TopoDetect: Framework for Topological Features Detection in Graph Embeddings
This work provides a tool for researchers and practitioners in graph machine learning to analyze embedding quality, but it is incremental as it focuses on evaluation rather than introducing new methods.
The authors tackled the problem of assessing whether graph embeddings preserve key topological features like node degree and triangle count, and they developed TopoDetect, a Python package that enables investigation and visualization of these features and evaluates their impact on downstream tasks like clustering and classification.
TopoDetect is a Python package that allows the user to investigate if important topological features, such as the Degree of the nodes, their Triangle Count, or their Local Clustering Score, are preserved in the embeddings of graph representation models. Additionally, the framework enables the visualization of the embeddings according to the distribution of the topological features among the nodes. Moreover, TopoDetect enables us to study the effect of the preservation of these features by evaluating the performance of the embeddings on downstream learning tasks such as clustering and classification.