A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper improves deep learning for instance-level classification from label proportions.
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 investigating the dimensionality of the deep representation subspace of training samples. …
Learning from Label Proportions (LLP) is a learning setting, where the training data is provided in groups, or "bags", and only the proportion of each class in each bag is known. The task is to learn a model to predict the class labels of the individual instances. LLP has broad applications in political science, market…
New attacks reveal training label proportions in federated learning.
New framework for weakly supervised learning from label proportions.
Deep learning systems thrive on abundance of labeled training data but such data is not always available, calling for alternative methods of supervision. One such method is expectation regularization (XR) (Mann and McCallum, 2007), where models are trained based on expected label proportions. We propose a novel applica…
We study the problem of learning with label proportions in which the training data is provided in groups and only the proportion of each class in each group is known. We propose a new method called proportion-SVM, or SVM, which explicitly models the latent unknown instance labels together with the known group …
We propose a learning algorithm capable of learning from label proportions instead of direct data labels. In this scenario, our data are arranged into various bags of a certain size, and only the proportions of each label within a given bag are known. This is a common situation in cases where per-data labeling is lengt…
This work efficiently learns linear threshold functions from label proportions using Gaussian distributions.
Paper proposes a new model using consistency regularization for learning from label proportions.
The paper explores learning from label proportions, showing differences in efficiency between LLP and PAC learning.
This work addresses two classification problems that fall under the heading of domain adaptation, wherein the distributions of training and testing examples differ. The first problem studied is that of class proportion estimation, which is the problem of estimating the class proportions in an unlabeled testing data set…
New method for estimating class proportions in open-set label shift data.
RLSbench benchmarks domain adaptation under label proportion shifts, revealing widespread failures and proposing a two-step meta-algorithm.
Modern machine learning techniques can be used to construct powerful models for difficult collider physics problems. In many applications, however, these models are trained on imperfect simulations due to a lack of truth-level information in the data, which risks the model learning artifacts of the simulation. In this …
In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is independent of the true class label, or that the noise proportions for each class are …
A common approach in positive-unlabeled learning is to train a classification model between labeled and unlabeled data. This strategy is in fact known to give an optimal classifier under mild conditions; however, it results in biased empirical estimates of the classifier performance. In this work, we show that the typi…
New learning rules achieve optimal sample complexity for weakly supervised classification.
We study binary classification in the setting where the learner is presented with multiple corrupted training samples, with possibly different sample sizes and degrees of corruption, and introduce an approach based on minimizing a weighted combination of corruption-corrected empirical risks. We establish a generalizati…
This work tackles robust multi-source domain adaptation under label shift.
A new large-scale tabular benchmark for Learning from Label Proportions.
Learning with label proportions (LLP), which is a learning task that only provides unlabeled data in bags and each bag's label proportion, has widespread successful applications in practice. However, most of the existing LLP methods don't consider the knowledge transfer for uncertain data. This paper presents a transfe…
We are interested in estimating individual labels given only coarse, aggregated signal over the data points. In our setting, we receive sets ("bags") of unlabeled instances with constraints on label proportions. We relax the unrealistic assumption of known label proportions, made in previous work; instead, we assume on…
We propose Rademacher complexity bounds for multiclass classifiers trained with a two-step semi-supervised model. In the first step, the algorithm partitions the partially labeled data and then identifies dense clusters containing predominant classes using the labeled training examples such that the proportion of t…
Learning with Label Proportions (LLP) is the problem of recovering the underlying true labels given a dataset when the data is presented in the form of bags. This paradigm is particularly suitable in contexts where providing individual labels is expensive and label aggregates are more easily obtained. In the healthcare…
In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level proportional information in labels is available. Endowed with end-to-end structure, LLP-GAN performs approximation in the light of an adversarial…
Deep learning algorithms have recently produced state-of-the-art accuracy in many classification tasks, but this success is typically dependent on access to many annotated training examples. For domains without such data, an attractive alternative is to train models with light, or distant supervision. In this paper, we…
New method improves deep learning models robustness to label noise.
A new method uses optimal transport for semi-supervised classification.
Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks (DNNs) poorly generalize from such noisy training datasets. To mitigate the issue, we propose a novel inference method, termed Robust Generative classifier (RoG), applicable …
We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by supervised fine tuning, our method takes advantage of both unlabelled and labelled data…
ETM models improve efficiency in semi-supervised logistic regression.
Easyllp simplifies LLP, achieving low task loss at individual instance level.
Discrepancy between training and testing domains is a fundamental problem in the generalization of machine learning techniques. Recently, several approaches have been proposed to learn domain invariant feature representations through adversarial deep learning. However, label shift, where the percentage of data in each …
learn2mix trains neural nets faster by adjusting class proportions dynamically.
Optimal machine learning requires interpolating training data in high-dimensional linear regression.
Paper tackles dynamic label shift in online learning, achieving optimal performance.
Develops NPMC method for noisy labels, improving multiclass classification accuracy.
Proposes a method to create predictive sets from partially labeled data.
Boosting weak learners to strong ones from aggregate labels is possible for LLP but not for MIL.
EC method calibrates neural networks by matching average confidence to correct label proportion.
Study improves model robustness in noisy datasets.
In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets harvested via these means, sometimes resulting in entire classes of data on which learn…
Adapts pretrained models to new classes without additional training.
Training on mixed distributions improves test performance even when components are unrelated.
A new method for distilling predictions from a teacher model to a student model without original training data.
New research shows that binary classification can be done with noisy data, but only if there are clean samples available.
Proposes LsrKD and MrKD to improve neural network training performance.