In this paper, we introduce PROPHET, an innovative approach to predictive process monitoring based on Heterogeneous Graph Neural Networks. PROPHET is designed to strike a balance between accurate predictions and interpretability, particularly focusing on the next-activity prediction task. For this purpose, we represent the event traces recorded for different business process executions as heterogeneous graphs within a multi-view learning scheme combined with a heterogeneous graph learning approach. Using heterogeneous Graph Attention Networks (GATs), we achieve good accuracy by incorporating different characteristics of several events into graphs with different node types and leveraging different types of graph links to express relationships between event characteristics, as well as relationships between events. In addition, the use of a GAT model enables the integration of a modified version of the GNN Explainer algorithm to add the explainable component to the predictive model. In particular, the GNN Explainer algorithm is modified to disclose explainable information related to characteristics, events and relationships between events that mainly influenced the prediction. Experiments with various benchmark event logs prove the accuracy of PROPHET compared to several current state-of-the-art methods and draw insights from explanations recovered through the GNN Explainer algorithm.
Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for multi-prompt, multi-way few-shot semantic segmentation. Our approach leverages diverse visual prompts—points, bounding boxes, and masks—to create a highly flexible and generalizable framework that significantly reduces annotation burden while maintaining high accuracy. Label Anything makes three key contributions: (i) we introduce a new task formulation that relaxes conventional few-shot segmentation constraints by supporting various types of prompts, multi-class classification, and enabling multiple prompts within a single image; (ii) we propose a novel architecture based on transformers and attention mechanisms; and (iii) we design a versatile training procedure allowing our model to operate seamlessly across different N-way K-shot and prompt-type configurations with a single trained model. Our extensive experimental evaluation on the widely used COCO-20i benchmark demonstrates that Label Anything achieves state-of-the-art performance among existing multi-way few-shot segmentation methods, while significantly outperforming leading single-class models when evaluated in multi-class settings. Code and trained models are available at https://github.com/pasqualedem/LabelAnything.
Balancing predictive performance with transparency remains a core challenge in eXplainable Artificial Intelligence, especially for tabular data. In this work, we present FuzzyGNN, a novel hybrid framework that combines fuzzy logic with Graph Neural Networks (GNNs) to deliver both high accuracy and interpretability. FuzzyGNN represents each data instance as a graph, where raw features and fuzzy sets are modeled as nodes, enabling contextual reasoning through message passing. Unlike traditional neuro-fuzzy systems—often limited by scalability and rule explosion—FuzzyGNN enforces model compactness through its graph-aware architecture and a pruning mechanism guided by graphbased explanations. Extensive experiments on seven benchmark datasets show that FuzzyGNN achieves competitive predictive performance while drastically reducing the number of fuzzy rules, linguistic terms, and active features used to produce output fuzzy rules. Additionally, it offers structural interpretability through rule extraction and post-hoc explainability via GNNExplainer. These capabilities make FuzzyGNN particularly well-suited for domains where transparency is as crucial as accuracy, such as healthcare, finance, and safety-critical systems. The code is available in the following link: https://github.com/cilabuniba/fuzzygnn