Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 12 of 12 for “"Negative Sampling"”.
-
How negative sampling provides class balance to rare event case data using a vehicular accident prediction project as a use case scenario
… probability prediction, several methods of data sampling exist to remedy the main issue of rare event case data: a lack of data to collect and learn from. The most effective methods often involve altering the distribution of the training samples in a data set. The least utilized of these methods …
-
Link Prediction on Distributed Systems
… diffusion-based model that incorporates advanced negative sampling and temporal graph representations. The goal is to enhance link prediction accuracy while maintaining scalability in real-world microservice networks. The study evaluates various predictive models, including Random Walk, GNNs, …
-
Towards Efficient and Scalable Deep Learning on Graph-Structured Data
… efficiently avoids the computational burden of negative sampling by using a feature decorrelation objective to prevent representational collapse. To enhance MLP-based models, which are faster but less accurate than GNNs, two papers are presented. OrthoReg tackles an "over-correlation" issue with …
-
Efficient visualization for large-scale and high-dimensional single-cell data
… online optimization method based on the idea of negative sampling. Using this approach, we can preserve the high-dimensional structure of single-cell data in an embedded low-dimensional space that facilitates visual analyses of the data.
-
Scaling contrastive learning batch size by two orders of magnitude
… are fundamentally limited by the number of negative pairs a model can observe, and memory-intensive backbones constrain practical batch sizes. We introduce a three-phase, adapter-augmented training framework that scales contrastive batch sizes by two orders of magnitude – surpassing previous …
-
Learning without Expert Labels for Multimodal Data
… this thesis proposes a novel Distance-aware Negative Sampling method for self-supervised Graph Representation Learning (GRL) that learns node representations directly from the graph structure by maximizing separation between distant nodes and maximizing cohesion among nearby nodes. Second, …
-
Multimodal learning and language models for enhanced knowledge representations
… embedded in large language models along with negative sampling strategies, this framework significantly improves retrieval accuracy and generalizability, particularly for tasks such as claim verification and evidence retrieval. The third contribution introduces TabMDA, a Transformer-based …
-
Classifying Challenging Behaviors in Autism Spectrum Disorder with Neural Document Embeddings
… the original Doc2Vec architecture through Negative Sampling. Once created, these embeddings are initially used as input to a Support Vector Machine classifier to demonstrate the success of binary classification within this problem set. This preliminary exploration achieves promising …
-
Predicting the Interactions of Viral and Human Proteins
… accuracy of such a prediction by introducing a negative sampling scheme that is based on sequence similarity. DeNovo achieved accuracy up to 81% and 86% when predicting for a new viral species and a new viral family, respectively. This result is comparable to the best achieved previously in …
-
Supporting the Discovery of Long-Tail Resources on the Web
… centered around the skip-gram model with negative sampling. Finally, we present an approach to learn representations from network and text jointly that can cope with the partial absence of one modality. Experimental results show close to human performance of our zero-effort query and user …
-
Mine the node association: Dig into the essence of graphs
… can be complicated. For example, competing sampling strategies exist in network embedding based algorithms (e.g., the distant positive sampling strategy, and close negative sampling strategy). Third (the graph challenge), almost any real graph keeps evolving. How to capture the evolution …
-
Enhancing multi-label object recognition in complex images via region-based continual learning
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms