• Corpus ID: 15008961

Learning from labeled and unlabeled data with label propagation

@inproceedings{Zhu2002LearningFL,
  title={Learning from labeled and unlabeled data with label propagation},
  author={Xiaojin Zhu and Zoubin Ghahramani},
  year={2002}
}
We investigate the use of unlabeled data to help labeled data in cl ssification. We propose a simple iterative algorithm, label pro pagation, to propagate labels through the dataset along high density are as d fined by unlabeled data. We analyze the algorithm, show its solution , and its connection to several other algorithms. We also show how to lear n p ameters by minimum spanning tree heuristic and entropy minimiz ation, and the algorithm’s ability to perform feature selection. Expe riment… 
Combining active learning and graph-based semi-supervised learning
  • J. Candao, Lilian Berton
  • Computer Science
    Anais do Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2019)
  • 2019
TLDR
Experimental results in artificial and real datasets indicate that the proposed approach requires significantly less labeled instances to reach the same performance of random label selection.
Graph-Based Active Learning Based on Label Propagation
TLDR
This work proposes a graph-based active learning method, which can also handle multi-class problems, in the entropy reduction framework and outperforms the traditional sampling methods on selected datasets.
Supervised Classification Leveraging Refined Unlabeled Data
TLDR
This thesis focuses on how unlabeled data can improve supervised learning classi-fiers in all contexts, for both scarce to abundant label situations, and recommends data-processing and algorithmic solutions appropriate to real-world situations.
Semi-Supervised Learning Using Random Walk Limiting Probabilities
TLDR
A semi-supervised technique that uses random walk limiting probabilities to propagate label information through a network of unlabeled instances via a biased random walk.
Label Propagation Through Optimal Transport
TLDR
The proposed approach, Optimal Transport Propagation (OTP), performs in an incremental process, label propagation through the edges of a complete bipartite edge-weighted graph, whose affinity matrix is constructed from the optimal transport plan between empirical measures defined on labeled and unlabeled data.
Relation Extraction Using Label Propagation Based Semi-Supervised Learning
TLDR
This paper investigates a graph based semi-supervised learning algorithm, a label propagation (LP) algorithm, for relation extraction that represents labeled and unlabeled examples and their distances as the nodes and the weights of edges of a graph, and tries to obtain a labeling function to satisfy two constraints.
AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning
TLDR
This paper introduces an aggregation module for consistency regularization framework that aggregates the initial pseudo labels based on the similarity between the instances, and proposes a novel uncertaintybased confidence measure for the pseudo label by considering the consensus among multiple hypotheses with different subsets of the queue.
Analysis of label noise in graph-based semi-supervised learning
TLDR
This work aims to perform an extensive empirical evaluation of existing graph-based semi-supervised algorithms, like Gaussian Fields and Harmonic Functions, Local and Global Consistency, Laplacian Eigenmaps, Graph Transduction Through Alternating Minimization, and so on, to compare the accuracy of classifiers while varying the amount of labeled data and label noise for many different samples.
Hypergraph Label Propagation Network
TLDR
A Hypergraph Label Propagation Network (HLPN) is proposed which combines hypergraph-based label propagation and deep neural networks in order to optimize the feature embedding for optimal hypergraph learning through an end-to-end architecture and can significantly outperform the state-of-the-art methods and alternative approaches.
Robust Graph Hyperparameter Learning for Graph Based Semi-supervised Classification
TLDR
This work proposes a technique to learn the hyperparameters for graphs that yields low leave-one-out prediction error on labeled data while retaining high stability of the prediction on unlabeled data.
...
...

References

SHOWING 1-10 OF 17 REFERENCES
Learning from Labeled and Unlabeled Data using Graph Mincuts
TLDR
An algorithm based on finding minimum cuts in graphs, that uses pairwise relationships among the examples in order to learn from both labeled and unlabeled data is considered.
Partially labeled classification with Markov random walks
TLDR
This work combines a limited number of labeled examples with a Markov random walk representation over the unlabeled examples and develops and compares several estimation criteria/algorithms suited to this representation.
IEEE transactions on pattern analysis and machine intelligence
TLDR
This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis and addressing interesting real-world computer Vision and multimedia applications.
Link Analysis, Eigenvectors and Stability
TLDR
This paper addresses the question of when HITS and PageRank can be expected to give stable rankings under small perturbations to the hyperlink patterns, using tools from matrix perturbation theory and Markov chain theory.
Diffusion Kernels on Graphs and Other Discrete Input Spaces
TLDR
This paper proposes a general method of constructing natural families of kernels over discrete structures, based on the matrix exponentiation idea, and focuses on generating kernels on graphs, for which a special class of exponential kernels called diffusion kernels are proposed.
Handwritten Digit Recognition with a Back-Propagation Network
TLDR
Minimal preprocessing of the data was required, but architecture of the network was highly constrained and specifically designed for the task, and has 1% error rate and about a 9% reject rate on zipcode digits provided by the U.S. Postal Service.
A Database for Handwritten Text Recognition Research
  • J. Hull
  • Computer Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1994
TLDR
An image database for handwritten text recognition research is described that contains digital images of approximately 5000 city names, 5000 state names, 10000 ZIP Codes, and 50000 alphanumeric characters to overcome the limitations of earlier databases.
On the shortest spanning subtree of a graph and the traveling salesman problem
7. A. Kurosh, Ringtheoretische Probleme die mit dem Burnsideschen Problem uber periodische Gruppen in Zussammenhang stehen, Bull. Acad. Sei. URSS, Ser. Math. vol. 5 (1941) pp. 233-240. 8. J.
An Introduction to Variational Methods for Graphical Models
  • Learning in Graphical Models
  • 1998
...
...