Publications (19)
Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study
Lena Podina, Christina Humer, Alexandre Duval +7
Efficient and inexpensive energy storage is essential for accelerating the adoption of renewable energy and ensuring a stable supply, despite fluctuations in sources such as wind a…
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…
LeMat-Bulk: aggregating, and de-duplicating quantum chemistry materials databases
Martin Siron, Inel Djafar, Ali Ramlaoui +10
The rapid expansion of materials science databases has driven machine learning-based discovery while also posing challenges in data integration, duplication, and interoperability.…
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…
LeMat-Traj: A Scalable and Unified Dataset of Materials Trajectories for Atomistic Modeling
Ali Ramlaoui, Martin Siron, Inel Djafar +4
The development of accurate machine learning interatomic potentials (MLIPs) is limited by the fragmented availability and inconsistent formatting of quantum mechanical trajectory d…
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
Alexandre Duval, Simon V. Mathis, Chaitanya K. Joshi +7
Recent advances in computational modelling of atomic systems, spanning molecules, proteins, and materials, represent them as geometric graphs with atoms embedded as nodes in 3D Euc…
On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions
Alvaro Carbonero, Alexandre Duval, Victor Schmidt +4
The use of machine learning for material property prediction and discovery has traditionally centered on graph neural networks that incorporate the geometric configuration of all a…
GraphSVX: Shapley Value Explanations for Graph Neural Networks
Alexandre Duval, Fragkiskos D. Malliaros
Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data due to the incorporation of graph structure into the learning of node repr…
EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
Yi-Lun Liao, Alexander J. Hoffman, Sabrina C. Shen +3
As -equivariant graph neural networks mature as a core tool for 3D atomistic modeling, improving their efficiency, expressivity, and physical consistency has become a centra…
The eyes and hearts of UAV pilots: observations of physiological responses in real-life scenarios
Alexandre Duval, Anita Paas, Abdalwhab Abdalwhab +1
The drone industry is diversifying and the number of pilots increases rapidly. In this context, flight schools need adapted tools to train pilots, most importantly with regard to t…
FAENet: Frame Averaging Equivariant GNN for Materials Modeling
Alexandre Duval, Victor Schmidt, Alex Hernandez Garcia +4
Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to specific symmetries. While graph neural netwo…
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…
Higher-order Clustering and Pooling for Graph Neural Networks
Alexandre Duval, Fragkiskos Malliaros
Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks, especially due to pooling operators, which aggregate learned node embeddings…
LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models
Siddharth Betala, Samuel P. Gleason, Ali Ramlaoui +12
Generative machine learning (ML) models hold great promise for accelerating materials discovery through the inverse design of inorganic crystals, enabling an unprecedented explorat…
LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature
Magdalena Lederbauer, Siddharth Betala, Xiyao Li +16
The development of synthesis procedures remains a fundamental challenge in materials discovery, with procedural knowledge scattered across decades of scientific literature in unstr…
PhAST: Physics-Aware, Scalable, and Task-specific GNNs for Accelerated Catalyst Design
Alexandre Duval, Victor Schmidt, Santiago Miret +3
Mitigating the climate crisis requires a rapid transition towards lower-carbon energy. Catalyst materials play a crucial role in the electrochemical reactions involved in numerous…
Crystal-GFN: sampling crystals with desirable properties and constraints
Mila AI4Science, :, Alex Hernandez-Garcia +11
The discovery of novel solid-state materials, such as electrocatalysts, super-ionic conductors, or photovoltaic materials, plays a critical role in addressing various global challe…
Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models
Alexandre Duval, Thomas Lamson, Gael de Leseleuc de Kerouara +1
It is standard procedure these days to solve Information Extraction task by fine-tuning large pre-trained language models. This is not the case for generation task, which relies on…
Adsorption energies are necessary but not sufficient to identify good catalysts
Shahana Chatterjee, Alexander Davis, Lena Podina +7
As a core technology for green chemical synthesis and electrochemical energy storage, electrocatalysis is central to decarbonization strategies aimed at combating climate change. I…