This paper addresses the problem of learning an undirected graph from data gathered at each node. Within Gaussian graphical models (GGM), the topology of such graph can be linked to the support of the conditional correlation matrix of the data. The corresponding graph learning problem then scales as the square of number of variables (nodes), which is usually problematic for large dimension. To tackle this issue, we propose a graph learning framework that leverages a low-rank factorization of the conditional correlation matrix. In order to solve the resulting optimization problem, we derive tools required to apply Riemannian optimization techniques for this particular structure. The proposal is then particularized to a low-rank constrained counterpart of the standard GGM estimation problem, i.e., the regularized maximum likelihood estimation of a precision matrix. Experiments on synthetic and real data demonstrate that a very efficient dimension-versus-performance trade-off can be achieved with this approach.
Inter-modal image registration (IMIR) and image segmentation with abdominal Ultrasound (US) data have many important clinical applications, including image-guided surgery, automatic organ measurement, and robotic navigation. However, research is severely limited by the lack of public datasets. We propose TRUSTED (the Tridimensional Renal Ultra Sound TomodEnsitometrie Dataset), comprising paired transabdominal 3DUS and CT kidney images from 48 human patients (96 kidneys), including segmentation, and anatomical landmark annotations by two experienced radiographers. Inter-rater segmentation agreement was over 93% (Dice score), and gold-standard segmentations were generated using the STAPLE algorithm. Seven anatomical landmarks were annotated, for IMIR systems development and evaluation. To validate the dataset's utility, 4 competitive Deep-Learning models for kidney segmentation were benchmarked, yielding average DICE scores from 79.63% to 90.09% for CT, and 70.51% to 80.70% for US images. Four IMIR methods were benchmarked, and Coherent Point Drift performed best with an average Target Registration Error of 4.47 mm and Dice score of 84.10%. The TRUSTED dataset may be used freely to develop and validate segmentation and IMIR methods.
Meeting the Sustainable Development Goals (SDGs) established by the United Nations, presents a large-scale challenge for all countries. To monitor progress towards these goals, there is a need to develop key performance indicators using existing data and metadata. The computation of the indicators requires integrating and analyzing heterogeneous datasets, in particular web open data. This approach aims to highlight the positive impact of the web on the society. However, the diversity of web data sources and formats raises major issues in terms of structuring and integration. Despite the abundance of open data and metadata, its exploitation remains limited, leaving untapped potential for guiding urban policies towards sustainability. We have so far introduced a novel approach for SDG indicator computation, leveraging the capabilities of Large Language Models (LLMs) and Knowledge Graphs (KGs). We have proposed a method that combines rule-based filtering with LLM-powered schema mapping to establish semantic correspondences between diverse data sources and SDG indicators, including disaggregated attributes. Our approach integrated these mappings into a KG, which enables indicator computation by querying graphs topology. Finally, we have evaluated our method through a case study focusing on the SDG Indicator 11.7.1 about accessibility of public open spaces. Our experimental results are promising showing significant improvements compared to traditional schema matching techniques.
The inclusive education paradigm aims to provide every student equal-learning opportunities at school. However, numerous barriers remain. Among these, teachers' beliefs about students with disabilities constitute a key obstacle. Research has shown that individuals with disabilities, and students with disabilities in particular, are often perceived as less competent compared to others. This finding has been obtained using various paradigms, most often involving lay participants. The present study, based on a large, nationwide sample with post-stratification checks, seeks to replicate these results in the overlooked context of France. To this end, educators completed two complementary measures: a self-reported questionnaire and an Implicit Association Test, both designed to assess the perceived or associated competence of students and people with disabilities, respectively. Results from both measures confirmed that incompetence is always more strongly associated with disability. The findings are discussed with regard to the necessity - and the potential risks - of emphasising the diversity of this minority group (e.g. in teachers' training) to reduce stigmatisation and enable students with disabilities to fully benefit from their educational journey.
In this article, we present a novel approach to program analysis through selective concrete execution. While static analysis of ELF binaries is necessarily limited by the theoretical undecidability of control-flow and data-flow analysis algorithms, we detail a new approach to reverse engineering through selective concrete execution of arbitrary functions within a x86_64 GNU/Linux binary by transforming ELF applications into shared libraries. This approach, named "procedural debugging", allows us to empirically recover information about function parameters and return values without resorting to any disassembly or decompilation, which are undecidable in general. In turn, this dynamic approach may be used as a feedback loop into existing program analyzers, being them static, fuzzing, symbolic, or concolic, to enrich their understanding of application interfaces. We publish an open-source framework, named the Witchcraft Compiler Collection, under a permissive MIT/BSD license, implementing binary libification, procedural debugging, and automatic function prototype annotations with the hope of benefiting the security community.
