Graph Neural Networks (GNNs) have emerged as the leading paradigm for learning over graph-structured data. However, their performance is limited by issues inherent to graph topology, most notably oversquashing and oversmoothing. Recent advances in graph rewiring aim to mitigate these limitations by modifying the graph topology to promote more effective information propagation. In this work, we introduce TRIGON, a novel framework that constructs enriched, non-planar triangulations by learning to select relevant triangles from multiple graph views. By jointly optimizing triangle selection and downstream classification performance, our method produces a rewired graph with markedly improved structural properties such as reduced diameter, increased spectral gap, and lower effective resistance compared to existing rewiring methods. Empirical results demonstrate that TRIGON outperforms state-of-the-art approaches on node classification tasks across a range of homophilic and heterophilic benchmarks.

International audience

GNNs rely on the exchange of messages to distribute information along the edges of the graph. This approach makes the efficiency of architectures highly dependent on the specific structure of the input graph. Certain graph topologies lead to inefficient information propagation, resulting in a phenomenon known as over-squashing. While the majority of existing methods address over-squashing by rewiring the input graph, our novel approach involves constructing a graph directly from features using Delaunay Triangulation. We posit that the topological properties of the resulting graph prove advantageous for mitigate oversmoothing and over-squashing. Our extensive experimentation demonstrates that our method consistently outperforms established graph rewiring methods.

In recent years, keen interest towards Knowledge Graphs has increased in both academia and the industry which has led to the creation of various datasets and the development of different research topics. In this paper, we present an approach that discovers differential causal rules in Knowledge Graphs. Such rules express that for two different class instances, a different treatment leads to different outcomes. Discovering causal rules is often the key of experiments, independently of their domain. The proposed approach is based on semantic matching relying on community detection and strata that can be defined as complex sub-classes. An experimental evaluation on two datasets shows that such mined rules can help gain insights into various domains.

Since 1997, the production, import and sale of asbestos\footnoteNaturally occurring mineral fibres which were used due to their insulating properties. have been banned in France. However, there are still millions of tons scattered in factories, buildings, or hospitals. In this paper we propose a method for predicting the presence of asbestos products in buildings based on temporal data that describes the probability of the presence of asbestos in marketed products.

International audience

This paper deals with the representation of multi-valued data by clustering them in a small number of classes organized in a hierarchy and described at an appropriate level of abstraction. The contribution of this paper is three fold. First, we investigate a partial order, namely nesting, relating Galois lattices. A nested Galois lattice is obtained by reducing (through projections) the original lattice. As a consequence it makes coarser the equivalence relations defined on extents and intents. Second we investigate the intensional and extensional aspects of the languages used in our system ZooM. In particular we discuss the notion of α-extension of terms of a class language £. We also present our most expressive language £3, close to a description logic, and which expresses optionality or/and multi-valuation of attributes. Finally, the nesting order between the Galois lattices corresponding to various languages and extensions is exploited in the interactive system ZooM. Typically a ZooM session starts from a propositional language £2 and a coarse view of the data (through α-extension). Then the user selects two ordered nodes in the lattice and ZooM constructs a fine-grained lattice between the antecedents of these nodes. So the general purpose of ZooM is to give a general view of concepts addressing a large data set, then focussing on part of this coarse taxonomy.