Publications

Qu’est-ce que mon GNN capture vraiment ? Exploration des représentations internes d’un GNN

By Luca Veyrin-Forrer, Ataollah Kamal, Stefan Duffner, Marc Plantevit, Céline Robardet

2022-03-24

In Extraction et gestion des connaissances, EGC 2022, blois, france, 24 au 28 janvier 2022

Abstract

While existing GNN’s explanation methods explain the decision by studying the output layer, we propose a method that analyzes the hidden layers to identify the neurons that are co-activated for a class. We associate to them a graph.

Continue reading

Local intensity order transformation for robust curvilinear object segmentation

By Tianyi Shi, Nicolas Boutry, Yongchao Xu, Thierry Géraud

2022-03-22

In IEEE Transactions on Image Processing

Abstract

Segmentation of curvilinear structures is important in many applications, such as retinal blood vessel segmentation for early detection of vessel diseases and pavement crack segmentation for road condition evaluation and maintenance. Currently, deep learning-based methods have achieved impressive performance on these tasks. Yet, most of them mainly focus on finding powerful deep architectures but ignore capturing the inherent curvilinear structure feature (e.g., the curvilinear structure is darker than the context) for a more robust representation. In consequence, the performance usually drops a lot on cross-datasets, which poses great challenges in practice. In this paper, we aim to improve the generalizability by introducing a novel local intensity order transformation (LIOT). Specifically, we transfer a gray-scale image into a contrast- invariant four-channel image based on the intensity order between each pixel and its nearby pixels along with the four (horizontal and vertical) directions. This results in a representation that preserves the inherent characteristic of the curvilinear structure while being robust to contrast changes. Cross-dataset evaluation on three retinal blood vessel segmentation datasets demonstrates that LIOT improves the generalizability of some state-of-the-art methods. Additionally, the cross-dataset evaluation between retinal blood vessel segmentation and pavement crack segmentation shows that LIOT is able to preserve the inherent characteristic of curvilinear structure with large appearance gaps. An implementation of the proposed method is available at https://github.com/TY-Shi/LIOT.

Continue reading

Electricity price forecasting on the day-ahead market using machine learning

Abstract

The price of electricity on the European market is very volatile. This is due both to its mode of production by different sources, each with its own constraints (volume of production, dependence on the weather, or production inertia), and by the difficulty of its storage. Being able to predict the prices of the next day is an important issue, to allow the development of intelligent uses of electricity. In this article, we investigate the capabilities of different machine learning techniques to accurately predict electricity prices. Specifically, we extend current state-of-the-art approaches by considering previously unused predictive features such as price histories of neighboring countries. We show that these features significantly improve the quality of forecasts, even in the current period when sudden changes are occurring. We also develop an analysis of the contribution of the different features in model prediction using Shap values, in order to shed light on how models make their prediction and to build user confidence in models.

Continue reading

Max-tree computation on GPUs

By Nicolas Blin, Edwin Carlinet, Florian Lemaitre, Lionel Lacassagne, Thierry Géraud

2022-03-09

In IEEE Transactions on Parallel and Distributed Systems

Abstract

In Mathematical Morphology, the max-tree is a region-based representation that encodes the inclusion relationship of the threshold sets of an image. This tree has been proven useful in numerous image processing applications. For the last decade, works have been led to improve the building time of this structure; mixing algorithmic optimizations, parallel and distributed computing. Nevertheless, there is still no algorithm that takes benefit from the computing power of the massively parallel architectures. In this work, we propose the first GPU algorithm to compute the max-tree. The proposed approach leads to significant speed-ups, and is up to one order of magnitude faster than the current State-of-the-Art parallel CPU algorithms. This work paves the way for a max-tree integration in image processing GPU pipelines and real-time image processing based on Mathematical Morphology. It is also a foundation for porting other image representations from Mathematical Morphology on GPUs.

Continue reading

Anomaly detection on static and dynamic graphs using graph convolutional neural networks

