Link prediction is a fundamental task in machine learning for graphs. Recently, Graph Neural Networks (GNNs) have gained in popularity and have become the default approach for solving this type of task. Despite the considerable interest for these methods, simple topological heuristics persistently emerge as competitive alternatives to GNNs. In this study, we show that this phenomenon is not an exception and that GNNs do not consistently establish a performance standard for link prediction on graphs. For this purpose, we identify several limitations in the current GNN evaluation methodology, such as the lack of variety in benchmark dataset characteristics and the limited use of diverse baselines outside of neural methods. In particular, we highlight that integrating feature information into topological heuristics remains a little-explored path. In line with this observation, we propose a simple non-neural model that leverages local structure, node feature, and graph feature information within a weighted combination. Experiments conducted on large variety of networks indicate that the proposed approach outperforms existing state-of-the-art GNNs and increases generalisation ability. Contrasting with GNNs, our approach does not rely on any learning process and therefore achieves superior results without sacrificing efficiency, showcasing a reduction of one to three orders of magnitude in computation time.

Graphs are ubiquitous in real-world data, ranging from the study of social interactions to bioinformatics or the modelling of physical systems. These real-world graphs are typically sparse, possibly large and frequently contain additional information in the form of attributes, making them a complex object to understand. Graph summarization techniques can help facilitate the discovery of hidden patterns in underlying data by providing an interesting subset of the interactions and available attributes, which we broadly call a pattern. However, determining what is considered interesting in this context is not straightforward. We address this challenge by designing an interestingness measure based on the information-theoretic measure of Unexpectedness, linking the concepts of relevance and Kolmogorov complexity. We design a pattern mining algorithm to provide a summary of the initial data in the form of a set of unexpected patterns, that is, patterns for which there is a drop between their expected complexity and the observed complexity. Experimental results on five real-world datasets with state-of-the-art methods demonstrate that our method exhibits a small number of diversified patterns, providing a human-readable summary of the initial attributed graph; we show that our summaries quantitatively outperforms attribute-only and interaction-only baselines as well as other pattern mining methods, reinforcing the need for methods dealing with attributed graphs. We visualize summaries extracted with our method, in order to qualitatively validate their readability.

Explainability (XAI) has matured in recent years to provide more human-centered explanations of AI-based decision systems. While static explanations remain predominant, interactive XAI has gathered momentum to support the human cognitive process of explaining. However, the evidence regarding the benefits of interactive explanations is unclear. In this paper, we map existing findings by conducting a detailed scoping review of 48 empirical studies in which interactive explanations are evaluated with human users. We also create a classification of interactive techniques specific to XAI and group the resulting categories according to their role in the cognitive process of explanation: "selective", "mutable" or "dialogic". We identify the effects of interactivity on several user-based metrics. We find that interactive explanations improve perceived usefulness and performance of the human+AI team but take longer. We highlight conflicting results regarding cognitive load and overconfidence. Lastly, we describe underexplored areas including measuring curiosity or learning or perturbing outcomes.