Related Experiment Video
Updated: Jul 7, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Semi-Supervised Variational Autoencoders for Out-of-Distribution Generation
Frantzeska Lavda1,2, Alexandros Kalousis1
1Geneva School of Business Administration (DMML Group), University of Applied Sciences and Arts Western Switzerland (HES-SO), 1227 Geneva, Switzerland.
Abstract:
Humans are able to quickly adapt to new situations, learn effectively with limited data, and create unique combinations of basic concepts. In contrast, generalizing out-of-distribution (OOD) data and achieving combinatorial generalizations are fundamental challenges for machine learning models. Moreover, obtaining high-quality labeled examples can be very time-consuming and expensive, particularly when specialized skills are required for labeling. To address these issues, we propose BtVAE, a method that utilizes conditional VAE models to achieve combinatorial generalization in certain scenarios and consequently to generate out-of-distribution (OOD) data in a semi-supervised manner. Unlike previous approaches that use new factors of variation during testing, our method uses only existing attributes from the training data but in ways that were not seen during training (e.g., small objects of a specific shape during training and large objects of the same shape during testing).
More Related Videos
Related Concept Videos
Distribution Reliability and Automation
Sampling Distribution
Variance
The standard deviation measures the spread in the same units as the...
Distributions to Estimate Population Parameter
Uniform Distribution
Two essential properties of this distribution are
Vector Algebra: Method of Components
In many applications, the magnitudes and directions of...

