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.
RAD improves robustness to domain annotation noise without explicit domain annotations.
Framework tackles class imbalance and noisy labels in active learning.
Proposes a new method to improve target annotation in ATR.
Paper tackles medical image diagnosis with unsupervised domain adaptation.
We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a respective classification noise rate). First, we consider the complete information scenario, where the learner knows the noise rates of all…
Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels often contain more errors which can deteriorate a classifier's performance when …
Bayesian method improves deep learning for noisy EEG seizure detection.
An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate user satisfaction use limited feature sets and rely on annotation schemes with low …
spex-LVM infers interpretable latent factors from biomedical data.
Study on noise models for noisy labels in NLP.
Domain shift is unavoidable in real-world applications of object detection. For example, in self-driving cars, the target domain consists of unconstrained road environments which cannot all possibly be observed in training data. Similarly, in surveillance applications sufficiently representative training data may be la…
Study real-world noisy labels from human annotations for better understanding.
Few-shot cell segmentation from diverse sources to target domain.
New method pools labels from similar data items to improve learning from small samples.
ADS filters data points for efficient batch active learning.
CPATTA uses conformal prediction for efficient test-time adaptation.
Paper presents a method to train NER models without labelled data using weak supervision.
Majority Vote is optimal for reliable data labeling under certain conditions.
Automated dialogue quality evaluation using user satisfaction estimates across multiple domains.
Unsupervised learning classifies transient noise in gravitational wave detectors.
Paper tackles instance-dependent label noise by approximating it with part-dependent noise.
We describe a method for selecting relevant new training data for the LSTM-based domain selection component of our personal assistant system. Adding more annotated training data for any ML system typically improves accuracy, but only if it provides examples not already adequately covered in the existing data. However, …
New method uses image-level and pixel-level annotations for brain tumor segmentation.
This study evaluates zero-shot LLMs in finance, finding ChatGPT performs well but fine-tuned models are better.
Integrates multiple datasets to solve open set crowdsourcing problems.
This work improves medical image segmentation with limited annotations using contrastive learning.
Meta-learning method for accurate classifier from noisy annotators' data.
Dynamic residual adapters improve performance across multiple latent domains without domain labels.
Paper tackles active learning under human label variation, proposing a new framework.
Deep learning for supervised learning has achieved astonishing performance in various machine learning applications. However, annotated data is expensive and rare. In practice, only a small portion of data samples are annotated. Pseudo-ensembling-based approaches have achieved state-of-the-art results in computer visio…
Active learning improves inspection systems by using weakly labeled data.
In machine learning the best performance on a certain task is achieved by fully supervised methods when perfect ground truth labels are available. However, labels are often noisy, especially in remote sensing where manually curated public datasets are rare. We study the multi-modal cadaster map alignment problem for wh…
Face recognition system trained with noisy labels.
The predictive performance of supervised learning algorithms depends on the quality of labels. In a typical label collection process, multiple annotators provide subjective noisy estimates of the "truth" under the influence of their varying skill-levels and biases. Blindly treating these noisy labels as the ground trut…
We propose a general-purpose approach to discovering active learning (AL) strategies from data. These strategies are transferable from one domain to another and can be used in conjunction with many machine learning models. To this end, we formalize the annotation process as a Markov decision process, design universal s…
Accurately annotating large scale dataset is notoriously expensive both in time and in money. Although acquiring low-quality-annotated dataset can be much cheaper, it often badly damages the performance of trained models when using such dataset without particular treatment. Various methods have been proposed for learni…
CORES2 removes noisy labels by sieving out corrupted examples.
Discriminative active learning reduces data annotation costs for domain adaptation.
Aims to eliminate domain bias in authentication without domain labels.
Early recognition of abnormal rhythms in ECG signals is crucial for monitoring and diagnosing patients' cardiac conditions, increasing the success rate of the treatment. Classifying abnormal rhythms into exact categories is very challenging due to the broad taxonomy of rhythms, noises and lack of large-scale real-world…
This paper refines human labeling as a measurement process, revealing four sources of variation.
In the absence of sufficient data variation (e.g., scanner and protocol variability) in annotated data, deep neural networks (DNNs) tend to overfit during training. As a result, their performance is significantly lower on data from unseen sources compared to the performance on data from the same source as the training …
Sentiment analysis is a highly subjective and challenging task. Its complexity further increases when applied to the Arabic language, mainly because of the large variety of dialects that are unstandardized and widely used in the Web, especially in social media. While many datasets have been released to train sentiment …
We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the marginal distributions of the domain are aligned, but the labels as wel…
The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on supervised topic models. However, the nature of most annotation tasks, prone to …
Supervised Deep Learning has been highly successful in recent years, achieving state-of-the-art results in most tasks. However, with the ongoing uptake of such methods in industrial applications, the requirement for large amounts of annotated data is often a challenge. In most real world problems, manual annotation is …
When learning a hidden Markov model (HMM), sequen- tial observations can often be complemented by real-valued summary response variables generated from the path of hid- den states. Such settings arise in numerous domains, includ- ing many applications in biology, like motif discovery and genome annotation. In this pape…
TCR improves DNN robustness to noisy labels with minimal overhead.