Publications

2024

• Exploiting temporal information to detect conversational groups in videos and predict the next speaker
  
  • Tosato Lucrezia
  • Fortier Victor
  • Bloch Isabelle
  • Pelachaud Catherine
  Pattern Recognition Letters, Elsevier, 2024, 177, pp.164-168. Studies in human-human interaction have introduced the concept of F-formation to describe the spatial arrangement of participants during social interactions. This paper has two objectives. It aims at detecting F-formations in video sequences and at predicting the next speaker in a group conversation. The proposed approach exploits time information and multimodal signals of humans in video sequences. In particular, we rely on measuring the engagement level of people as a feature of group belonging. Our approach makes use of a recursive neural network, the Long Short Term Memory (LSTM), to predict who will take the speaker's turn in a conversation group. Experiments on the MatchNMingle dataset led to 85% true positives in group detection and 98% accuracy in predicting the next speaker. (10.1016/j.patrec.2023.10.002)
  DOI : 10.1016/j.patrec.2023.10.002
• Source-Guided Similarity Preservation for Online Person Re-Identification
  
  • Rami Hamza
  • Giraldo Jhony H.
  • Winckler Nicolas
  • Lathuilière Stéphane
  , 2024, pp.1700-1709. Online Unsupervised Domain Adaptation (OUDA) for person Re-Identification (Re-ID) is the task of continuously adapting a model trained on a well-annotated source-domain dataset to a target domain observed as a data stream. In OUDA, person Re-ID models face two main challenges: catastrophic forgetting and domain shift. In this work, we propose a new Source-guided Similarity Preservation (S2P) framework to alleviate these two problems. Our framework is based on the extraction of a support set composed of source images that maximizes the similarity with the target data. This support set is used to identify feature similarities that must be preserved during the learning process. S2P can incorporate multiple existing UDA methods to mitigate catastrophic forgetting. Our experiments show that S2P outperforms previous state-of-the-art methods on multiple real-to-real and synthetic-to-real challenging OUDA benchmarks. (10.1109/WACV57701.2024.00173)
  DOI : 10.1109/WACV57701.2024.00173
• Mini but Mighty: Finetuning ViTs with Mini Adapters
  
  • Marouf Imad Eddine
  • Tartaglione Enzo
  • Lathuilière Stéphane
  , 2024, pp.1721-1730. Vision Transformers (ViTs) have become one of the dominant architectures in computer vision, and pre-trained ViT models are commonly adapted to new tasks via fine-tuning. Recent works proposed several parameter-efficient transfer learning methods, such as adapters, to avoid the prohibitive training and storage cost of finetuning. In this work, we observe that adapters perform poorly when the dimension of adapters is small, and we propose MiMi, a training framework that addresses this issue. We start with large adapters which can reach high performance, and iteratively reduce their size. To enable automatic estimation of the hidden dimension of every adapter, we also introduce a new scoring function, specifically designed for adapters, that compares the neuron importance across layers. Our method outperforms existing methods in finding the best trade-off between accuracy and trained parameters across the three dataset benchmarks DomainNet, VTAB, and Multi-task, for a total of 29 datasets. (10.1109/WACV57701.2024.00175)
  DOI : 10.1109/WACV57701.2024.00175
• Efficient thermalization and universal quantum computing with quantum Gibbs samplers
  
