arXiv subjects

Pietro Pinoli

Publications and source records attributed to Pietro Pinoli.

5 recordsLinked to original sources

arXiv2026

Novel Knowledge-Guided Generative Methods for Synthetic Transcriptomic Data

As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, biases, and ethical or legal constraints often limit access to high-quality data. Synthetic data generation can help overcome these limitations. Here, we present a comparative analysis of generative models for transcriptomic data, investigating strategies to incorporate prior biological knowledge via gene graphs. This ensures that synthetic data capture real-world gene patterns, maintaining their usefulness for downstream tasks. In particular, we introduce and benchmark three variants of the Generative Adversarial Network. Among the alternatives, MK-TGAN - an innovative multi-kernel, Graph Neural Network-based model - stands out for its performance in terms of both the realism and utility of the generated data. Unlike other methods, MK-TGAN leverages prior knowledge graphs by exploiting graph neural networks. Our results show that prior knowledge integration strategies improve performance, and that MK-TGAN consistently produces synthetic samples with superior realism and biological plausibility.

cs.LG↗

arXiv2026

QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption

Tabular machine learning systems are frequently trained on data affected by non-uniform corruption, including noisy measurements, missing entries, and feature-specific biases. In practice, these defects are often documented only through column-level reliability indicators rather than instance-wise quality annotations, limiting the applicability of many robustness and cleaning techniques. We present QuAIL, a quality-informed training mechanism that incorporates feature reliability priors directly into the learning process. QuAIL augments existing models with a learnable feature-modulation layer whose updates are selectively constrained by a quality-dependent proximal regularizer, thereby inducing controlled adaptation across features of varying trustworthiness. This stabilizes optimization under structured corruption without explicit data repair or sample-level reweighting. Empirical evaluation across 50 classification and regression datasets demonstrates that QuAIL consistently improves average performance over neural baselines under both random and value-dependent corruption, with especially robust behavior in low-data and systematically biased settings. These results suggest that incorporating feature reliability information directly into optimization dynamics is a practical and effective approach for resilient tabular learning.

cs.LG↗

arXiv2026

GeMM-GAN: A Multimodal Generative Model Conditioned on Histopathology Images and Clinical Descriptions for Gene Expression Profile Generation

Biomedical research increasingly relies on integrating diverse data modalities, including gene expression profiles, medical images, and clinical metadata. While medical images and clinical metadata are routinely collected in clinical practice, gene expression data presents unique challenges for widespread research use, mainly due to stringent privacy regulations and costly laboratory experiments. To address these limitations, we present GeMM-GAN, a novel Generative Adversarial Network conditioned on histopathology tissue slides and clinical metadata, designed to synthesize realistic gene expression profiles. GeMM-GAN combines a Transformer Encoder for image patches with a final Cross Attention mechanism between patches and text tokens, producing a conditioning vector to guide a generative model in generating biologically coherent gene expression profiles. We evaluate our approach on the TCGA dataset and demonstrate that our framework outperforms standard generative models and generates more realistic and functionally meaningful gene expression profiles, improving by more than 11\% the accuracy on downstream disease type prediction compared to current state-of-the-art generative models. Code will be available at: https://github.com/francescapia/GeMM-GAN

cs.AI↗

arXiv2025

I-ETL: an interoperability-aware health (meta) data pipeline to enable federated analyses

Clinicians are interested in better understanding complex diseases, such as cancer or rare diseases, so they need to produce and exchange data to mutualize sources and join forces. To do so and ensure privacy, a natural way consists in using a decentralized architecture and Federated Learning algorithms. This ensures that data stays in the organization in which it has been collected, but requires data to be collected in similar settings and similar models. In practice, this is often not the case because healthcare institutions work individually with different representations and raw data; they do not have means to normalize their data, and even less to do so across centers. For instance, clinicians have at hand phenotypic, clinical, imaging and genomic data (each individually collected) and want to better understand some diseases by analyzing them together. This example highlights the needs and challenges for a cooperative use of this wealth of information. We designed and implemented a framework, named I-ETL, for integrating highly heterogeneous healthcare datasets of hospitals in interoperable databases. Our proposal is twofold: (i) we devise two general and extensible conceptual models for modeling both data and metadata and (ii) we propose an Extract-Transform-Load (ETL) pipeline ensuring and assessing interoperability from the start. By conducting experiments on open-source datasets, we show that I-ETL succeeds in representing various health datasets in a unified way thanks to our two general conceptual models. Next, we demonstrate the importance of blending interoperability as a first-class citizen in integration pipelines, ensuring possible collaboration between different centers.

cs.DB↗

arXiv2024

A comparison of online search engine autocompletion in Google and Baidu

Warning: This paper contains content that may be offensive or upsetting. Online search engine auto-completions make it faster for users to search and access information. However, they also have the potential to reinforce and promote stereotypes and negative opinions about a variety of social groups. We study the characteristics of search auto-completions in two different linguistic and cultural contexts: Baidu and Google. We find differences between the two search engines in the way they suppress or modify original queries, and we highlight a concerning presence of negative suggestions across all social groups. Our study highlights the need for more refined, culturally sensitive moderation strategies in current language technologies.

cs.CY↗