Computationally Efficient Wasserstein Loss for Structured Labels
- URL: http://arxiv.org/abs/2103.00899v1
- Date: Mon, 1 Mar 2021 10:45:13 GMT
- Title: Computationally Efficient Wasserstein Loss for Structured Labels
- Authors: Ayato Toyokuni, Sho Yokoi, Hisashi Kashima, Makoto Yamada
- Abstract summary: We propose a tree-Wasserstein distance regularized LDL algorithm, focusing on hierarchical text classification tasks.
We show that the proposed method successfully considers the structure of labels during training, and it compares favorably with the Sinkhorn algorithm in terms of computation time and memory usage.
- Score: 37.33134854462556
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The problem of estimating the probability distribution of labels has been
widely studied as a label distribution learning (LDL) problem, whose
applications include age estimation, emotion analysis, and semantic
segmentation. We propose a tree-Wasserstein distance regularized LDL algorithm,
focusing on hierarchical text classification tasks. We propose predicting the
entire label hierarchy using neural networks, where the similarity between
predicted and true labels is measured using the tree-Wasserstein distance.
Through experiments using synthetic and real-world datasets, we demonstrate
that the proposed method successfully considers the structure of labels during
training, and it compares favorably with the Sinkhorn algorithm in terms of
computation time and memory usage.
Related papers
- Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning [0.0]
This study explores label propagation in semi-supervised learning.
We employ a transductive label propagation method based on the manifold assumption for text classification.
By extending labels based on cosine proximity within a nearest neighbor graph from network embeddings, we combine unlabeled data into supervised learning.
arXiv Detail & Related papers (2024-10-15T07:25:33Z) - Inaccurate Label Distribution Learning with Dependency Noise [52.08553913094809]
We introduce the Dependent Noise-based Inaccurate Label Distribution Learning (DN-ILDL) framework to tackle the challenges posed by noise in label distribution learning.
We show that DN-ILDL effectively addresses the ILDL problem and outperforms existing LDL methods.
arXiv Detail & Related papers (2024-05-26T07:58:07Z) - Label distribution learning via label correlation grid [9.340734188957727]
We propose a textbfLabel textbfCorrelation textbfGrid (LCG) to model the uncertainty of label relationships.
Our network learns the LCG to accurately estimate the label distribution for each instance.
arXiv Detail & Related papers (2022-10-15T03:58:15Z) - 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) - AutoGeoLabel: Automated Label Generation for Geospatial Machine Learning [69.47585818994959]
We evaluate a big data processing pipeline to auto-generate labels for remote sensing data.
We utilize the big geo-data platform IBM PAIRS to dynamically generate such labels in dense urban areas.
arXiv Detail & Related papers (2022-01-31T20:02:22Z) - Multi-label Classification via Adaptive Resonance Theory-based
Clustering [9.58897929546191]
The paper proposes a multi-label classification algorithm capable of continual learning by applying an Adaptive Resonance Theory (ART)-based clustering algorithm and the Bayesian approach for label probability computation.
Experimental results with synthetic and real-world multi-label datasets show that the proposed algorithm has competitive classification performance to other well-known algorithms.
arXiv Detail & Related papers (2021-03-02T06:51:41Z) - PseudoSeg: Designing Pseudo Labels for Semantic Segmentation [78.35515004654553]
We present a re-design of pseudo-labeling to generate structured pseudo labels for training with unlabeled or weakly-labeled data.
We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes.
arXiv Detail & Related papers (2020-10-19T17:59:30Z) - Analysis of label noise in graph-based semi-supervised learning [2.4366811507669124]
In machine learning, one must acquire labels to help supervise a model that will be able to generalize to unseen data.
It is often the case that most of our data is unlabeled.
Semi-supervised learning (SSL) alleviates that by making strong assumptions about the relation between the labels and the input data distribution.
arXiv Detail & Related papers (2020-09-27T22:13:20Z) - Gradient Descent in RKHS with Importance Labeling [58.79085525115987]
We study importance labeling problem, in which we are given many unlabeled data.
We propose a new importance labeling scheme that can effectively select an informative subset of unlabeled data.
arXiv Detail & Related papers (2020-06-19T01:55:00Z) - 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.