  • Rouzé Cambyse
  • Stilck França Daniel
  • Alhambra Álvaro
  Nature Physics, Nature Publishing Group [2005-....], 2024. The preparation of thermal states of matter is a crucial task in quantum simulation. In this work, we prove that a recently introduced, efficiently implementable dissipative evolution thermalizes to the Gibbs state in time scaling polynomially with system size at high enough temperatures for any Hamiltonian that satisfies a Lieb-Robinson bound, such as local Hamiltonians on a lattice. Furthermore, we show the efficient adiabatic preparation of the associated purifications or "thermofield double" states. To the best of our knowledge, these are the first results rigorously establishing the efficient preparation of high-temperature Gibbs states and their purifications. In the low-temperature regime, we show that implementing this family of dissipative evolutions for inverse temperatures polynomial in the system's size is computationally equivalent to standard quantum computations. On a technical level, for high temperatures, our proof makes use of the mapping of the generator of the evolution into a Hamiltonian, and then connecting its convergence to that of the infinite temperature limit. For low temperature, we instead perform a perturbation at zero temperature and resort to circuit-to-Hamiltonian mappings akin to the proof of universality of quantum adiabatic computing. Taken together, our results show that a family of quasi-local dissipative evolutions efficiently prepares a large class of quantum many-body states of interest, and has the potential to mirror the success of classical Monte Carlo methods for quantum many-body systems. (10.1038/s41567-026-03246-y)
  DOI : 10.1038/s41567-026-03246-y
• Coarse Ricci curvature of quantum channels
  
  • Gao Li
  • Rouzé Cambyse
  Journal of Functional Analysis, Elsevier, 2024, 286 (8), pp.110336. Following Ollivier's work [60], we introduce the coarse Ricci curvature of a quantum channel as the contraction coefficient of non-commutative metrics on the state space. These metrics are defined as a non-commutative transportation cost in the spirit of [41], [40], which gives a unified approach to different quantum Wasserstein distances in the literature. We prove that the coarse Ricci curvature lower bound and its dual gradient estimate, under suitable assumptions, imply the Poincaré inequality (spectral gap) as well as transportation cost inequalities. Using intertwining relations, we obtain positive coarse Ricci curvature bounds of Gibbs samplers, Bosonic beam-splitters as well as Pauli channels on n-qubits. (10.1016/j.jfa.2024.110336)
  DOI : 10.1016/j.jfa.2024.110336
• On Iiro Honkala’s contributions to identifying codes
  
  • Hudry Olivier
  • Junnila Ville
  • Lobstein Antoine
  Fundamenta Informaticae, Polskie Towarzystwo Matematyczne, 2024, 191 (3-4), pp.165-196. A set C of vertices in a graph G = (V, E) is an identifying code if it is dominating and any two vertices of V are dominated by distinct sets of codewords. This paper presents a survey of Iiro Honkala's contributions to the study of identifying codes with respect to several aspects: complexity of computing an identifying code, combinatorics in binary Hamming spaces, infinite grids, relationships between identifying codes and usual parameters in graphs, structural properties of graphs admitting identifying codes, and number of optimal identifying codes. (10.3233/FI-242178)
  DOI : 10.3233/FI-242178
• Malliavin structure for conditionally independent random variables
  
  • Decreusefond Laurent
  • Vuong Christophe
  , 2024. We consider a countable family of random variables which are conditionally independent given a latent random variable $Z$. Given $Z$, the random variables are independent. Hence the Malliavin calculus for independent random variables applies for each value of $Z$. We show that these constructions fit together. We obtain the chaos decomposition, the domains of the Malliavin operators, the Mehler formula and the carré du champ operator, with conditional expectations given $Z$ in place of ordinary expectations. For normal approximation, conditioning on $Z$ and the infinite de Jong theorem of D\"obler give mixed normal approximations of degenerate U-statistics, in Wasserstein and Kolmogorov distances. Working under the unconditional probability, we obtain a de Jong type bound for U-statistics whose kernels are products. In both cases, the fluctuations of the conditional variance appear as an additional term, which cannot be removed. As an application, we consider subhypergraph counts in a random $3$-uniform hypergraph built on a latent random graph. For the count centred at its conditional mean, we obtain an explicit rate in Wasserstein distance. It reduces to the known rate for the Erd\H{o}s--R\'enyi hypergraph when the latent graph is complete. The count centred at its mean is a pattern count in a non-uniform hypergraph with independent edges, which gives a necessary and sufficient condition for its asymptotic normality.
• New dominating, locating-dominating or identifying codes in the q-ary Lee Hypercube
  
