arXiv research

New research shows label refinement and weak training have limitations for aligning LLMs.

Process mining is a research field focused on the analysis of event data with the aim of extracting insights in processes. Applying process mining techniques on data from smart home environments has the potential to provide valuable insights in (un)healthy habits and to contribute to ambient assisted living solutions. …

LARA forecasts financial asset trends by refining noisy labels and extracting profitable samples.

PAS method improves UDA by progressively refining subspaces for reliable pseudo-labels.

Automated labeling of intracranial arteries improves accuracy and efficiency.

INN method refines clean labeled data from noisy labels.

Improved self-distillation reduces label noise and enhances model accuracy.

Solves biased pseudo-labels in imbalanced SSL by refining them.

New method observes learning paths to improve model supervision.

A new criterion for deep active learning selects minimal labeled data points.

Refines neural network predictions using background knowledge for improved accuracy.

This work tackles robust multi-source domain adaptation under label shift.

Paper refines braidoid equivalence for spherical knotoids.

Applying machine learning in the health care domain has shown promising results in recent years. Interpretable outputs from learning algorithms are desirable for decision making by health care personnel. In this work, we explore the possibility of utilizing causal relationships to refine diagnostic prediction. We focus…

CAGNN learns graph embeddings without labels by clustering and refining graph topology.

Self-training improves model accuracy by refining pseudo-labels.

Proposes a progressive label correction method for feature-dependent label noise.

Proposes a robust VIB approach using soft labels and mutual info estimation.

Label aggregation makes learning robust to noisy labels.

PG-EVIKAL refines molecular property predictions using neighbor fusion and evidential neural networks.

Automated machine learning (AutoML) has received increasing attention in the recent past. While the main tools for AutoML, such as Auto-WEKA, TPOT, and auto-sklearn, mainly deal with single-label classification and regression, there is very little work on other types of machine learning tasks. In particular, there is a…

Efficiently learns from partial labels using variational inference.

We introduce a new and improved characterization of the label complexity of disagreement-based active learning, in which the leading quantity is the version space compression set size. This quantity is defined as the size of the smallest subset of the training data that induces the same version space. We show various a…

New algorithms improve community detection in network data with strong consistency.

This paper examines error bounds for deep learning classifiers with noisy labels.

This paper refines human labeling as a measurement process, revealing four sources of variation.

Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning. Many real life data sets contain a small amount of labelled data points, that are typically disregarded when training generative models. We propose the Cluster-aware Generative Mod…

Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, co…

Crowdsourcing is a popular paradigm for effectively collecting labels at low cost. The Dawid-Skene estimator has been widely used for inferring the true labels from the noisy labels provided by non-expert crowdsourcing workers. However, since the estimator maximizes a non-convex log-likelihood function, it is hard to t…

While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. In this work, we consider the problem of SSL multi-class classification with very few labelled instances. We introduce tw…

Paper tackles causal inference with partially labeled data, introducing robust methods.

Generating large quantities of quality labeled data in medical imaging is very time consuming and expensive. The performance of supervised algorithms for various tasks on imaging has improved drastically over the years, however the availability of data to train these algorithms have become one of the main bottlenecks f…

Scarcity of labeled data is one of the most frequent problems faced in machine learning. This is particularly true in relation extraction in text mining, where large corpora of texts exists in many application domains, while labeling of text data requires an expert to invest much time to read the documents. Overall, st…

The recent state-of-the-art deep learning methods have significantly improved brain tumor segmentation. However, fully supervised training requires a large amount of manually labeled masks, which is highly time-consuming and needs domain expertise. Weakly supervised learning with scribbles provides a good trade-off bet…

WeLa-VAE learns interpretable disentangled representations with weak supervision.

This article studies the achievable guarantees on the error rates of certain learning algorithms, with particular focus on refining logarithmic factors. Many of the results are based on a general technique for obtaining bounds on the error rates of sample-consistent classifiers with monotonic error regions, in the real…

Paper shows noisy labels can improve PLR variable selection.

Proposes a novel graph self-training method with EM regularization for semi-supervised node classification.

Big models pretrain and fine-tune for semi-supervised learning on ImageNet.

Framework controls uncertainty in LLMs without labels or probabilities.

Recent advances in Graph Convolutional Networks (GCNs) have led to state-of-the-art performance on various graph-related tasks. However, most existing GCN models do not explicitly identify whether all the aggregated neighbors are valuable to the learning tasks, which may harm the learning performance. In this paper, we…

New method estimates hidden binary mixture model centers efficiently.

New method tackles label noise on imbalanced datasets by considering class-specific uncertainty.

Study on online regression with noise, achieving near-optimal regret bounds.

BOSS learns from one labeled sample per class to match fully supervised performance.

AutoElicit uses LLMs to quickly create expert priors for predictive models.

In many real applications of statistical learning, a decision made from misclassification can be too costly to afford; in this case, a reject option, which defers the decision until further investigation is conducted, is often preferred. In recent years, there has been much development for binary classification with a …

Nested learning improves model performance on multi-granular tasks.