Portrait of Pablo Piantanida

Pablo Piantanida

Associate Academic Member
Full Professor, Université Paris-Saclay
Director, International Laboratory on Learning Systems (ILLS), McGill University
Associate professor, École de technologie supérieure (ETS), Department of Systems Engineering
Research Topics
Computer Vision
Deep Learning
Information Theory
Machine Learning Theory
Molecular Modeling
Natural Language Processing

Biography

I am a professor at CentraleSupélec (Université Paris-Saclay) with the French National Centre for Scientific Research (CNRS), and Director of the International Laboratory on Learning Systems (ILLS) which gathers McGill University, École de technologie supérieure (ÉTS), Mila – Quebec AI Institute, France’s Centre Nationale de la Recherche Scientifique (CNRS), Université Paris-Saclay, and the École CentraleSupélec.

My research revolves around the application of advanced statistical and information-theoretic techniques to the field of machine learning. I am interested in developing rigorous techniques based on information measures and concepts for building safe and trustworthy AI systems and establishing confidence in their behavior and robustness, thereby securing their use in society. My primary areas of expertise include information theory, information geometry, learning theory, privacy, fairness, with applications to computer vision and natural language processing.

I obtained my undergraduate education at the University of Buenos Aires and pursued graduate studies in applied mathematics at Paris-Saclay University in France. Throughout my career, I have also held visiting positions at INRIA, Université de Montréal and Ecole de Technologie Supérieure (ÉTS), among others.

My earlier research encompassed the fields of information theory beyond distributed compression, statistical decision, universal source coding, cooperation, feedback, index coding, key generation, security, and privacy, among others.

I teach courses on machine learning, information theory and deep learning, covering topics such as statistical learning theory, information measures, statistical principles of neural networks.

Current Students

Independent visiting researcher - Université Paris-Saclay
PhD - McGill University
Principal supervisor :

