Francesco Maria Donini

This work addresses the need for efficient and reusable vector embeddings (VEs) for large-scale RDF Knowledge Graphs, focusing on the widely used DrugBank dataset. The study aims to reduce the computational burden and environmental impact associated with repeatedly generating embeddings for downstream tasks such as link prediction, clustering, and recommendation. To this end, embeddings are generated from the DrugBank Knowledge Graph—comprising over 3.6 million triples, more than 1.5 million entities, and 95 relations—using 25 models implemented in the PyKEEN framework. The dataset is processed into training, validation, and test splits, and embeddings of fixed dimensionality are produced for both entities and relations. The resulting representations are released in multiple formats, including full JSON files, class-partitioned subsets, and an efficient Parquet-based structure, to support scalable querying. Experimental evaluation demonstrates substantial improvements in access time and memory usage when using structured formats, particularly Parquet. Additionally, the study quantifies the carbon footprint of embedding generation, showing that distributing precomputed embeddings can reduce energy consumption by up to 99.37% compared to on-demand recomputation. Overall, the work provides a comprehensive, reusable resource that facilitates research while promoting computational efficiency and environmental sustainability.

Personal Artificial Intelligence is currently hindered by the fragmentation of user data across isolated silos. While Retrieval-Augmented Generation offers a partial remedy, its reliance on unstructured vector similarity fails to capture the latent semantic topology and temporal dependencies essential for holistic sensemaking. We introduce EpisTwin, a neuro-symbolic framework that grounds generative reasoning in a verifiable, user-centric Personal Knowledge Graph. EpisTwin leverages Multimodal Language Models to lift heterogeneous, cross-application data into semantic triples. At inference, EpisTwin enables complex reasoning over the personal semantic graph via an agentic coordinator that combines Graph Retrieval-Augmented Generation with Online Deep Visual Refinement, dynamically re-grounding symbolic entities in their raw visual context. We also introduce PersonalQA-71-100, a synthetic benchmark designed to simulate a realistic user's digital footprint and evaluate EpisTwin performance. Our framework demonstrates robust results across a suite of state-of-the-art judge models, offering a promising direction for trustworthy Personal AI.

The Personal AI landscape is currently dominated by "Black Box" Retrieval-Augmented Generation. While standard vector databases offer statistical matching, they suffer from a fundamental lack of accountability: when an AI hallucinates or retrieves sensitive data, the user cannot inspect the cause nor correct the error. Worse, "deleting" a concept from a vector space is mathematically imprecise, leaving behind probabilistic "ghosts" that violate true privacy. We propose Ruva, the first "Glass Box" architecture designed for Human-in-the-Loop Memory Curation. Ruva grounds Personal AI in a Personal Knowledge Graph, enabling users to inspect what the AI knows and to perform precise redaction of specific facts. By shifting the paradigm from Vector Matching to Graph Reasoning, Ruva ensures the "Right to be Forgotten." Users are the editors of their own lives; Ruva hands them the pen. The project and the demo video are available at http://sisinf00.poliba.it/ruva/.

Background: Knowledge Graph Embeddings are increasingly used in biomedical informatics to support similarity assessment, clustering, and knowledge discovery. Despite strong performance in link prediction, recent studies show that numerical proximity in embedding spaces does not always reflect meaningful semantic similarity. LISE, a logic-based interactive similarity explainer, was introduced to expose shared semantic properties among clustered RDF resources and incorporate user feedback when evaluating cluster coherence. This work extends LISE by integrating Large Language Models for natural-language explanation and investigating whether user-derived relevance signals can actively influence embedding generation, improving the semantic adequacy of similarity-based clustering. Results: We replaced LISE’s template-based verbalization component with a Gemini 2.5 Flash module capable of generating human-readable, path-level explanations of logical Common Subsumers. This resolves previous LISE limitations related to granularity and anaphora resolution, enabling reliable sentence-level user evaluations. To assess whether user preferences can guide the embedding process, we simulated feedback on 1,280 DrugBank-derived triples and evaluated two custom pyRDF2Vec sampling strategies: Predicate Relevance Weight and Predicate-Object Relevance Weight. Relevance weights were learned via a random forest regressor trained on simulated user scores. Predicate-level weighting increased the presence of user-preferred predicates in the most cohesive clusters, with all predicates showing positive or neutral deviation under learned weights. By contrast, predicate-object weighting exhibited limited sensitivity, with most pairs showing unchanged frequency regardless of weight assignment. Average deviation metrics confirm that predicate-level adjustments redirect clustering more effectively toward semantically meaningful biomedical information. Conclusions: User-informed predicate weighting can successfully influence embedding-based clustering, improving alignment with semantically relevant biomedical properties. Predicate-object adjustments provide minimal benefit. Part of this research has been published in the proceedings of the 8th Workshop on Semantic Web Solutions for Large-scale Biomedical Data Analytics (SeWeBMeDA 2025).

Clustering methods are instrumental in the preliminary analysis of unstructured data, yet interpreting the resulting groups—–especially in the context of RDF (Resource Description Framework) data—–poses significant challenges. This paper introduces LISE (Logic-based Interactive Similarity Explainer), an integrated and model-agnostic framework designed to generate explainable, human-readable insights into clusters of RDF resources. LISE combines four core components: (i) a machine learning module leveraging vector embeddings and k-means clustering; (ii) a logic-based reasoning component that computes the common semantic features of clustered items via an optimized Least Common Subsumer (LCS); (iii) a natural language generation (NLG) module that verbalizes these features into structured and human-readable explanations; and (iv) an interactive user feedback loop that captures user perception of explanation relevance to iteratively enhance embedding quality and cluster interpretability. An extensive use case on the DrugBank dataset demonstrates LISE ’s ability to generate meaningful, context-aware cluster explanations and adapt to user preferences, advancing the state of explainable AI for semantic web technologies and knowledge graph analytics. The paper investigates also the integration in LISE of an LLM-based NLG approach, both in the DrugBank use case and through an extended experiment in a general-purpose dataset: YAGO3-10.

Clustering is a very common means of analysis of the data present in large datasets, with the aims of understanding and summarizing the data and discovering similarities, among other goals. However, despite the present success of the use of subsymbolic methods for data clustering, a description of the obtained clusters cannot rely on the intricacies of the subsymbolic processing. For clusters of data expressed in a Resource Description Framework (RDF), we extend and implement an optimized, previously proposed, logic-based methodology that computes an RDF structure—called a Common Subsumer—describing the commonalities among all resources. We tested our implementation with two open, and very different, RDF datasets: one devoted to public procurement, and the other devoted to drugs in pharmacology. For both datasets, we were able to provide reasonably concise and readable descriptions of clusters with up to 1800 resources. Our analysis shows the viability of our methodology and computation, and paves the way for general cluster explanations to be provided to lay users.

Clustering is a very common analysis of data present in large datasets, with the aims of understanding and summarizing data, and discovering similarities, among others. However, despite the present success of subsymbolic methods for data clustering, the description of the obtained clusters cannot rely on the intricacies of the subsymbolic processing. For clusters of data expressed in the Resource Description Framework (RDF) we extend and implement an optimized previously proposed logic-based methodology which computed an RDF structure — called a Common Subsumer — describing the commonalities among all resources. We tested our implementation with two open, and very different RDF datasets: one devoted to Public Procurement, and the other devoted to drugs in Pharmacology. For both datasets, we were able to provide reasonably concise and readable descriptions of clusters up to 1800 resources. Our analysis shows the viability of our methodology and computation, and paves the way for general cluster explanations to lay users.