Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Confidence Coefficient01:24

Confidence Coefficient

7.4K
The confidence coefficient is also known as the confidence level or degree of confidence. It is the percent expression for the probability, 1-α, that the confidence interval contains the true population parameter assuming that the confidence interval is obtained after sufficient unbiased sampling; for example, if the CL = 90%, then in 90 out of 100 samples the interval estimate will enclose the true population parameter. Here α is the area under the curve, distributed equally under...
7.4K
Confirmation Biases01:31

Confirmation Biases

5.4K
The confirmation bias is the tendency to focus on information that confirms our existing beliefs and ignore information that is inconsistent with our expectations. For example, if you think that your professor is not very nice, you notice all of the instances of rude behavior exhibited by the professor while ignoring the countless pleasant interactions he is involved in on a daily basis. Have you ever fallen prey to the confirmation bias, either as the source or target of such bias?
5.4K
Cluster Sampling Method01:20

Cluster Sampling Method

11.5K
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
11.5K
Associative Learning01:27

Associative Learning

246
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
246
Stereotype Threat and Self-fulfilling Prophecies02:09

Stereotype Threat and Self-fulfilling Prophecies

37.2K
When we hold a stereotype about a person, we have expectations that he or she will fulfill that stereotype. A self-fulfilling prophecy is an expectation held by a person that alters his or her behavior in a way that tends to make it true. When we hold stereotypes about a person, we tend to treat the person according to our expectations. This treatment can influence the person to act according to our stereotypic expectations, thus confirming our stereotypic beliefs. Research by Rosenthal and...
37.2K
Improving Translational Accuracy02:07

Improving Translational Accuracy

8.5K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
8.5K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Air pollution and hepatocellular carcinoma: Integrated network toxicology, machine learning, molecular docking and multiomics analysis.

Oncology letters·2026
Same author

Exploring the mechanism by which triphenyl phosphate promotes malignant phenotypes in bladder and kidney cancer through MMP9 based on bioinformatics analysis and experimental validation.

Clinical and experimental medicine·2026
Same author

SGMHA: semantic graph reconstruction with multi-head attention for gene regulatory network inference.

BMC genomics·2026
Same author

Comment on "Analysis of risk factors and development of a prediction model for acute kidney injury in elderly patients after abdominal surgery".

Journal of the Formosan Medical Association = Taiwan yi zhi·2026
Same author

ABRefine: An Accurate Antibody Structure Refinement Method by Equivariant Graph Transformer with Rigid Body Constraint.

Journal of medicinal chemistry·2026
Same author

Increasing Dietary Quercetin Intake Reduces Stroke Risk and Improve Long-Term Survival in Chronic Kidney Disease Patients.

Phytotherapy research : PTR·2026

Related Experiment Video

Updated: May 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

463

Boosting semi-supervised federated learning by effectively exploiting server-side knowledge and client-side

Hongquan Liu1, Yuxi Mi1, Yateng Tang2

  • 1Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, Shanghai, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 13, 2025
PubMed
Summary

This study introduces a novel semi-supervised federated learning (SSFL) method to improve model training with limited labeled data. The approach effectively uses server knowledge and client data, even with uncertain labels, outperforming existing techniques.

Keywords:
Federated learningHeterogeneous dataSemi-supervised federated learningSemi-supervised learningUnconfident pseudo-label utilization

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

434
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K

Related Experiment Videos

Last Updated: May 13, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

463
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

434
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Data Science

Background:

  • Semi-supervised federated learning (SSFL) trains models with less labeled data, crucial when data is decentralized.
  • The label-at-server scenario presents challenges due to non-IID client data and unreliable pseudo-labels, potentially biasing local training.
  • Existing methods often underutilize data by discarding uncertain pseudo-labels and fail to leverage server knowledge effectively during local training.

Purpose of the Study:

  • To enhance SSFL performance by leveraging server-side labeled data and client-side unlabeled data, including samples with uncertain pseudo-labels.
  • To address the bias introduced by non-IID data and incorrect pseudo-labels in the label-at-server setting.
  • To develop a method that improves model accuracy and convergence speed while reducing communication costs.

Main Methods:

  • Proposed a representation alignment module to mitigate non-IID data influence by aligning local features with server-side class proxies.
  • Introduced a shrink loss function to manage risks associated with unreliable pseudo-labels, enabling the use of more client data.
  • Evaluated the method on five benchmark datasets under various non-IID settings.

Main Results:

  • The proposed method significantly outperforms existing SSFL techniques across diverse experimental settings.
  • The approach effectively mitigates bias stemming from non-IID data and pseudo-label inaccuracies.
  • Demonstrated improved performance and faster convergence compared to prior methods.
  • Achieved target performance with reduced communication costs.

Conclusions:

  • The novel SSFL method effectively exploits both server and client data, including uncertain samples, to enhance model training.
  • The representation alignment and shrink loss components are key to overcoming challenges in the label-at-server scenario.
  • The method offers a more efficient and effective approach to SSFL, reducing reliance on extensive labeled datasets and communication overhead.