Pablo Piantanida

2024-09-25

NeurIPS.cc/2024/Conference (poster)

openreview.net

Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning

Georg Pichler

Marco Romanelli

Leonardo Rey Vega

2024-08-01

IEEE Transactions on Dependable and Secure Computing (publié)

GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews

Maxime DARRIN

Ines Arous

Jackie Cheung

Scientific peer review is essential for the quality of academic publications. However, the increasing number of paper submissions to confere… (voir plus)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.

2024-06-11

ArXiv (prépublication)

When is an Embedding Model More Promising than Another?

Maxime DARRIN

Philippe Formont

Ismail Ben Ayed

Jackie Cheung

Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to p… (voir plus)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.

2024-06-11

ArXiv (prépublication)

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.… (voir plus), 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.

2024-05-01

ICML.cc/2024/Conference (spotlight)

openreview.net

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… (voir plus)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.

2024-04-02

ArXiv (prépublication)

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… (voir plus) 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.

2024-03-19

Data Compression Conference (publié)

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… (voir plus)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

2024-02-29

ArXiv (prépublication)

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

Eduardo Dadalto Câmara Gomes

Marco Romanelli

Georg Pichler

2024-01-16

ICLR.cc/2024/Conference (poster)

openreview.net

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

2024-01-05

ArXiv (prépublication)

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… (voir plus)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.

2024-01-01

AISTATS (publié)

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… (voir plus)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.

2024-01-01

IEEE Transactions on Information Forensics and Security (publié)