SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
- URL: http://arxiv.org/abs/2209.10365v1
- Date: Wed, 21 Sep 2022 14:00:16 GMT
- Title: SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
- Authors: Haobo Wang, Mingxuan Xia, Yixuan Li, Yuren Mao, Lei Feng, Gang Chen,
Junbo Zhao
- Abstract summary: Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth.
We propose SoLar, a novel framework that allows refine the disambiguated labels towards matching the marginal class prior distribution.
SoLar exhibits substantially superior results on standardized benchmarks compared to the previous state-the-art methods.
- Score: 31.535219018410707
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Partial-label learning (PLL) is a peculiar weakly-supervised learning task
where the training samples are generally associated with a set of candidate
labels instead of single ground truth. While a variety of label disambiguation
methods have been proposed in this domain, they normally assume a
class-balanced scenario that may not hold in many real-world applications.
Empirically, we observe degenerated performance of the prior methods when
facing the combinatorial challenge from the long-tailed distribution and
partial-labeling. In this work, we first identify the major reasons that the
prior work failed. We subsequently propose SoLar, a novel Optimal
Transport-based framework that allows to refine the disambiguated labels
towards matching the marginal class prior distribution. SoLar additionally
incorporates a new and systematic mechanism for estimating the long-tailed
class prior distribution under the PLL setup. Through extensive experiments,
SoLar exhibits substantially superior results on standardized benchmarks
compared to the previous state-of-the-art PLL methods. Code and data are
available at: https://github.com/hbzju/SoLar .
Related papers
- Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning [55.4510979153023]
In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth.
To help these mislabeled samples "appeal," we propose the first appeal-based framework.
arXiv Detail & Related papers (2023-12-18T09:09:52Z) - Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label
Learning [97.88458953075205]
Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data.
This paper proposes a novel solution called Class-Aware Pseudo-Labeling (CAP) that performs pseudo-labeling in a class-aware manner.
arXiv Detail & Related papers (2023-05-04T12:52:18Z) - Pseudo Labels Regularization for Imbalanced Partial-Label Learning [11.93067260471484]
The challenge of partial-label learning and long-tail learning lies in matching between a decent marginal prior distribution with drawing the pseudo labels.
By punishing the pseudo labels of head classes, our method implements state-of-art under the standardized benchmarks.
arXiv Detail & Related papers (2023-03-06T15:21:55Z) - Long-Tailed Partial Label Learning via Dynamic Rebalancing [30.16563291182992]
Real-world data usually couples the label ambiguity and heavy imbalance.
LT methods build upon a given class distribution that is unavailable in, and the performance of is severely influenced in long-tailed context.
We propose a dynamic rebalancing method, termed as RECORDS, without assuming any prior knowledge about the class distribution.
arXiv Detail & Related papers (2023-02-10T06:43:53Z) - Dist-PU: Positive-Unlabeled Learning from a Label Distribution
Perspective [89.5370481649529]
We propose a label distribution perspective for PU learning in this paper.
Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions.
Experiments on three benchmark datasets validate the effectiveness of the proposed method.
arXiv Detail & Related papers (2022-12-06T07:38:29Z) - Progressive Purification for Instance-Dependent Partial Label Learning [37.65717805892473]
Partial label learning (PLL) aims to train multiclass classifiers from the examples each annotated with a set of candidate labels where a fixed but unknown candidate label is correct.
The candidate labels are always instance-dependent in practice and there is no theoretical guarantee that the model trained on the instance-dependent examples can converge to an ideal one.
In this paper, a theoretically grounded and practically effective approach named POP, i.e. PrOgressive Purification, is proposed. Specifically, POP updates the learning model and purifies each candidate label set progressively in every epoch.
arXiv Detail & Related papers (2022-06-02T02:07:12Z) - Learning from Label Proportions by Learning with Label Noise [30.7933303912474]
Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags.
We provide a theoretically grounded approach to LLP based on a reduction to learning with label noise.
Our approach demonstrates improved empirical performance in deep learning scenarios across multiple datasets and architectures.
arXiv Detail & Related papers (2022-03-04T18:52:21Z) - Instance-Dependent Partial Label Learning [69.49681837908511]
Partial label learning is a typical weakly supervised learning problem.
Most existing approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels.
In this paper, we consider instance-dependent and assume that each example is associated with a latent label distribution constituted by the real number of each label.
arXiv Detail & Related papers (2021-10-25T12:50:26Z) - Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced
Semi-Supervised Learning [80.05441565830726]
This paper addresses imbalanced semi-supervised learning, where heavily biased pseudo-labels can harm the model performance.
We propose a general pseudo-labeling framework to address the bias motivated by this observation.
We term the novel pseudo-labeling framework for imbalanced SSL as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label.
arXiv Detail & Related papers (2021-06-10T11:58:25Z) - Progressive Identification of True Labels for Partial-Label Learning [112.94467491335611]
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label.
Most existing methods elaborately designed as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data.
This paper proposes a novel framework of classifier with flexibility on the model and optimization algorithm.
arXiv Detail & Related papers (2020-02-19T08:35:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.