  • Hudry Olivier
  WSEAS Transactions on Mathematics, World Scientific and Engineering Academy and Society (WSEAS), 2024. Let $q$ be an integer and $F_q$ the set $\{0, 1, \ldots , q-1\}$ and let $F_q^n$ be the $q$-ary hypercube of dimension $n$, i.e. the set of vectors whose the $n$ components belong to $F_q$. For $x=(x_1, \ldots ,x_n) \in F_q^n$ and ${y=(y_1, \ldots , y_n) \in F_q^n}$, the {\it Lee distance} between $x$ and $y$ is equal to ${\sum _{i=1}^{n}\min(|x_i-y_i|,q-|x_i-y_i|)}$. Let $C\subseteq F_q^n$; $C$ is called a {\it code}. Given an integer radius $r\geqslant 1$, we consider three types of codes with respect to the Lee distance: an $r$-{\it dominating code} $C$ (also called an $r$-{\it covering code}) is such that any element $x\in F_q^n$ is within distance $r$ from at least one codeword $c\in C$ (then $c$ $r$-{\it dominates}~$x$); an $r$-{\it locating-dominating code} $C$ is (i)~$r$-dominating and (ii)~such that any two elements $x$ and $y$ belonging to $F_q^n \setminus C$ are $r$-dominated by distinct sets of codewords; an $r$-{\it identifying code} $C$ is (i)~$r$-dominating and (ii)~such that any two elements $x$ and $y$ belonging to $F_q^n$ are $r$-dominated by distinct sets of codewords. We look for minimum such codes. We improve the cardinalities of $r$-dominating codes, $r$-locating-dominating codes or $r$-identifying codes of $F_q^n$ for some values of the alphabet size $q\in \{4,5,6\}$, of the dimension $n$ up to~$7$, and the radius $r$ up to~$5$.
• Analyse combinatoire
  
  • Hudry Olivier
  • Charon Irène
  , 2024.
• Machine Learning-Driven Low-Complexity Optical Power Optimization for Point-to-Point Links
  
  • Andrenacci Isaia
  • Lonardi Matteo
  • Ramantanis Petros
  • Awwad Élie
  • Irurozki Ekhiñe
  • Clémençon Stephan
  • Serena Paolo
  • Lasagni Chiara
  • Bigo Sébastien
  • Layec Patricia
  , 2024, pp.W2A.19. We propose a strategy to dynamically adjust transmitted power solely based on the analysis of performance fluctuations due to polarization-dependent loss. We show that our method converges faster to optimum compared to a standard approach. (10.1364/OFC.2024.W2A.19)
  DOI : 10.1364/OFC.2024.W2A.19
• Diffusive limits of Lipschitz functionals of Poisson measures
  
  • Besançon Eustache
  • Coutin Laure
  • Decreusefond Laurent
  • Moyal Pascal
  The Annals of Applied Probability, Institute of Mathematical Statistics (IMS), 2024, 34 (1A), pp.555-584. Continuous Time Markov Chains, Hawkes processes and many other interesting processes can be described as solution of stochastic differential equations driven by Poisson measures. Previous works, using the Stein's method, give the convergence rate of a sequence of renormalized Poisson measures towards the Brownian motion in several distances, constructed on the model of the Kantorovitch-Rubinstein (or Wasserstein-1) distance. We show that many operations (like time change, convolution) on continuous functions are Lipschitz continuous to extend these quantified convergences to diffuse limits of Markov processes and long-time behavior of Hawkes processes. (10.1214/23-AAP1972)
  DOI : 10.1214/23-AAP1972
• Learning quantum many-body systems from a few copies
  
