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.
Paper proposes Meta Label Learning to infer global labels for robust few-shot models.
DM2L tackles missing labels in multi-label learning by modeling local and global rank structures.
MeLa learns task relations by inferring global labels for robust FSL.
Visualizing the details of different cellular structures is of great importance to elucidate cellular functions. However, it is challenging to obtain high quality images of different structures directly due to complex cellular environments. Fluorescence staining is a popular technique to label different structures but …
FedReLa: A novel data-level approach for imbalanced federated learning
This paper studies how label noise affects Federated Learning.
Complex textual information extraction tasks are often posed as sequence labeling or \emph{shallow parsing}, where fields are extracted using local labels made consistent through probabilistic inference in a graphical model with constrained transitions. Recently, it has become common to locally parametrize these models…
Label noise in SGD helps converge to flatter minima.
Transferring learned models to novel tasks is a challenging problem, particularly if only very few labeled examples are available. Although this few-shot learning setup has received a lot of attention recently, most proposed methods focus on discriminating novel classes only. Instead, we consider the extended setup of …
Deeper networks are better for local labels, but shallower for global labels.
The goal of eXtreme Multi-label Learning (XML) is to automatically annotate a given data point with the most relevant subset of labels from an extremely large vocabulary of labels (e.g., a million labels). Lately, many attempts have been made to address this problem that achieve reasonable performance on benchmark data…
A filter detects and removes noisy labels in semi-supervised learning.
Learning with Label Proportions (LLP) is the problem of recovering the underlying true labels given a dataset when the data is presented in the form of bags. This paradigm is particularly suitable in contexts where providing individual labels is expensive and label aggregates are more easily obtained. In the healthcare…
Adaptive sampling detects local concept drift with limited labels.
Paper improves short text clustering by integrating semantic relationships into Optimal Transport.
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…
TopoGeoScore selects robust checkpoints using only source-domain representations.
Efficiently selects nearest neighbors for labeling to speed up active learning.
Proposes a new contrastive loss for semi-supervised medical image segmentation.
Class-imbalance is an inherent characteristic of multi-label data which affects the prediction accuracy of most multi-label learning methods. One efficient strategy to deal with this problem is to employ resampling techniques before training the classifier. Existing multilabel sampling methods alleviate the (global) im…
We created financial benchmarks for distribution shifts in crude oil prices and volatility.
GOLFS selects features for clustering by combining global and local information.
Semantic segmentation of land cover classes is fundamental for agricultural and economic development work, from sustainable forestry to urban planning, yet existing training datasets have significant limitations. To generate an open and comprehensive training library of high resolution Earth imagery and high quality la…
Proposes methods to improve multi-label learning by addressing local label imbalance.
GWHD dataset offers 4,700 high-res images of wheat heads.
Human analysts that use anomaly detection systems in practice want to retain the use of simple and explainable global anomaly detectors. In this paper, we propose a novel human-in-the-loop learning algorithm called GLAD (GLocalized Anomaly Detection) that supports global anomaly detectors. GLAD automatically learns the…
FABLE incorporates instance features into PWS label models for improved performance.
Dimensionality reduction is an important operation in information visualization, feature extraction, clustering, regression, and classification, especially for processing noisy high dimensional data. However, most existing approaches preserve either the global or the local structure of the data, but not both. Approache…
We introduce nonlinear higher-order label spreading for semi-supervised learning.
AM-PPI uses multiple predictors to reduce label cost in healthcare AI.
Partial Label Learning (PLL) aims to learn from the data where each training instance is associated with a set of candidate labels, among which only one is correct. Most existing methods deal with such problem by either treating each candidate label equally or identifying the ground-truth label iteratively. In this pap…
Proposes a framework to improve domain adaptation without labeled data.
Given the potential difficulties in obtaining large quantities of labelled data, many works have explored the use of deep semi-supervised learning, which uses both labelled and unlabelled data to train a neural network architecture. The vast majority of SSL approaches focus on implementing the low-density separation as…
It has been shown that deep neural networks (DNNs) may be vulnerable to adversarial attacks, raising the concern on their robustness particularly for safety-critical applications. Recognizing the local nature and limitations of existing adversarial attacks, we present a new type of global adversarial attacks for assess…
Proposes methods to recover labels from shuffled networks using graph averages.
Feature selection and reducing the dimensionality of data is an essential step in data analysis. In this work, we propose a new criterion for feature selection that is formulated as conditional information between features given the labeled variable. Instead of using the standard mutual information measure based on Kul…
A new learning scheme improves model efficiency and performance.
Pairwise Label Smoothing improves deep model generalization by reducing overconfidence.
Annotating automotive radar data is a difficult task. This article presents an automated way of acquiring data labels which uses a highly accurate and portable global navigation satellite system (GNSS). The proposed system is discussed besides a revision of other label acquisitions techniques and a problem description …
Study evaluates graph-based semi-supervised learning under noisy label conditions.
Semi-supervised EM improves convergence rate with labeled samples.
Proposes new attribution methods for trees with regularization.
In this paper, we leverage generative adversarial networks (GANs) to derive an effective algorithm LLP-GAN for learning from label proportions (LLP), where only the bag-level proportional information in labels is available. Endowed with end-to-end structure, LLP-GAN performs approximation in the light of an adversarial…
A new method for unsupervised domain adaptation using manifold learning.
We address the problem of \emph{instance label stability} in multiple instance learning (MIL) classifiers. These classifiers are trained only on globally annotated images (bags), but often can provide fine-grained annotations for image pixels or patches (instances). This is interesting for computer aided diagnosis (CAD…
Measures policy-violating content prevalence with ML-assisted sampling and LLM labeling.
A novel supervised visualization technique for data exploration.
Online structure learning approaches, such as those stemming from Statistical Relational Learning, enable the discovery of complex relations in noisy data streams. However, these methods assume the existence of fully-labelled training data, which is unrealistic for most real-world applications. We present a novel appro…