The School of Computer Science is pleased to present…
BeComE – A Novel Framework for Node Classification in Social Graphs
MSc Thesis Proposal by: Akshay Gopan
Date: Friday, 31 May 2024
Time: 10:00 AM
Location: Essex Hall, Room 122
Abstract: In this study, we explore the important role of graph embedding methods in extracting valuable insights from graph structures, specifically focusing on node classification tasks. It is important to know the structural and semantic features and connections within nodes in a graph to learn more detailed hidden patterns. Hence, we propose a hybrid architecture, BeComE (Bert-ComplEx Embedding Model), a novel framework that employs both semantic and structural features from social network structures extracted through label - aware embedding models to aid in node classification in social graphs. A Support Vector Machine (SVM) classifier receives these vector embeddings as input features for classification tasks on social graphs and networks. The evaluation shows that BeComE gives state-of-the-art results on the benchmarking data sets.
Keywords: node classification, social network analysis, language model, knowledge graph embedding, representation learning, machine learning.
Thesis Committee:
Internal Reader: Dr. Dan Wu
External Reader: Dr. Gokul Bhandari
Advisor: Dr. Ziad Kobti