  • Rouzé Cambyse
  • Stilck França Daniel
  Quantum, Verein zur Förderung des Open Access Publizierens in den Quantenwissenschaften, 2024, 8, pp.1319. Estimating physical properties of quantum states from measurements is one of the most fundamental tasks in quantum science. In this work, we identify conditions on states under which it is possible to infer the expectation values of all quasi-local observables of a state from a number of copies that scales polylogarithmically with the system's size and polynomially on the locality of the target observables. We show that this constitutes a provable exponential improvement in the number of copies over state-of-the-art tomography protocols. We achieve our results by combining the maximum entropy method with tools from the emerging fields of classical shadows and quantum optimal transport. The latter allows us to fine-tune the error made in estimating the expectation value of an observable in terms of how local it is and how well we approximate the expectation value of a fixed set of few-body observables. We conjecture that our condition holds for all states exhibiting some form of decay of correlations and establish it for several subsets thereof. These include widely studied classes of states such as one-dimensional thermal and high-temperature Gibbs states of local commuting Hamiltonians on arbitrary hypergraphs or outputs of shallow circuits. Moreover, we show improvements of the maximum entropy method beyond the sample complexity that are of independent interest. These include identifying regimes in which it is possible to perform the postprocessing efficiently as well as novel bounds on the condition number of covariance matrices of many-body states. (10.22331/q-2024-04-30-1319)
  DOI : 10.22331/q-2024-04-30-1319
• HI-AUDIO ONLINE PLATFORM: OPPORTUNITIES AND CHALLENGES OF COLLECTING VARIED MUSIC DATA ON THE WEB
  
  • Gil Panal José Manuel
  • David Aurélien
  • Richard Gael
  , 2024. <div><p>We present in this paper the extended online HI-AUDIO platform which relies on a distributed and iterative music recording paradigm to asynchronously record musicians localised at different remote individual sites. The major goal of this platform is to become a key enabling tool for building a large, varied, multi-genre, multi-track, multiinstrument music dataset, to be ultimately publicly distributed for MIR research purposes. We describe in this paper the main characteristics of the web platform and discuss some of the major challenges for collecting music data on the web. The platform will be demonstrated on site with local and distant access and illustrate its merits for recording collaborative compositions.</p></div>
• New penalized criteria for smooth non-negative tensor factorization with missing entries
  
  • Durand Amaury
  • Roueff François
  • Jicquel Jean-Marc
  • Paul Nicolas
  IEEE Transactions on Signal Processing, Institute of Electrical and Electronics Engineers, 2024, 72, pp.2233-2243. Tensor factorization models are widely used in many applied fields such as chemometrics, psychometrics, computer vision or communication networks. Real life data collection is often subject to errors, resulting in missing data. Here we focus in understanding how this issue should be dealt with for nonnegative tensor factorization. We investigate several criteria used for non-negative tensor factorization in the case where some entries are missing. In particular we show how smoothness penalties can compensate the presence of missing values in order to ensure the existence of an optimum. This lead us to propose new criteria with efficient numerical optimization algorithms. Numerical experiments are conducted to support our claims. (10.1109/TSP.2024.3392357)
  DOI : 10.1109/TSP.2024.3392357
• Stochastic Subgradient Descent Escapes Active Strict Saddles on Weakly Convex Functions
  
  • Bianchi Pascal
  • Hachem Walid
  • Schechtman Sholom
  Mathematics of Operations Research, INFORMS, 2024, 49 (3), pp.1761-1790. In non-smooth stochastic optimization, we establish the non-convergence of the stochastic subgradient descent (SGD) to the critical points recently called active strict saddles by Davis and Drusvyatskiy. Such points lie on a manifold $M$ where the function $f$ has a direction of second-order negative curvature. Off this manifold, the norm of the Clarke subdifferential of $f$ is lower-bounded. We require two conditions on $f$. The first assumption is a Verdier stratification condition, which is a refinement of the popular Whitney stratification. It allows us to establish a reinforced version of the projection formula of Bolte et al. for Whitney stratifiable functions, and which is of independent interest. The second assumption, termed the angle condition, allows to control the distance of the iterates to $M$. When $f$ is weakly convex, our assumptions are generic. Consequently, generically in the class of definable weakly convex functions, the SGD converges to a local minimizer. (10.1287/moor.2021.0194)
  DOI : 10.1287/moor.2021.0194
• Input Visualization: Collecting and Modifying Data with Visual Representations
  
