Sökning: "Neurala Nätverk för Grafer"
Visar resultat 1 - 5 av 12 uppsatser innehållade orden Neurala Nätverk för Grafer.
1. Cyber Threat Detection using Machine Learning on Graphs : Continuous-Time Temporal Graph Learning on Provenance Graphs
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Cyber attacks are ubiquitous and increasingly prevalent in industry, society, and governmental departments. They affect the economy, politics, and individuals. LÄS MER
2. Link Prediction Using Learnable Topology Augmentation
Master-uppsats, KTH/Matematik (Avd.)Sammanfattning : Link prediction is a crucial task in many downstream applications of graph machine learning. Graph Neural Networks (GNNs) are a prominent approach for transductive link prediction, where the aim is to predict missing links or connections only within the existing nodes of a given graph. LÄS MER
3. CONNECTING THE DOTS : Exploring gene contexts through knowledge-graph representations of gene-information derived from scientific literature
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Analyzing the data produced by next-generation sequencing technologies relies on access to information synthesized based on previous research findings. The volume of data available in the literature is growing rapidly, and it is becoming increasingly necessary for researchers to use AI or other statistics-based approaches in the analysis of their datasets. LÄS MER
4. Impact of Central Nodes in Information Propagation over Graphs
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : There are many systems which can be represented as graphs, to say the least the networks in which we communicate with each other. Thorough understanding of graph structures enables better predictions of the dynamics in real life networks, such as the spreading of a disease in a community or failure propagation in a system. LÄS MER
5. Reliable graph predictions : Conformal prediction for Graph Neural Networks
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : We have seen a rapid increase in the development of deep learning algorithms in recent decades. However, while these algorithms have unlocked new business areas and led to great development in many fields, they are usually limited to Euclidean data. LÄS MER