On-device research index

arXiv research

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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “meta-labels”

The Role of Global Labels in Few-Shot Classification and How to Infer Themcs.LG

Paper proposes Meta Label Learning to infer global labels for robust few-shot models.

problem Few-shot learning with limited training data.

method Meta Label Learning (MeLa) framework that infers global labels.

result MeLa framework is competitive with existing methods and robust for few-shot learning.

few-shot learning meta-learning global labels pre-training robust models

2021-08-09abs ↗pdf ↗

Representation Learning Through Latent Canonicalizationscs.LG

This research improves representation learning for new domains with limited new supervision.

problem Learning representations that generalize well to new domains with minimal new data.

method Encourages linearity of factors of variation through learned linear transformations called latent canonicalizers.

result Reduces the number of observations needed to generalize to a similar target domain compared to supervised baselines.

representation learning latent canonicalizers disentanglement meta-labels generalization

2020-02-26abs ↗pdf ↗

A Novel Meta Learning Framework for Feature Selection using Data Synthesis and Fuzzy Similaritycs.LG

A new method selects the best feature selection technique for datasets.

problem Selecting the best feature selection method for unseen datasets.

method Data synthesis, meta features, fuzzy similarity, classification model training.

result Successfully recommended the best feature selection method for five out of eight datasets.

feature selection meta learning fuzzy similarity classification data synthesis

2020-05-20abs ↗pdf ↗

Meta Label Correction for Noisy Label Learningcs.LG

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…

2019-11-10abs ↗pdf ↗

Meta Soft Label Generation for Noisy Labelscs.CV

MSLG generates soft labels to improve DNN performance on noisy datasets.

problem Significant performance degradation of DNNs due to noisy labels.

method Meta-learning techniques to estimate optimal label distribution and iteratively update soft labels.

result MSLG outperforms state-of-the-art methods by a large margin on various datasets.

Meta Learning Soft Labels Deep Neural Networks Noisy Labels CIFAR10

2020-07-11abs ↗pdf ↗

Towards meta-learning for multi-target regression problemscs.LG

Several multi-target regression methods were devel-oped in the last years aiming at improving predictive performanceby exploring inter-target correlation within the problem. However, none of these methods outperforms the others for all problems. This motivates the development of automatic approachesto recommend the mos…

2019-07-25abs ↗pdf ↗

Robust Meta-Representation Learning via Global Label Inference and Classificationcs.LG

MeLa learns task relations by inferring global labels for robust FSL.

problem Few-shot learning with limited global labels.

method Meta Label Learning (MeLa) and augmented pre-training.

result MeLa outperforms existing methods across diverse benchmarks.

few-shot learning meta-learning global labels robust representation pre-training

2022-12-22abs ↗pdf ↗