The transnational networks of the illicit and illegal antiquities trade are hard to perceive. We suggest representing the trade as a knowledge graph with multiple kinds of relationships that can be transformed by a neural architecture into a “knowledge graph embedding model.” The result is that the vectorization of the knowledge represented in the graph can be queried for missing “knowledge” of the trade by virtue of the various entities’ proximity in the multidimensional embedding space. In this article, we build a knowledge graph about the antiquities trade using a semantic annotation tool, drawing on the series of articles in the Trafficking Culture Project's online encyclopedia. We then use the AmpliGraph package, a series of tools for supervised machine learning (Costabello et al. 2019) to turn the graph into a knowledge graph embedding model. We query the model to predict new hypotheses and to cluster actors in the trade. The model suggests connections between actors and institutions hitherto unsuspected and not otherwise present in the original knowledge graph. This approach could hold enormous potential for illuminating the hidden corners of the illicit antiquities trade. The same method could be applied to other kinds of archaeological knowledge.

Machine learning applications on large-scale network-structured data commonly encode network information in the form of node embeddings. Network embedding algorithms map the nodes into a low-dimensional space such that the nodes that are “similar” with respect to network topology are also close to each other in the embedding space. Real-world networks often have multiple versions or can be “multiplex” with multiple types of edges with different semantics. For such networks, computation of Consensus Embeddings based on the node embeddings of individual versions can be useful for various reasons, including privacy, efficiency, and effectiveness of analyses. Here, we systematically investigate the performance of three dimensionality reduction methods in computing consensus embeddings on networks with multiple versions: singular value decomposition, variational auto-encoders, and canonical correlation analysis (CCA). Our results show that (i) CCA outperforms other dimensionality reduction methods in computing concensus embeddings, (ii) in the context of link prediction, consensus embeddings can be used to make predictions with accuracy close to that provided by embeddings of integrated networks, and (iii) consensus embeddings can be used to improve the efficiency of combinatorial link prediction queries on multiple networks by multiple orders of magnitude.

The link prediction task has found numerous applications in real-world scenarios. However, in most of the cases like interactions, purchases, mobility, etc., links can re-occur again and again across time. As a result, the data being generated is excessively large to handle, associated with the complexity and sparsity of networks. Therefore, we propose a very fast, memory-less, and dynamic sampling-based method for predicting recurring links for a successive future point in time. This method works by biasing the links exponentially based on their time of occurrence, frequency, and stability. To evaluate the efficiency of our method, we carried out rigorous experiments with massive real-world graph streams. Our empirical results show that the proposed method outperforms the state-of-the-art method for recurring links prediction. Additionally, we also empirically analyzed the evolution of links with the perspective of multi-graph topology and their recurrence probability over time.

Global analysis of vessel motion patterns has become possible using satellite-based Automatic Identification System (AIS). The concept of space-based AIS needs several satellites to provide complete coverage and high detection probability. However, in early development stages, often only one satellite is launched and due to its limitation of orbit and footprint, received AIS messages are discontinuous. In this paper, we have analysed real AIS data obtained by satellite to form a global maritime surveillance picture. Furthermore, we propose to take advantage of the tensor CANDECOMP/PARAFAC (CP) decomposition to analyse three mode characteristics of the data, which are location, vessel and time. For incomplete data, we exploit the link prediction technique based on tensor factorisation to recover vessel tracks in a specified area. A variant of temporal link prediction based on CP is presented. We illustrate the usefulness of exploiting the three-mode structure of AIS data by simulation, and demonstrate that the track recovery result has acceptable precision.

The study of covert networks is plagued by the fact that individuals conceal their attributes and associations. To address this problem, we develop a technology for eliciting this information from qualitative subject-matter experts to inform statistical social network analysis. We show how the information from the subjective probability distributions can be used as input to Bayesian hierarchical models for network data. In the spirit of “proof of concept,” the results of a test of the technology are reported. Our findings show that human subjects can use the elicitation tool effectively, supplying attribute and edge information to update a network indicative of a covert one.