In recent years, there has been a significant surge in machine learning techniques, particularly in the domain of deep learning, tailored for handling attributed graphs. Nevertheless, to work, these methods assume that the attributes values are fully known, which is not realistic in numerous real-world applications. This paper explores the potential of Optimal Transport (OT) to impute missing attributes on graphs. To proceed, we design a novel multi-view OT loss function that can encompass both node feature data and the underlying topological structure of the graph by utilizing multiple graph representations. We then utilize this novel loss to train efficiently a Graph Convolutional Neural Network (GCN) architecture capable of imputing all missing values over the graph at once. We evaluate the interest of our approach with experiments both on synthetic data and real-world graphs, including different missingness mechanisms and a wide range of missing data. These experiments demonstrate that our method is competitive with the state-of-the-art in all cases and of particular interest on weakly homophilic graphs.

Computing frequent itemsets and their frequencies from large Boolean matrices (e.g., to derive association rules) has been one of the hot topics in data mining. Levelwise algorithms (e.g., the a priori algorithm) have been proved effective for frequent itemset mining from sparse data. However, in many practical applications, the computation turns out to be intractable for the user-given frequency threshold and the lack of focus leads to huge collections of frequent itemsets. In the last three years, two promising issues have been investigated: the use of user defined constraints and closed set mining. To the best of our knowledge, combining these two frameworks has not been studied yet. The authors show that the benefit of these two approaches can be combined into levelwise algorithms. An experimental validation related to the discovery of association rules with negations is reported.

Frequent association rules (e.g., A∧B⇒C to say that when properties A and B are true in a record then, C tends to be also true) have become a popular way to summarize huge datasets. The last 5 years, there has been a lot of research on association rule mining and more precisely, the tractable discovery of interesting rules among the frequent ones. We consider now the problem of mining association rules that may involve negations e.g., A∧B⇒⌝C or ⌝A∧B⇒C. Mining such rules is difficult and remains an open problem. We identify several possibilities for a tractable approach in practical cases. Among others, we discuss the active use of constraints. We propose a generic algorithm and discuss the use of constraints to mine the generalized sets from which rules with negations can be derived.