  • Bressa Nathalie
  • Louis Jordan
  • Willett Wesley
  • Huron Samuel
  , 2024. We examine input visualizations, visual representations that are designed to collect (and represent) new data rather than encode preexisting datasets. Information visualization is commonly used to reveal insights and stories within existing data. As a result, most contemporary visualization approaches assume existing datasets as the starting point for design, through which that data is mapped to visual encodings. Meanwhile, the implications of visualizations as inputs and as data sources have received little attention—despite the existence of visual and physical examples stretching back centuries. In this paper, we present a design space of 50 input visualizations analyzing their visual representation, data, artifact, context, and input. Based on this, we identify input modalities, purposes of input visualizations, and a set of design considerations. Finally, we discuss the relationship between input visualization and traditional visualization design and suggest opportunities for future research to better understand these visual representations and their potential. (10.1145/3613904.3642808)
  DOI : 10.1145/3613904.3642808
• The European approach to regulating AI through technical standards
  
  • Gornet Mélanie
  • Maxwell Winston
  Internet Policy Review, Alexander von Humboldt Institute for Internet and Society, 2024, 13 (3), pp.1-27. In December 2023, the European institutions reached a political agreement on the AI Act, a new regulation on artificial intelligence. The AI Act will require providers of high-risk AI systems to test their products against harmonised standards (hENs) before affixing a European Conformity (CE) mark to allow AI products to circulate freely on the European market. The CE mark and hENs are long-established European regulatory tools to deal with product safety and already apply to a wide range of products. To date, however, they have never been used to attest to compliance with fundamental rights, something the AI Act aims to achieve. In this article, we examine the role of hENs and CE marking in the AI Act, and how these product safety regulatory techniques have been expanded to cover protection of fundamental rights. We analyse the 5 March 2024 CJEU decision and the respective opinion of the Advocate General in the Public.Resource.Org case which raises questions on democratic processes in standardisation organisations. We show that unlike compliance with product safety norms, compliance with fundamental rights cannot be certified through use of technical standards because violations of rights are too context-specific and require a judicial determination. However, technical standards have an important role to play in encouraging best practices in AI governance. (10.14763/2024.3.1784)
  DOI : 10.14763/2024.3.1784
• Uncertainty quantification for fast reconstruction methods using augmented equivariant bootstrap: Application to radio interferometry
  
  • Cherif Mostafa
  • Liaudat Tobias I
  • Kern Jonathan
  • Kervazo Christophe
  • Bobin Jérôme
  , 2024. The advent of next-generation radio interferometers like the Square Kilometer Array promises to revolutionise our radio astronomy observational capabilities. The unprecedented volume of data these devices generate requires fast and accurate image reconstruction algorithms to solve the ill-posed radio interferometric imaging problem. Most state-of-the-art reconstruction methods lack trustworthy and scalable uncertainty quantification, which is critical for the rigorous scientific interpretation of radio observations. We propose an unsupervised technique based on a conformalized version of a radio-augmented equivariant bootstrapping method, which allows us to quantify uncertainties for fast reconstruction methods. Noticeably, we rely on reconstructions from ultra-fast unrolled algorithms. The proposed method brings more reliable uncertainty estimations to our problem than existing alternatives. (10.48550/arXiv.2410.23178)
  DOI : 10.48550/arXiv.2410.23178
• RF-EMF Exposure Assessment of Fetus During the First Trimester of Pregnancy
  
