1 code implementation • NeurIPS 2021 • Pablo Barceló, Floris Geerts, Juan Reutter, Maksimilian Ryschkov
We propose local graph parameter enabled GNNs as a framework for studying the latter kind of approaches and precisely characterize their distinguishing power, in terms of a variant of the WL test, and in terms of the graph structural properties that they can take into account.
1 code implementation • NeurIPS 2023 • Xingyue Huang, Miguel Romero Orth, İsmail İlkan Ceylan, Pablo Barceló
Our goal is to provide a systematic understanding of the landscape of graph neural networks for knowledge graphs pertaining to the prominent task of link prediction.
1 code implementation • NeurIPS 2021 • Marcelo Arenas, Daniel Baez, Pablo Barceló, Jorge Pérez, Bernardo Subercaseaux
Several queries and scores have recently been proposed to explain individual predictions over ML models.
no code implementations • ICLR 2019 • Jorge Pérez, Javier Marinković, Pablo Barceló
Alternatives to recurrent neural networks, in particular, architectures based on attention or convolutions, have been gaining momentum for processing input sequences.
no code implementations • ICLR 2020 • Pablo Barceló, Egor V. Kostylev, Mikael Monet, Jorge Pérez, Juan Reutter, Juan Pablo Silva
We show that this class of GNNs is too weak to capture all FOC2 classifiers, and provide a syntactic characterization of the largest subclass of FOC2 classifiers that can be captured by AC-GNNs.
no code implementations • NeurIPS 2020 • Pablo Barceló, Mikaël Monet, Jorge Pérez, Bernardo Subercaseaux
We prove that this notion provides a good theoretical counterpart to current beliefs on the interpretability of models; in particular, we show that under our definition and assuming standard complexity-theoretical assumptions (such as P$\neq$NP), both linear and tree-based models are strictly more interpretable than neural networks.
no code implementations • 16 Apr 2021 • Marcelo Arenas, Pablo Barceló, Leopoldo Bertossi, Mikaël Monet
While in general computing Shapley values is an intractable problem, we prove a strong positive result stating that the $\mathsf{SHAP}$-score can be computed in polynomial time over deterministic and decomposable Boolean circuits.
no code implementations • 30 Jun 2022 • Marcelo Arenas, Pablo Barceló, Miguel Romero, Bernardo Subercaseaux
Formal XAI (explainable AI) is a growing area that focuses on computing explanations with mathematical guarantees for the decisions made by ML models.
no code implementations • 3 Nov 2022 • Pablo Barceló, Mauricio Duarte, Cristóbal Rojas, Tomasz Steifer
It may be assumed that each reviewer has her own mapping from the set of features to a recommendation, and that different reviewers have different mappings in mind.
no code implementations • 22 Mar 2023 • Valentino Delle Rose, Alexander Kozachinskiy, Cristóbal Rojas, Mircea Petrache, Pablo Barceló
Our main result states that the $(d-1)$-dimensional WL test is complete for point clouds in $d$-dimensional Euclidean space, for any $d\ge 2$, and that only three iterations of the test suffice.
no code implementations • 29 Sep 2023 • Matthias Lanzinger, Pablo Barceló
A central focus of research in this field revolves around determining the least dimensionality $k$, for which $k$WL can discern graphs with different number of occurrences of a pattern graph $P$.
no code implementations • 6 Oct 2023 • Pablo Barceló, Tamara Cucumides, Floris Geerts, Juan Reutter, Miguel Romero
The problem of answering logical queries over incomplete knowledge graphs is receiving significant attention in the machine learning community.
no code implementations • 6 Feb 2024 • Xingyue Huang, Miguel Romero Orth, Pablo Barceló, Michael M. Bronstein, İsmail İlkan Ceylan
In this paper, we propose two frameworks for link prediction with relational hypergraphs and conduct a thorough analysis of the expressive power of the resulting model architectures via corresponding relational Weisfeiler-Leman algorithms, and also via some natural logical formalisms.