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.
Proposes a new model for noisy labels considering multiple labelers and adversarial attacks.
Label smoothing improves model performance even with noisy labels.
We describe a nonparametric topic model for labeled data. The model uses a mixture of random measures (MRM) as a base distribution of the Dirichlet process (DP) of the HDP framework, so we call it the DP-MRM. To model labeled data, we define a DP distributed random measure for each label, and the resulting model genera…
Proposes MGPLL for PL learning with non-random noise.
Retraining with predicted labels improves model accuracy in noisy settings.
Machine learning approaches to multi-label document classification have to date largely relied on discriminative modeling techniques such as support vector machines. A drawback of these approaches is that performance rapidly drops off as the total number of labels and the number of labels per document increase. This pr…
FABLE incorporates instance features into PWS label models for improved performance.
A new Q&A labeling method for assigning labels in machine learning.
A framework learns dynamic soft labels to improve model generalization and accuracy.
Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research community. In this paper, we propose a novel adversarial learning model, PML-GAN, under a generalized encod…
Conditional Random Fields (CRF) are frequently applied for labeling and segmenting sequence data. Morency et al. (2007) introduced hidden state variables in a labeled CRF structure in order to model the latent dynamics within class labels, thus improving the labeling performance. Such a model is known as Latent-Dynamic…
New PL method improves ASR accuracy without pseudo-labels.
Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul challenge. We propose Label Message Passing (LaMP) Neural Networks to efficiently model the joint prediction of multiple labels. LaMP treats labe…
It is challenging to handle a large volume of labels in multi-label learning. However, existing approaches explicitly or implicitly assume that all the labels in the learning process are given, which could be easily violated in changing environments. In this paper, we define and study streaming label learning (SLL), i.…
DynaCor detects noisy labels by learning from corrupted training signals.
Expands weak supervision by allowing partial labels from multiple noisy sources.
DM2L tackles missing labels in multi-label learning by modeling local and global rank structures.
It is well-known that exploiting label correlations is crucially important to multi-label learning. Most of the existing approaches take label correlations as prior knowledge, which may not correctly characterize the real relationships among labels. Besides, label correlations are normally used to regularize the hypoth…
DCEM algorithm reduces bias in machine learning models trained on selective labels.
Paper proposes a universal probabilistic model for handling instance-dependent label noise.
MPVAE learns latent embeddings and label correlations for multi-label classification.
Improved self-distillation reduces label noise and enhances model accuracy.
Logistic regression can handle noisy labels effectively when labels are imperfectly assigned by multiple experts.
Recent work has shown that exploiting relations between labels improves the performance of multi-label classification. We propose a novel framework based on generative adversarial networks (GANs) to model label dependency. The discriminator learns to model label dependency by discriminating real and generated label set…
Study enhances classifier robustness against noisy labels.
Curriculum Labeling improves semi-supervised learning with pseudo-labeling, achieving high accuracy with minimal labeled data.
DP models misspecify LF dependencies, leading to significant performance errors.
Unified model combines feature and label propagation for semi-supervised classification.
The usage of machine learning models has grown substantially and is spreading into several application domains. A common need in using machine learning models is collecting the data required to train these models. In some cases, labeling a massive dataset can be a crippling bottleneck, so there is need to develop model…
Study shows label errors impact model disparity metrics, proposing mitigation methods.
Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep learning models. Weak or noisy supervision could originate from multiple sources i…
A new method handles label noise by leveraging causal information.
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much attention, training text classification models have not. In this paper, we propose an…
Method curates cost-effective, high-quality datasets using AI models.
Adversarial examples are delicately perturbed inputs, which aim to mislead machine learning models towards incorrect outputs. While most of the existing work focuses on generating adversarial perturbations in multi-class classification problems, many real-world applications fall into the multi-label setting in which on…
PML-LFC improves PML by estimating label confidence from both feature and label spaces.
Graph attention network improves MLTC by capturing label dependencies.
ASEs use surrogate estimation to efficiently evaluate model performance with minimal labels.
In multi-label learning, each instance is associated with multiple labels and the crucial task is how to leverage label correlations in building models. Deep neural network methods usually jointly embed the feature and label information into a latent space to exploit label correlations. However, the success of these me…
In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector belongs to at least one group. Then, instead of the true label of each instance, we observe the label distribution of the instances associated …
Inserting label noise can improve model accuracy and fairness.
We study the problem of aggregation noisy labels. Usually, it is solved by proposing a stochastic model for the process of generating noisy labels and then estimating the model parameters using the observed noisy labels. A traditional assumption underlying previously introduced generative models is that each object has…
Unified model for sequence labeling and classification.
Study reveals pervasive label errors in test sets, affecting machine learning benchmarks.
Study on noise models for noisy labels in NLP.
The graph convolution network (GCN) is a widely-used facility to realize graph-based semi-supervised learning, which usually integrates node features and graph topologic information to build learning models. However, as for multi-label learning tasks, the supervision part of GCN simply minimizes the cross-entropy loss …
Semi-supervised learning improves with partial label information.
FLAME auto-labels mobile data efficiently on diverse processors.