  • Sandeep Srikumar
  • Vard Alireza
  • Guxens Mònica
  • Bloch Isabelle
  • Wiart Joe
  IEEE Access, IEEE, 2024, 12, pp.75311-75322. This article describes the computational analysis of Radio Frequency - Electromagnetic Field (RF-EMF) exposure of Uterus-Fetus Units (UFUs) embedded inside the body of a 26 year old human female. Realistic UFU models are obtained from ultrasound images acquired for different fetuses and at specific development stages (7 weeks, 9 weeks and 11 weeks old), for which a deep-learning based segmentation method is developed. Each UFU model is then inserted into a computational electromagnetic model of a 26 year old female. The Specific Absorption Rate (SAR) of the fetus at commonly used wireless communication frequencies is estimated using a commercially available numerical electromagnetic solver. The Inverted F antenna (IFA), which is a commonly used mobile phone antenna was used as the excitation source. Fetus SAR values are reported for different combinations of excitation frequencies, phone positions and UFU ages. It was found that the fetus SAR for all the cases is well below the maximum allowable exposure limit of 80 mW/kg, as prescribed by ICNIRP. Furthermore, we replaced the embryo with uterus tissues and calculated the SAR in the uterus tissues (i.e. uterus tissues with same volume and shape, and at the same location as that of UFU). The uterus SAR values were found to be only marginally different from that of fetus SAR. (10.1109/ACCESS.2024.3404369)
  DOI : 10.1109/ACCESS.2024.3404369
• Towards image compression with perfect realism at ultra-low bitrates
  
  • Careil Marlène
  • Muckley Matthew J.
  • Verbeek Jakob
  • Lathuilière Stéphane
  , 2024. Image codecs are typically optimized to trade-off bitrate \vs distortion metrics. At low bitrates, this leads to compression artefacts which are easily perceptible, even when training with perceptual or adversarial losses. To improve image quality and remove dependency on the bitrate, we propose to decode with iterative diffusion models. We condition the decoding process on a vector-quantized image representation, as well as a global image description to provide additional context. We dub our model PerCo for 'perceptual compression', and compare it to state-of-the-art codecs at rates from 0.1 down to 0.003 bits per pixel. The latter rate is more than an order of magnitude smaller than those considered in most prior work, compressing a 512x768 Kodak image with less than 153 bytes. Despite this ultra-low bitrate, our approach maintains the ability to reconstruct realistic images. We find that our model leads to reconstructions with state-of-the-art visual quality as measured by FID and KID. As predicted by rate-distortion-perception theory, visual quality is less dependent on the bitrate than previous methods.
• Towards On-Device Learning on the Edge: Ways to Select Neurons to Update Under a Budget Constraint
  
  • Quélennec Aël
  • Tartaglione Enzo
  • Mozharovskyi Pavlo
  • Nguyen Van-Tam
  , 2024, pp.685-694. n the realm of efficient on-device learning under extreme memory and computation constraints, a significant gap in successful approaches persists. Although considerable effort has been devoted to efficient inference, the main obstacle to efficient learning is the prohibitive cost of backpropagation. The resources required to compute gradients and update network parameters often exceed the limits of tightly constrained memory budgets. This paper challenges conventional wisdom and proposes a series of experiments that reveal the existence of superior sub-networks. Furthermore, we hint at the potential for substantial gains through a dynamic neuron selection strategy when fine-tuning a target task. Our efforts extend to the adaptation of a recent dynamic neuron selection strategy pioneered by Bragagnolo et al. (NEq), revealing its effectiveness in the most stringent scenarios. Our experiments demonstrate, in the average case, the superiority of a NEq-inspired approach over a random selection. This observation prompts a compelling avenue for further exploration in the area, highlighting the opportunity to design a new class of algorithms designed to facilitate parameter update selection. Our findings usher in a new era of possibilities in the field of on-device learning under extreme constraints and encourage the pursuit of innovative strategies for efficient, resource-friendly model fine-tuning. (10.1109/WACVW60836.2024.00080)
  DOI : 10.1109/WACVW60836.2024.00080
• A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regions
  
