ChainNet: Learning on Blockchain Graphs with Topological Features

Abstract

With emergence of blockchain technologies and the associated cryptocurrencies, such as Bitcoin, understanding network dynamics behind Blockchain graphs has become a rapidly evolving research direction. Unlike other financial networks, such as stock and currency trading, blockchain based cryptocurrencies have the entire transaction graph accessible to the public (i.e., all transactions can be downloaded and analyzed). A natural question is then to ask whether the dynamics of the transaction graph impacts the price of the underlying cryptocurrency. We show that standard graph features such as degree distribution of the transaction graph may not be sufficient to capture network dynamics and its potential impact on fluctuations of Bitcoin price. In contrast, the new graph associated topological features computed using the tools of persistent homology, are found to exhibit a high utility for predicting Bitcoin price dynamics. Using the proposed persistent homology-based techniques, we offer a new elegant, easily extendable and computationally light approach for graph representation learning on Blockchain.

RETRACTED: Hybrid blockchain–based privacy-preserving electronic medical records sharing scheme across medical information control system

“…Blockchain can be divided into three categories: public, consortium and private blockchain. 30,31 The overall comparison of these three is shown in Table 1.…”

Machine learning in/for blockchain: Future and challenges

“…One focuses on the recognition of cybercriminal entities using supervised learning (Yin & Vatrapu, 2017) as well as topological data analysis (TDA) (Akcora et al, 2020), while another focuses on the recognition of common categories of entities for most transactions (Jourdan et al, 2018). Section 3.2 reviews Bitcoin price prediction from different perspectives such as probabilistic graphical models (Jourdan et al, 2018), Bayesian regression (Shah & Zhang, 2014), and feature selection on blockchain topological structure using Granger causality and TDA (Akcora et al, 2019; Abay et al, 2019; Dey et al, 2020).…”

“…Chainlet models study the topological features of a single transaction and only take the number of input and output UTXOs into account. Abay et al (2019) extend the chainlet model to a new graphical model, ChainNet, that further considers topological features based on the number of distinct chainlets and the amount of coins transferred by the chainlets. More specifically, from the perspective of all transactions, an occurrence matrix is created to count the number of transactions between distinct chainlets.…”

Detecting Mixing Services via Mining Bitcoin Transaction Network with Hybrid Motifs

“…Since many interactions between objects are intermittent rather than persistent [27], network motifs combined with temporal information were proposed to characterize dynamic homogeneous network [10], and also had an extensive version in heterogeneous information network [28]. Recently, there are many studies utilized network motifs in blockchain transaction network mining tasks, such as price prediction [29], [30], network property analysis [31], exchange pattern mining [23] and so on. Network attributes play important roles in network mining tasks [11], nevertheless, few work have been conducted to considering in the construction of specific attributes.…”