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.
A new method simplifies noisy data filtering for CNNs.
Subset selection improves weak supervision performance.
Supervised object detection and semantic segmentation require object or even pixel level annotations. When there exist image level labels only, it is challenging for weakly supervised algorithms to achieve accurate predictions. The accuracy achieved by top weakly supervised algorithms is still significantly lower than …
New taxonomy reveals different detection limits for various types of fraud.
Nemo improves WS learning pipeline by 20%.
In this paper, we propose a capsule-based neural network model to solve the semantic segmentation problem. By taking advantage of the extractable part-whole dependencies available in capsule layers, we derive the probabilities of the class labels for individual capsules through a recursive, layer-by-layer procedure. We…
New Roman pipeline detects astronomical transients.
Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative examples for labeling so that human time is not wasted labeling irrelevant, redundant…
Label aggregation makes learning robust to noisy labels.
End-to-end speech synthesis is a promising approach that directly converts raw text to speech. Although it was shown that Tacotron2 outperforms classical pipeline systems with regards to naturalness in English, its applicability to other languages is still unknown. Japanese could be one of the most difficult languages …
Study semi-supervised learning with noisy proxy covariates, deriving bounds and showing gains.
This paper evaluates conformal prediction for aerial image classification in challenging environments.
CascadeXML improves multi-resolution learning for XMC with transformer features.
CMRM improves robustness in noisy label settings without requiring privileged knowledge.
Proposes a weighted conformal approach for cluster label uncertainty.
This work compares regularization and constrained inference for label constraints in machine learning.
Label noise is emerging as a pressing issue in sound event classification. This arises as we move towards larger datasets that are difficult to annotate manually, but it is even more severe if datasets are collected automatically from online repositories, where labels are inferred through automated heuristics applied t…
Paper improves deep learning for instance-level classification from label proportions.
Domain Adaptation in 6G wireless networks: When is it green?
OPAL optimizes labeling strategy for precise inference from uncertain models.
Labeling training datasets has become a key barrier to building medical machine learning models. One strategy is to generate training labels programmatically, for example by applying natural language processing pipelines to text reports associated with imaging studies. We propose cross-modal data programming, which gen…
Obtaining enough labeled data to robustly train complex discriminative models is a major bottleneck in the machine learning pipeline. A popular solution is combining multiple sources of weak supervision using generative models. The structure of these models affects training label quality, but is difficult to learn with…
Improves understanding of PWS by calculating influence of sources and data.
AVATAR uses a surrogate model to quickly evaluate ML pipelines, saving time and resources.
Data augmentation is usually used by supervised learning approaches for offline writer identification, but such approaches require extra training data and potentially lead to overfitting errors. In this study, a semi-supervised feature learning pipeline was proposed to improve the performance of writer identification b…
A key requirement for supervised machine learning is labeled training data, which is created by annotating unlabeled data with the appropriate class. Because this process can in many cases not be done by machines, labeling needs to be performed by human domain experts. This process tends to be expensive both in time an…
Early detection of incipient faults is of vital importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings. Popular supervised learning models such as deep neural networks are considered promising due to their ability to directly learn from labeled fault data; however, it is kn…
Hybrid approach combines topic and graph embeddings for legal document clustering.
Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden. Motivated by the observation that work can be reused across pipelines if the intermediate computations are the same, we propose a pipeline-aware approach to hyperparameter tuning. Our approach optimizes both the design and exe…
Modular deep learning framework using pairwise labels without backpropagation.
The paper introduces uncertainty quantification for NER models.
Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however, estimating the dependencies among these sources is a critical challenge. We foc…
Classical Machine Learning (ML) pipelines often comprise of multiple ML models where models, within a pipeline, are trained in isolation. Conversely, when training neural network models, layers composing the neural models are simultaneously trained using backpropagation. We argue that the isolated training scheme of ML…
CheXpert++ improves CheXpert's accuracy and usability for medical radiology reports.
Study proposes a statistical testing framework for evaluating clustering pipelines.
Proposes a novel graph self-training method with EM regularization for semi-supervised node classification.
FavMac maximizes value while controlling cost in multi-label prediction.
The study examines when to trust confidence thresholding in pseudo-labelling regression.
Investigates fairness in pipeline models where individuals may drop out.
Labeling training data is increasingly the largest bottleneck in deploying machine learning systems. We present Snorkel, a first-of-its-kind system that enables users to train state-of-the-art models without hand labeling any training data. Instead, users write labeling functions that express arbitrary heuristics, whic…
Efficiently poisons offline RLHF models by flipping preference labels.
Cancer survival prediction is an active area of research that can help prevent unnecessary therapies and improve patient's quality of life. Gene expression profiling is being widely used in cancer studies to discover informative biomarkers that aid predict different clinical endpoint prediction. We use multiple modalit…
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.…
This paper improves anomaly detection in lane rendering images for safer navigation.
Bayesian neural networks are vulnerable to adversarial attacks.
SLIC-UAV monitors forest recovery using UAVs and machine learning.
In structured output prediction tasks, labeling ground-truth training output is often expensive. However, for many tasks, even when the true output is unknown, we can evaluate predictions using a scalar reward function, which may be easily assembled from human knowledge or non-differentiable pipelines. But searching th…
Data science relies on pipelines that are organized in the form of interdependent computational steps. Each step consists of various candidate algorithms that maybe used for performing a particular function. Each algorithm consists of several hyperparameters. Algorithms and hyperparameters must be optimized as a whole …