Category: Graph-Based Learning

Graph Embedding Propagation

Graph embedding propagation is a technique used to represent nodes, edges, or entire graphs as vectors of numbers, while spreading information across the graph structure. This process allows the properties and relationships of nodes to influence each other, so that the final vector captures both the characteristics of a node and its position in the…

Secure Knowledge Graphs

Secure knowledge graphs are digital structures that organise and connect information, with added features to protect data from unauthorised access or tampering. They use security measures such as encryption, access controls, and auditing to ensure that only trusted users can view or change sensitive information. These protections help organisations manage complex data relationships while keeping…

Temporal Graph Prediction

Temporal graph prediction is a technique used to forecast future changes in networks where both the structure and connections change over time. Unlike static graphs, temporal graphs capture how relationships between items or people evolve, allowing predictions about future links or behaviours. This helps in understanding and anticipating patterns in dynamic systems such as social…

Neural Symbolic Reasoning

Neural symbolic reasoning is an approach in artificial intelligence that combines neural networks with symbolic logic. Neural networks are good at learning from data, while symbolic logic helps with clear rules and reasoning. By joining these two methods, systems can learn from examples and also follow logical steps to solve problems or make decisions.

Temporal Knowledge Graphs

Temporal Knowledge Graphs are data structures that store information about entities, their relationships, and how these relationships change over time. Unlike standard knowledge graphs, which show static connections, temporal knowledge graphs add a time element to each relationship, helping track when things happen or change. This allows for more accurate analysis of events, trends, and…

Graph-Based Knowledge Fusion

Graph-based knowledge fusion is a technique for combining information from different sources by representing data as nodes and relationships in a graph structure. This method helps identify overlaps, resolve conflicts, and create a unified view of knowledge from multiple datasets. By using graphs, it becomes easier to visualise and manage complex connections between pieces of…

Graph Neural Network Pruning

Graph neural network pruning is a technique used to make graph neural networks (GNNs) smaller and faster by removing unnecessary parts of the model. These parts can include nodes, edges, or parameters that do not contribute much to the final prediction. Pruning helps reduce memory use and computation time while keeping most of the model’s…

Knowledge Graph Completion

Knowledge graph completion is the process of filling in missing information or relationships within a knowledge graph. A knowledge graph is a structured network of facts, where entities like people, places, or things are connected by relationships. Because real-world data is often incomplete, algorithms are used to predict and add missing links or facts, making…