Publications

Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning
Georg Pichler
Marco Romanelli
Leonardo Rey Vega
GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews
Maxime Darrin
Ines Arous
Scientific peer review is essential for the quality of academic publications. However, the increasing number of paper submissions to confere… (see more)nces has strained the reviewing process. This surge poses a burden on area chairs who have to carefully read an ever-growing volume of reviews and discern each reviewer's main arguments as part of their decision process. In this paper, we introduce \sys, a summarization method designed to offer a concise yet comprehensive overview of scholarly reviews. Unlike traditional consensus-based methods, \sys extracts both common and unique opinions from the reviews. We introduce novel uniqueness scores based on the Rational Speech Act framework to identify relevant sentences in the reviews. Our method aims to provide a pragmatic glimpse into all reviews, offering a balanced perspective on their opinions. Our experimental results with both automatic metrics and human evaluation show that \sys generates more discriminative summaries than baseline methods in terms of human evaluation while achieving comparable performance with these methods in terms of automatic metrics.
When is an Embedding Model More Promising than Another?
Maxime Darrin
Philippe Formont
Ismail Ben Ayed
Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to p… (see more)erform various downstream tasks. The evaluation of embedding models typically depends on domain-specific empirical approaches utilizing downstream tasks, primarily because of the lack of a standardized framework for comparison. However, acquiring adequately large and representative datasets for conducting these assessments is not always viable and can prove to be prohibitively expensive and time-consuming. In this paper, we present a unified approach to evaluate embedders. First, we establish theoretical foundations for comparing embedding models, drawing upon the concepts of sufficiency and informativeness. We then leverage these concepts to devise a tractable comparison criterion (information sufficiency), leading to a task-agnostic and self-supervised ranking procedure. We demonstrate experimentally that our approach aligns closely with the capability of embedding models to facilitate various downstream tasks in both natural language processing and molecular biology. This effectively offers practitioners a valuable tool for prioritizing model trials.
Beyond the Norms: Detecting Prediction Errors in Regression Models
Andres Altieri
Marco Romanelli
Georg Pichler
Florence Alberge
This paper tackles the challenge of detecting unreliable behavior in regression algorithms, which may arise from intrinsic variability (e.g.… (see more), aleatoric uncertainty) or modeling errors (e.g., model uncertainty). First, we formally introduce the notion of unreliability in regression, i.e., when the output of the regressor exceeds a specified discrepancy (or error). Then, using powerful tools for probabilistic modeling, we estimate the discrepancy density, and we measure its statistical diversity using our proposed metric for statistical dissimilarity. In turn, this allows us to derive a data-driven score that expresses the uncertainty of the regression outcome. We show empirical improvements in error detection for multiple regression tasks, consistently outperforming popular baseline approaches, and contributing to the broader field of uncertainty quantification and safe machine learning systems.
Is Meta-training Really Necessary for Molecular Few-Shot Learning ?
Philippe Formont
Hugo Jeannin
Ismail Ben Ayed
Few-shot learning has recently attracted significant interest in drug discovery, with a recent, fast-growing literature mostly involving con… (see more)voluted meta-learning strategies. We revisit the more straightforward fine-tuning approach for molecular data, and propose a regularized quadratic-probe loss based on the the Mahalanobis distance. We design a dedicated block-coordinate descent optimizer, which avoid the degenerate solutions of our loss. Interestingly, our simple fine-tuning approach achieves highly competitive performances in comparison to state-of-the-art methods, while being applicable to black-box settings and removing the need for specific episodic pre-training strategies. Furthermore, we introduce a new benchmark to assess the robustness of the competing methods to domain shifts. In this setting, our fine-tuning baseline obtains consistently better results than meta-learning methods.
Two-stage Multiple-Model Compression Approach for Sampled Electrical Signals
Corentin Presvôts
Michel Kieffer
Thibault Prevost
Patrick Panciatici
Zuxing Li
This paper presents a two-stage Multiple-Model Compression (MMC) approach for sampled electrical waveforms. To limit latency, the processing… (see more) is window-based, with a window length commensurate to the electrical period. For each window, the first stage compares several parametric models to get a coarse representation of the samples. The second stage then compares different residual compression techniques to minimize the norm of the reconstruction error. The allocation of the rate budget among the two stages is optimized. The proposed MMC approach provides better signal-to-noise ratios than state-of-the-art solutions on periodic and transient waveforms.
COSMIC: Mutual Information for Task-Agnostic Summarization Evaluation
Maxime Darrin
Philippe Formont
Jackie Chi Kit Cheung
Assessing the quality of summarizers poses significant challenges. In response, we propose a novel task-oriented evaluation approach that as… (see more)sesses summarizers based on their capacity to produce summaries that are useful for downstream tasks, while preserving task outcomes. We theoretically establish a direct relationship between the resulting error probability of these tasks and the mutual information between source texts and generated summaries. We introduce
A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
Eduardo Dadalto Câmara Gomes
Marco Romanelli
Georg Pichler
On the Stability of a non-hyperbolic nonlinear map with non-bounded set of non-isolated fixed points with applications to Machine Learning
Roberta Hansen
Matias Vera
Lautaro Estienne
LUCIANA FERRER
Optimal Zero-Shot Detector for Multi-Armed Attacks
Federica Granese
Marco Romanelli
This paper explores a scenario in which a malicious actor employs a multi-armed attack strategy to manipulate data samples, offering them va… (see more)rious avenues to introduce noise into the dataset. Our central objective is to protect the data by detecting any alterations to the input. We approach this defensive strategy with utmost caution, operating in an environment where the defender possesses significantly less information compared to the attacker. Specifically, the defender is unable to utilize any data samples for training a defense model or verifying the integrity of the channel. Instead, the defender relies exclusively on a set of pre-existing detectors readily available"off the shelf". To tackle this challenge, we derive an innovative information-theoretic defense approach that optimally aggregates the decisions made by these detectors, eliminating the need for any training data. We further explore a practical use-case scenario for empirical evaluation, where the attacker possesses a pre-trained classifier and launches well-known adversarial attacks against it. Our experiments highlight the effectiveness of our proposed solution, even in scenarios that deviate from the optimal setup.
Preserving Privacy in GANs Against Membership Inference Attack
Mohammadhadi Shateri
Francisco Messina
Fabrice Labeau
Generative Adversarial Networks (GANs) have been widely used for generating synthetic data for cases where there is a limited size real-worl… (see more)d data set or when data holders are unwilling to share their data samples. Recent works showed that GANs, due to overfitting and memorization, might leak information regarding their training data samples. This makes GANs vulnerable to Membership Inference Attacks (MIAs). Several defense strategies have been proposed in the literature to mitigate this privacy issue. Unfortunately, defense strategies based on differential privacy are proven to reduce extensively the quality of the synthetic data points. On the other hand, more recent frameworks such as PrivGAN and PAR-GAN are not suitable for small-size training data sets. In the present work, the overfitting in GANs is studied in terms of the discriminator, and a more general measure of overfitting based on the Bhattacharyya coefficient is defined. Then, inspired by Fano’s inequality, our first defense mechanism against MIAs is proposed. This framework, which requires only a simple modification in the loss function of GANs, is referred to as the maximum entropy GAN or MEGAN and significantly improves the robustness of GANs to MIAs. As a second defense strategy, a more heuristic model based on minimizing the information leaked from the generated samples about the training data points is presented. This approach is referred to as mutual information minimization GAN (MIMGAN) and uses a variational representation of the mutual information to minimize the information that a synthetic sample might leak about the whole training data set. Applying the proposed frameworks to some commonly used data sets against state-of-the-art MIAs reveals that the proposed methods can reduce the accuracy of the adversaries to the level of random guessing accuracy with a small reduction in the quality of the synthetic data samples.
Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data
Maxime Darrin
Pierre Colombo
Implementing effective control mechanisms to ensure the proper functioning and security of deployed NLP models, from translation to chatbots… (see more), is essential. A key ingredient to ensure safe system behaviour is Out-Of-Distribution (OOD) detection, which aims to detect whether an input sample is statistically far from the training distribution. Although OOD detection is a widely covered topic in classification tasks, most methods rely on hidden features output by the encoder. In this work, we focus on leveraging soft-probabilities in a black-box framework, i.e. we can access the soft-predictions but not the internal states of the model. Our contributions include: (i) RAINPROOF a Relative informAItioN Projection OOD detection framework; and (ii) a more operational evaluation setting for OOD detection. Surprisingly, we find that OOD detection is not necessarily aligned with task-specific measures. The OOD detector may filter out samples well processed by the model and keep samples that are not, leading to weaker performance. Our results show that RAINPROOF provides OOD detection methods more aligned with task-specific performance metrics than traditional OOD detectors.