Píetro Lió

Impact of novel aggregation methods for flexible, time-sensitive EHR prediction without variable selection or cleaning

2019 · arXiv (Cornell University)

Dynamic assessment of patient status (e.g. by an automated, continuously updated assessment of outcome) in the Intensive Care Unit (ICU) is of paramount importance for early alerting, decision support and resource allocation. Extraction and cleaning …

Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks

2021 · arXiv (Cornell University)

The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems. However, graphs alone cannot capture the multi-level interactions present in many complex systems and the expressive power of such …

Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off

2022 · arXiv (Cornell University)

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an intermediate level of human-like concepts. This enables human interventions …

Extending Logic Explained Networks to Text Classification

2022 · arXiv (Cornell University)

Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have only been applied to vision and tabular data, and they mostly favour the …

Graph Classification Gaussian Processes via Spectral Features

2023 · arXiv (Cornell University)

Graph classification aims to categorise graphs based on their structure and node attributes. In this work, we propose to tackle this task using tools from graph signal processing by deriving spectral features, which we then …

FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theory

2025 · arXiv (Cornell University)

Letting AI agents interact in multi-agent applications adds a layer of complexity to the interpretability and prediction of AI outcomes, with profound implications for their trustworthy adoption in research and society. Game theory offers powerful …

Deep Graph Infomax

2018 · Apollo (University of Cambridge)

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both …