599 citations · 823 across the 38 of their papers we have counts for
47 papers
Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets
Ali Ramlaoui, Daniel T. Speckhard, Sagar Pal +3
Atomistic machine learning datasets are increasingly used for training: large immutable snapshots are read repeatedly, shuffled across epochs, staged across clusters' storage syste…
Scaling Higher-Order Graph Learning with Maximal Clique Complexes
Antoine Vialle, Aref Einizade, Fragkiskos D. Malliaros +1
Graph neural networks (GNNs) are limited to modeling pairwise interactions, while higher-order models based on cell complexes achieve greater expressivity but often suffer from poo…
TriForces: Augmenting Atomistic GNNs for Transferable Representations
Ali Ramlaoui, Alexandre Duval, Hannah Bull +4
Machine learning interatomic potentials (MLIPs) achieve excellent accuracy when trained on large Density Functional Theory (DFT) data. To be useful in practice, they must often be…
Generalization Bounds for Spectral GNNs via Fourier Domain Analysis
Vahan A. Martirosyan, Daniele Malitesta, Hugues Talbot +2
Spectral graph neural networks learn graph filters, but their behavior with increasing depth and polynomial order is not well understood. We analyze these models in the graph Fouri…
Training-free Graph-based Imputation of Missing Modalities in Multimodal Recommendation
Daniele Malitesta, Emanuele Rossi, Claudio Pomo +2
Multimodal recommender systems (RSs) represent items in the catalog through multimodal data (e.g., product images and descriptions) that, in some cases, might be noisy or (even wor…
Retrieval-Constrained Decoding Reveals Underestimated Parametric Knowledge in Language Models
Rajaa El Hamdani, Samy Haffoudhi, Nils Holzenberger +3
Language models (LMs) encode substantial factual knowledge, but often produce answers judged as incorrect. We hypothesize that many of these answers are actually correct, but are e…
Second-Order Tensorial Partial Differential Equations on Graphs
Aref Einizade, Fragkiskos D. Malliaros, Jhony H. Giraldo
Processing data on multiple interacting graphs is crucial for many applications, but existing approaches rely mostly on discrete filtering or first-order continuous models, dampeni…
ADMP-GNN: Adaptive Depth Message Passing GNN
Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer +1
Graph Neural Networks (GNNs) have proven to be highly effective in various graph learning tasks. A key characteristic of GNNs is their use of a fixed number of message-passing step…
Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks
Hugo Attali, Thomas Papastergiou, Nathalie Pernelle +1
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 topolog…
FAROS: Fair Graph Generation via Attribute Switching Mechanisms
Abdennacer Badaoui, Oussama Kharouiche, Hatim Mrabet +2
Recent advancements in graph diffusion models (GDMs) have enabled the synthesis of realistic network structures, yet ensuring fairness in the generated data remains a critical chal…
Piecewise Constant Spectral Graph Neural Network
Vahan Martirosyan, Jhony H. Giraldo, Fragkiskos D. Malliaros
Graph Neural Networks (GNNs) have achieved significant success across various domains by leveraging graph structures in data. Existing spectral GNNs, which use low-degree polynomia…
Continuous Simplicial Neural Networks
Aref Einizade, Dorina Thanou, Fragkiskos D. Malliaros +1
Simplicial complexes provide a powerful framework for modeling higher-order interactions in structured data, making them particularly suitable for applications such as trajectory p…
A Fused Gromov-Wasserstein Approach to Subgraph Contrastive Learning
Amadou S. Sangare, Nicolas Dunou, Jhony H. Giraldo +1
Self-supervised learning has become a key method for training deep learning models when labeled data is scarce or unavailable. While graph machine learning holds great promise acro…
Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields
Yassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer +2
Graph Neural Networks (GNNs), which are nowadays the benchmark approach in graph representation learning, have been shown to be vulnerable to adversarial attacks, raising concerns…
Centrality Graph Shift Operators for Graph Neural Networks
Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer +1
Graph Shift Operators (GSOs), such as the adjacency and graph Laplacian matrices, play a fundamental role in graph theory and graph representation learning. Traditional GSOs are ty…
Higher-Order GNNs Meet Efficiency: Sparse Sobolev Graph Neural Networks
Jhony H. Giraldo, Aref Einizade, Andjela Todorovic +4
Graph Neural Networks (GNNs) have shown great promise in modeling relationships between nodes in a graph, but capturing higher-order relationships remains a challenge for large-sca…
Graph Neural Network Generalization with Gaussian Mixture Model Based Augmentation
Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer +2
Graph Neural Networks (GNNs) have shown great promise in tasks like node and graph classification, but they often struggle to generalize, particularly to unseen or out-of-distribut…
The Factuality of Large Language Models in the Legal Domain
Rajaa El Hamdani, Thomas Bonald, Fragkiskos Malliaros +2
This paper investigates the factuality of large language models (LLMs) as knowledge bases in the legal domain, in a realistic usage scenario: we allow for acceptable variations in…
How Fair is Your Diffusion Recommender Model?
Daniele Malitesta, Giacomo Medda, Erasmo Purificato +3
Diffusion-based learning has settled as a rising paradigm in generative recommendation, outperforming traditional approaches built upon variational autoencoders and generative adve…
Do We Really Need to Drop Items with Missing Modalities in Multimodal Recommendation?
Daniele Malitesta, Emanuele Rossi, Claudio Pomo +2
Generally, items with missing modalities are dropped in multimodal recommendation. However, with this work, we question this procedure, highlighting that it would further damage th…
Improving Molecular Modeling with Geometric GNNs: an Empirical Study
Ali Ramlaoui, Théo Saulus, Basile Terver +4
Rapid advancements in machine learning (ML) are transforming materials science by significantly speeding up material property calculations. However, the proliferation of ML approac…
Cometh: A continuous-time discrete-state graph diffusion model
Antoine Siraudin, Fragkiskos D. Malliaros, Christopher Morris
Discrete-state denoising diffusion models led to state-of-the-art performance in graph generation, especially in the molecular domain. Recently, they have been transposed to contin…
Spatiotemporal Forecasting Meets Efficiency: Causal Graph Process Neural Networks
Aref Einizade, Fragkiskos D. Malliaros, Jhony H. Giraldo
Graph Neural Networks (GNNs) have advanced spatiotemporal forecasting by leveraging relational inductive biases among sensors (or any other measuring scheme) represented as nodes i…
Continuous Product Graph Neural Networks
Aref Einizade, Fragkiskos D. Malliaros, Jhony H. Giraldo
Processing multidomain data defined on multiple graphs holds significant potential in various practical applications in computer science. However, current methods are mostly limite…