Smoothed adaptive weighting for imbalanced semi-supervised learning: Improve reliability against unknown distribution data
Despite recent promising results on semi-supervised learning (SSL), data imbalance,
particularly in the unlabeled dataset, could significantly impact the training performance of a …
particularly in the unlabeled dataset, could significantly impact the training performance of a …
Extreme f-measure maximization using sparse probability estimates
K Jasinska, K Dembczynski… - International …, 2016 - proceedings.mlr.press
We consider the problem of (macro) F-measure maximization in the context of extreme multi-
label classification (XMLC), ie, multi-label classification with extremely large label spaces …
label classification (XMLC), ie, multi-label classification with extremely large label spaces …
Named entity recognition with stack residual lstm and trainable bias decoding
Recurrent Neural Network models are the state-of-the-art for Named Entity Recognition
(NER). We present two innovations to improve the performance of these models. The first …
(NER). We present two innovations to improve the performance of these models. The first …
Optimizing the multiclass F-measure via biconcave programming
H Narasimhan, W Pan, P Kar… - 2016 IEEE 16th …, 2016 - ieeexplore.ieee.org
The F-measure and its variants are performance measures of choice for evaluating
classification and retrieval tasks in the presence of severe class imbalance. It is thus highly …
classification and retrieval tasks in the presence of severe class imbalance. It is thus highly …
Probabilistic label trees for extreme multi-label classification
K Jasinska-Kobus, M Wydmuch, K Dembczynski… - arXiv preprint arXiv …, 2020 - arxiv.org
Extreme multi-label classification (XMLC) is a learning task of tagging instances with a small
subset of relevant labels chosen from an extremely large pool of possible labels. Problems …
subset of relevant labels chosen from an extremely large pool of possible labels. Problems …
Optimizing generalized rate metrics with three players
H Narasimhan, A Cotter… - Advances in Neural …, 2019 - proceedings.neurips.cc
We present a general framework for solving a large class of learning problems with non-
linear functions of classification rates. This includes problems where one wishes to optimize …
linear functions of classification rates. This includes problems where one wishes to optimize …
[HTML][HTML] An unsupervised pattern recognition methodology based on factor analysis and a genetic-DBSCAN algorithm to infer operational conditions from strain …
JC PERAFáN-LóPEZ, J Sierra-Pérez - Chinese Journal of Aeronautics, 2021 - Elsevier
Abstract Structural Health Monitoring (SHM) suggests the use of machine learning
algorithms with the aim of understanding specific behaviors in a structural system. This work …
algorithms with the aim of understanding specific behaviors in a structural system. This work …
Binary classification with karmic, threshold-quasi-concave metrics
Complex performance measures, beyond the popular measure of accuracy, are increasingly
being used in the context of binary classification. These complex performance measures are …
being used in the context of binary classification. These complex performance measures are …
Attentional-Biased Stochastic Gradient Descent
In this paper, we present a simple yet effective provable method (named ABSGD) for
addressing the data imbalance or label noise problem in deep learning. Our method is a …
addressing the data imbalance or label noise problem in deep learning. Our method is a …
A framework of online learning with imbalanced streaming data
A challenge for mining large-scale streaming data overlooked by most existing studies on
online learning is the skewdistribution of examples over different classes. Many previous …
online learning is the skewdistribution of examples over different classes. Many previous …