By Amani Abou Rida, Rabih Amhaz, Pierre Parrend

2022-03-01

In Robotics and AI for cybersecurity and critical infrastructure in smart cities

Abstract

Anomalies represent rare observations that vary significantly from others. Anomaly detection intended to discover these rare observations has the power to prevent detrimental events, such as financial fraud, network intrusion, and social spam. However, conventional anomaly detection methods cannot handle this problem well because of the complexity of graph data (e.g., irregular structures, relational dependencies, node/edge types/attributes/directions/multiplicities/weights, large scale, etc.) [1]. Thanks to the rise of deep learning in solving these limitations, graph anomaly detection with deep learning has obtained an increasing attention from many scientists recently. However, while deep learning can capture unseen patterns of multi-dimensional Euclidean data, there is a huge number of applications where data are represented in the form of graphs. Graphs have been used to represent the structural relational information, which raises the graph anomaly detection problem - identifying anomalous graph objects (i.e., vertex, edges, sub-graphs, and change detection). These graphs can be constructed as a static graph, or a dynamic graph based on the availability of timestamp. Recent years have observed a huge efforts on static graphs, among which Graph Convolutional Network (GCN) has appeared as a useful class of models. A challenge today is to detect anomalies with dynamic structures. In this chapter, we aim at providing methods used for detecting anomalies in static and dynamic graphs using graph analysis, graph embedding, and graph convolutional neural networks. For static graphs we categorize these methods according to plain and attribute static graphs. For dynamic graphs we categorize existing methods according to the type of anomalies that they can detect. Moreover, we focus on the challenges in this research area and discuss the strengths and weaknesses of various methods in each category. Finally, we provide open challenges for graph anomaly detection using graph convolutional neural networks on dynamic graphs.

Continue reading

ETAP: Experimental typesetting algorithms platform

By Didier Verna

2022-03-01

In ELS 2022, the 15th european lisp symposium

Abstract

We present the early development stages of ETAP, a platform for experimenting with typesetting algorithms. The purpose of this platform is twofold: while its primary objective is to provide building blocks for quickly and easily designing and testing new algorithms (or variations on existing ones), it can also be used as an interactive, real time demonstrator for many features of digital typography, such as kerning, hyphenation, or ligaturing.

Continue reading

New security protocols for offline point-of-sale machines

By Nour El Madhoun, Emmanuel Bertin, Mohamad Badra, Guy Pujolle

2022-03-01

In The 36th international conference on advanced information networking and applications (AINA-2022)

Abstract

EMV (Europay MasterCard Visa) is the protocol implemented to secure the communication, between a client’s payment device and a Point-of-Sale machine, during a contact or an NFC (Near Field Communication) purchase transaction. In several studies, researchers have analyzed the operation of this protocol in order to verify its safety: unfortunately, they have identified two security vulnerabilities that lead to multiple attacks and dangerous risks threatening both clients and merchants. In this paper, we are interested in proposing new security solutions that aim to overcome the two dangerous EMV vulnerabilities. Our solutions address the case of Point-of-Sale machines that do not have access to the banking network and are therefore in the “offline” connectivity mode. We verify the accuracy of our proposals by using the Scyther security verification tool.

Continue reading

How to boost close-range remote sensing courses using a serious game: Uncover in a fun way the complexity and transversality of multi-domain field acquisitions

Abstract

Close-range remote sensing, and more particularly, its acquisition part that is linked to field robotics, is at the crossroads of many scientific and engineering fields. Thus, it takes time for students to acquire the solid foundations needed before practicing on real systems. Therefore, we are interested in a means that allow students without prerequisites to quickly appropriate the fundamentals of this interdisciplinary field. For this, we adapted a haggle game to the close-range remote sensing theme. In this article, we explain the mechanics that serve our educational purposes. We have used it, so far, for four academic years with hundreds of students. The experience was assessed through quality surveys and quizzes to calculate success indicators. The results show that the serious game is well appreciated by the students. It allows them to better structure information and acquire a good global vision of multi-domain acquisition and data processing in close-range remote sensing. The students are also more involved in the rest of the lessons; all of this helps to facilitate their learning of the theoretical parts. Thus, we were able to shorten the time before moving on to real practice by replacing three lesson sessions with one serious game session, with an increase in mastering fundamental skills. The designed serious game can be useful for close-range remote sensing teachers looking for an effective starting lesson. In addition, teachers from other technical fields can draw inspiration from the creation mechanisms described in this article to create their own adapted version. Such a serious game is also a good asset for selecting promising students in a recruitment context.

Continue reading

Practical applications of the Alternating Cycle Decomposition

By Antonio Casares, Alexandre Duret-Lutz, Klara J. Meyer, Florian Renkin, Salomon Sickert

2022-02-01

In Proceedings of the 28th international conference on tools and algorithms for the construction and analysis of systems (TACAS’22)

Abstract

In 2021, Casares, Colcombet, and Fijalkow introduced the Alternating Cycle Decomposition (ACD) to study properties and transformations of Muller automata. We present the first practical implementation of the ACD in two different tools, Owl and Spot, and adapt it to the framework of Emerson-Lei automata, i.e., $\omega$-automata whose acceptance conditions are defined by Boolean formulas. The ACD provides a transformation of Emerson-Lei automata into parity automata with strong optimality guarantees: the resulting parity automaton is minimal among those automata that can be obtained by duplication of states. Our empirical results show that this transformation is usable in practice. Further, we show how the ACD can generalize many other specialized constructions such as deciding typeness of automata and degeneralization of generalized Büchi automata, providing a framework of practical algorithms for $\omega$-automata.

Continue reading