  • Staerman Guillaume
  • Mozharovskyi Pavlo
  • Colombo Pierre
  • Clémençon Stéphan
  • d'Alché-Buc Florence
  Transactions on Machine Learning Research, [Amherst Massachusetts]: OpenReview.net, 2022, 2024. The design of a metric between probability distributions is a longstanding problem motivated by numerous applications in Machine Learning. Focusing on continuous probability distributions on the Euclidean space $\mathbb{R}^d$, we introduce a novel pseudo-metric between probability distributions by leveraging the extension of univariate quantiles to multivariate spaces. Data depth is a nonparametric statistical tool that measures the centrality of any element $x\in\mathbb{R}^d$ with respect to (w.r.t.) a probability distribution or a data set. It is a natural median-oriented extension of the cumulative distribution function (cdf) to the multivariate case. Thus, its upper-level sets -- the depth-trimmed regions -- give rise to a definition of multivariate quantiles. The new pseudo-metric relies on the average of the Hausdorff distance between the depth-based quantile regions w.r.t. each distribution. Its good behavior w.r.t. major transformation groups, as well as its ability to factor out translations, are depicted. Robustness, an appealing feature of this pseudo-metric, is studied through the finite sample breakdown point. Moreover, we propose an efficient approximation method with linear time complexity w.r.t. the size of the data set and its dimension. The quality of this approximation as well as the performance of the proposed approach are illustrated in numerical experiments.
• The Impact of the COVID-19 Pandemic on Women's Contribution to Public Code
  
  • Casanueva Annalí
  • Rossi Davide
  • Zacchiroli Stefano
  • Zimmermann Théo
  Empirical Software Engineering, Springer Verlag, 2024. Despite its promise of openness and inclusiveness, the development of free and open source software (FOSS) remains significantly unbalanced in terms of gender representation among contributors. To assist open source project maintainers and communities in addressing this imbalance, it is crucial to understand the causes of this inequality. In this study, we aim to establish how the COVID-19 pandemic has influenced the ability of women to contribute to public code. To do so, we use the Software Heritage archive, which holds the largest dataset of commits to public code, and the difference in differences (DID) methodology from econometrics that enables the derivation of causality from historical data. Our findings show that the COVID-19 pandemic has disproportionately impacted women's ability to contribute to the development of public code, relatively to men. Further, our observations of specific contributor subgroups indicate that COVID-19 particularly affected women hobbyists, identified using contribution patterns and email address domains. (10.1007/s10664-024-10552-7)
  DOI : 10.1007/s10664-024-10552-7
• Completeness, Recall, and Negation in Open-World Knowledge Bases: A Survey
  
  • Suchanek Fabian M.
  • Razniewski Simon
  • Arnaout Hiba
  • Ghosh Shrestha
  ACM Computing Surveys, Association for Computing Machinery, 2024. General-purpose knowledge bases (KBs) are a cornerstone of knowledge-centric AI. Many of them are constructed pragmatically from web sources, and are thus far from complete. This poses challenges for the consumption as well as the curation of their content. While several surveys target the problem of completing incomplete KBs, the first problem is arguably to know whether and where the KB is incomplete in the first place, and to which degree. In this survey, we discuss how knowledge about completeness, recall, and negation in KBs can be expressed, extracted, and inferred. We cover (i) the logical foundations of knowledge representation and querying under partial closed-world semantics; (ii) the estimation of this information via statistical patterns; (iii) the extraction of information about recall from KBs and text; (iv) the identification of interesting negative statements; and (v) relaxed notions of relative recall. This survey is targeted at two types of audiences: (1) practitioners who are interested in tracking KB quality, focusing extraction efforts, and building quality-aware downstream applications; and (2) data management, knowledge base and semantic web researchers who wish to understand the state of the art of knowledge bases beyond the open-world assumption. Consequently, our survey presents both fundamental methodologies and the results that they have produced, and gives practice-oriented recommendations on how to choose between different approaches for a problem at hand. CCS Concepts: • General and reference → Surveys and overviews; • Computing methodologies → Knowledge representation and reasoning; Artificial intelligence.
• Exploring the potential of representation and transfer learning for anatomical neuroimaging: application to psychiatry
  
  • Dufumier Benoit
  • Gori Pietro
  • Petiton Sara
  • Louiset Robin
  • Mangin Jean-François
  • Grigis Antoine
  • Duchesnay Edouard
  NeuroImage, Elsevier, 2024. The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimagingbased prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modelling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging dataset (N ≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N ≤ 1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity of learning meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry.