple views, in this paper, we propose a novel Latent Multi-view Semi-Supervised Classification (LMSSC) method. Unlike most existing multi-view semi-supervised classification methods that learn the graph using original features, our method seeks an underlying late…

Probabilistic clustering models (or equivalently, mixture models) are basic building blocks in countless statistical models and involve latent random variables over discrete spaces. For these models, posterior inference methods can be inaccurate and/or very slow. In this work we introduce deep network architectures tra…

Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks (MANNs) called Labeled Memory Networks (LMNs) suited for tasks requiring online adaptation in class…

A new method for adapting to label shifts using class probability matching.

This paper improves multi-label ranking by reweighting univariate losses, enhancing consistency and performance.

New method MRI improves machine learning models' ability to generalize to unseen data.

Supervised machine learning (ML) algorithms are aimed at maximizing classification performance under available energy and storage constraints. They try to map the training data to the corresponding labels while ensuring generalizability to unseen data. However, they do not integrate meaning-based relationships among la…

There is growing interest in multi-label image classification due to its critical role in web-based image analytics-based applications, such as large-scale image retrieval and browsing. Matrix completion has recently been introduced as a method for transductive (semi-supervised) multi-label classification, and has seve…

Two approaches improve conformal Bayes for label shift, one post-hoc and one in-training.

Conformal Bayes under label shift: post-hoc calibration vs. in-training adaptation

New methods protect privacy while providing accurate prediction sets.

We show that any self-complementary graph with $n$ vertices contains a $K_{\lfloor \frac{n+1}{2}\rfloor}$ minor. We derive topological properties of self-complementary graphs.

Dimensionality reduction and manifold learning methods such as t-Distributed Stochastic Neighbor Embedding (t-SNE) are routinely used to map high-dimensional data into a 2-dimensional space to visualize and explore the data. However, two dimensions are typically insufficient to capture all structure in the data, the sa…

Semi-automatic data annotation helps experts label unlabeled samples based on feature space projection.

Geometrization says `` any closed oriented three-manifold which is prime (not a connected sum) carries one of the eight Thurston geometries OR it has incompressible torus walls whose complementary components each carry one of four particular Thurston geometries" (see Introduction and Figure 1). These geometric componen…

New method classifies reticulocytes from red blood cells without labels.

A new method simplifies noisy data filtering for CNNs.

After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for curr…

Proposes a method for multi-view clustering that integrates consistent and complementary graph regularizers.

Verification determines whether two samples belong to the same class or not, and has important applications such as face and fingerprint verification, where thousands or millions of categories are present but each category has scarce labeled examples, presenting two major challenges for existing deep learning models. W…

We propose a novel learning framework to answer questions such as "if a user is purchasing a shirt, what other items will (s)he need with the shirt?" Our framework learns distributed representations for items from available textual data, with the learned representations representing items in a latent space expressing f…

Deep learning, even if it is very successful nowadays, traditionally needs very large amounts of labeled data to perform excellent on the classification task. In an attempt to solve this problem, the one-shot learning paradigm, which makes use of just one labeled sample per class and prior knowledge, becomes increasing…

Learning product representations that reflect complementary relationship plays a central role in e-commerce recommender system. In the absence of the product relationships graph, which existing methods rely on, there is a need to detect the complementary relationships directly from noisy and sparse customer purchase ac…

In this note we study the Seifert rational homology spheres with two complementary legs, i.e. with a pair of invariants whose fractions add up to one. We give a complete classification of the Seifert manifolds with 3 exceptional fibers and two complementary legs which bound rational homology balls. The result translate…

Proposes a multimodal deep generative model for semi-supervised learning with class imbalance.

SidAE combines autoencoders and Siamese networks for self-supervised feature extraction.