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.
Generative model creates synthetic unlabeled data for SSL.
MTL method uses unlabeled data with pseudo labels to improve classification with disjoint datasets.
MixMOOD improves SSDL by selecting unlabelled data based on deep feature similarity.
Proposes PUUPL for PUL in imbalanced datasets, boosting minority class signals.
We consider the problem of estimating the class prior in an unlabeled dataset. Under the assumption that an additional labeled dataset is available, the class prior can be estimated by fitting a mixture of class-wise data distributions to the unlabeled data distribution. However, in practice, such an additional labeled…
Knowledge distillation is a widely used technique for model compression. We posit that the teacher model used in a distillation setup, captures relationships between classes, that extend beyond the original dataset. We empirically show that a teacher model can transfer this knowledge to a student model even on an {\it …
StyleDiff compares unlabeled datasets using disentangled image spaces.
Deep RL detects anomalies from few labeled examples and large unlabeled data.
Compressing giant neural networks has gained much attention for their extensive applications on edge devices such as cellphones. During the compressing process, one of the most important procedures is to retrain the pre-trained models using the original training dataset. However, due to the consideration of security, p…
This paper considers a semi-supervised learning framework for weakly labeled polyphonic sound event detection problems for the DCASE 2019 challenge's task4 by combining both the tri-training and adversarial learning. The goal of the task4 is to detect onsets and offsets of multiple sound events in a single audio clip. …
Prevents sensitive data generation in diffusion models using labeled and unlabeled data.
Paper tackles leveraging unlabeled data for PU classification and robust generation.
Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets than those required for standard classification. This result is a key hurdle in the deployment of robust machine learning models in many re…
Deep neural networks (DNNs) are incredibly brittle due to adversarial examples. To robustify DNNs, adversarial training was proposed, which requires large-scale but well-labeled data. However, it is quite expensive to annotate large-scale data well. To compensate for this shortage, several seminal works are utilizing l…
Improves anomaly detection with contaminated unlabeled data.
Positive-unlabeled (PU) learning trains a binary classifier using only positive and unlabeled data. A common simplifying assumption is that the positive data is representative of the target positive class. This assumption rarely holds in practice due to temporal drift, domain shift, and/or adversarial manipulation. Thi…
Enhances U-statistics for semi-supervised datasets using unlabeled data.
The recently proposed unlabeled-unlabeled (UU) classification method allows us to train a binary classifier only from two unlabeled datasets with different class priors. Since this method is based on the empirical risk minimization, it works as if it is a supervised classification method, compatible with any model and …
Paper proposes a method to extract style features from unlabeled data.
Bayesian framework uses unlabeled data to improve fairness assessment.
BetaDataWeighter learns weights for unlabelled data to improve self-supervised learning accuracy.
Proposes a method to classify binary data from multiple unlabeled datasets.
WILDS 2.0 expands benchmark datasets for unsupervised adaptation.
Enhances few-shot image classification using unlabelled examples.
Enhances adversarial robustness with unlabeled out-of-domain data.
Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model. However, the estimation and classifier learning are normally conducted in a pipeline instead of being jointly optimized.…
TAP transfers knowledge from unlabeled data to improve cross-modal learning.
In-context learning solves PU classification without iterative optimization.
DoubleMatch combines pseudo-labeling with self-supervision for SSL.
Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch between the unlabeled and labeled examples. We investigate this phenomenon for image classification on the CIFAR-10 and the ImageNet datasets, …
ATC predicts target domain accuracy using only labeled and unlabeled data.
ADS filters data points for efficient batch active learning.
Semi-supervised learning uses unlabeled data to improve fairness without sacrificing accuracy.
ORDisCo learns from unlabeled data to improve semi-supervised continual learning.
New framework assesses value of labeled vs unlabeled data in latent variable models.
Existing methods for CWS usually rely on a large number of labeled sentences to train word segmentation models, which are expensive and time-consuming to annotate. Luckily, the unlabeled data is usually easy to collect and many high-quality Chinese lexicons are off-the-shelf, both of which can provide useful informatio…
Federated Learning (FL) proposed in recent years has received significant attention from researchers in that it can bring separate data sources together and build machine learning models in a collaborative but private manner. Yet, in most applications of FL, such as keyboard prediction, labeling data requires virtually…
This paper proposes a semi-conditional normalizing flow model for semi-supervised learning. The model uses both labelled and unlabeled data to learn an explicit model of joint distribution over objects and labels. Semi-conditional architecture of the model allows us to efficiently compute a value and gradients of the m…
Novel categories are commonly defined as those unobserved during training but present during testing. However, partially labelled training datasets can contain unlabelled training samples that belong to novel categories, meaning these can be present in training and testing. This research is the first to generalise betw…
Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that works by guessing low-entropy labels for data-aug…
Proposes a few-shot learning method for feature selection without labeled data.
We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implement many classification problems, including supervised, semi-supervised, positive-unlabelled, noisy-label and suggests a general solution to…
Study improves treatment effect estimation using unlabeled covariates.
Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that th…
Model predicts future term connections in biomedical research.
Semi-Supervised Learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, our experiments illustrate several shortcomings that prior SSL algorithms suffer from. In particular, poor performance when unlabeled and lab…
Improves PU learning for imbalanced data with practical AUL estimation and new training method.
FLowDUP trains personalized models with unlabeled clients in low dimensions.