A1015
Title: Effective multidimensional persistence for Ethereum network representation learning
Authors: Yuzhou Chen - Temple University (United States) [presenting]
Abstract: Topological data analysis (TDA) is gaining prominence across a wide spectrum of machine learning tasks spanning manifold learning to graph classification. A pivotal technique within TDA is persistent homology (PH), which furnishes an exclusive topological imprint of data by tracing the evolution of latent structures as a scale parameter changes. Present PH tools are confined to analyzing data through a single filter parameter. However, many scenarios necessitate the consideration of multiple relevant parameters to attain finer insights into the data. The issue is addressed by introducing the effective multidimensional persistence (EMP) framework, empowering data exploration by simultaneously varying multiple scale parameters. The framework integrates descriptor functions into the analysis process, yielding a highly expressive data summary. It seamlessly integrates established single PH summaries into multidimensional counterparts like EMP landscapes, silhouettes, images, and surfaces. In addition, EMP's utility is demonstrated in Ethereum network prediction tasks, showing its effectiveness. Results reveal EMP enhances various single PH descriptors, outperforming state-of-the-art baselines.
